beyhan/graphify
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(install): add cross-framework agents platform (+ skills alias)

Browse Source 
`graphify install --platform agents` installs the skill to the generic
Agent-Skills locations: the spec's user-global ~/.agents/skills (global) and
./.agents/skills (--project) — the directories `npx skills` and spec-compliant
frameworks read. `--platform skills` is an alias. Previously that user-global
location was only reachable as an accidental side effect of the gemini-on-Windows
branch. Bare `graphify install` is unchanged (still single-platform claude/windows).

The platform is registered in tools/skillgen/platforms.toml (split, mirroring
amp's agents-md body) and rendered through the skillgen drift/coverage guards.
Since it is a post-v8 platform with no own v8 body, its --audit-coverage baseline
is amp's v8 body (the body it re-homes). The rendered skill body is byte-identical
to amp's; only the on-demand hooks reference differs (its own `graphify agents
install` wording).

The `graphify agents install` / `graphify skills install` subcommand is the
amp-twin: it also wires an AGENTS.md always-on section, keeping it honest with the
hooks reference it points at. The `--platform agents` path stays skill-only,
exactly as amp's `--platform amp` does.

Also: `skill-agents.md` added to package-data, and the wheel-packaging guard now
covers every platform's skill body (not just references/always-on), so a missing
skill body fails CI instead of only breaking install for real users.

Closes #1405. Implements #1432.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
tpateeq
2026-06-23 17:26:49 +01:00
committed by safishamsi
co-authored by Claude Opus 4.8
parent 29fd98fd04
commit ad6cb753c0
27 changed files with 3446 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+2
View File
@@ -4,6 +4,8 @@ Full release notes with details on each version: [GitHub Releases](https://githu
## Unreleased
- Feat: new first-class `agents` platform installs the skill to the generic cross-framework Agent-Skills locations. `graphify install --platform agents` (alias `--platform skills`) writes the spec's user-global `~/.agents/skills/graphify/SKILL.md` — the directory `npx skills` and spec-compliant frameworks read — and `--project` writes `./.agents/skills/graphify/SKILL.md`; `graphify uninstall` removes them. Previously that user-global location was only reachable as an accidental side effect of the gemini-on-Windows branch. The skill bundle re-homes amp's agents-md body (registered in `tools/skillgen/platforms.toml`, rendered through the skillgen drift/coverage guards); the body is identical to amp's, and only the on-demand hooks reference differs — it points at `graphify agents install`, which (as the amp-twin subcommand) wires the skill plus an AGENTS.md always-on section. Bare `graphify install` is unchanged — still single-platform (claude/windows) (#1432, closes #1405).
## 0.8.46 (2026-06-23)
- Perf: graph queries on large graphs are faster via a trigram candidate prefilter in the MCP/CLI query path. A trigram→node index (built once per graph and rebuilt on hot-reload) narrows the candidate set before the IDF-weighted scorer runs, cutting the previous O(N) scan. The prefilter is a strict superset of the exhaustive scorer (it indexes `norm_label`, `label_tokens`, `nid`, and `source_file`), so results and ranking are unchanged; short/CJK queries and low-selectivity terms fall back to the full scan (#1431; thanks @papinto).
README.md
+6
View File
@@ -142,6 +142,7 @@ for example `graphify claude install --project` or `graphify codex install --pro
| Hermes | `graphify install --platform hermes` |
| Kimi Code | `graphify install --platform kimi` |
| Amp | `graphify amp install` |
| Agent Skills (cross-framework) | `graphify install --platform agents` (alias `--platform skills`) |
| Kiro IDE/CLI | `graphify kiro install` |
| Pi coding agent | `graphify install --platform pi` |
| Cursor | `graphify cursor install` |
@@ -150,6 +151,8 @@ for example `graphify claude install --project` or `graphify codex install --pro
Codex users also need `multi_agent = true` under `[features]` in `~/.codex/config.toml` for parallel extraction. CodeBuddy uses the same Agent tool and PreToolUse hook mechanism as Claude Code. Factory Droid uses the `Task` tool for parallel subagent dispatch. OpenClaw and Aider use sequential extraction (parallel agent support is still early on those platforms). Trae uses the Agent tool for parallel subagent dispatch and does **not** support PreToolUse hooks — AGENTS.md is the always-on mechanism.
`--platform agents` (alias `--platform skills`) targets the generic cross-framework [Agent-Skills](https://github.com/anthropics/skills) locations: the spec's user-global `~/.agents/skills/` (read by `npx skills` and spec-compliant frameworks) for a global install, and `./.agents/skills/` for a project (`--project`) install. The bare `graphify install` stays single-platform (Claude Code) by design — use the named `agents` platform when you want the skill discoverable by any framework that reads `.agents/skills`.
> Codex uses `$graphify` instead of `/graphify`.
### Optional extras
@@ -205,6 +208,7 @@ Run this once in your project after building a graph:
| Hermes | `graphify hermes install` |
| Kimi Code | `graphify install --platform kimi` |
| Amp | `graphify amp install` |
| Agent Skills (cross-framework) | `graphify agents install` (alias `graphify skills install`) |
| Kiro IDE/CLI | `graphify kiro install` |
| Pi coding agent | `graphify pi install` |
| Devin CLI | `graphify devin install` |
@@ -571,6 +575,8 @@ graphify hermes install # AGENTS.md + ~/.hermes/skills/ (Hermes)
graphify hermes uninstall
graphify amp install # skill file (Amp)
graphify amp uninstall
graphify agents install # ~/.agents/skills/ + AGENTS.md (cross-framework; alias: graphify skills)
graphify agents uninstall
graphify kiro install # .kiro/skills/ + .kiro/steering/graphify.md (Kiro IDE/CLI)
graphify kiro uninstall
graphify pi install # skill file (Pi coding agent)
graphify/__main__.py
+76 -3
View File
@@ -171,6 +171,14 @@ def _platform_skill_destination(platform_name: str, *, project: bool = False, pr
return (project_dir or Path(".")) / ".agents" / "skills" / "graphify" / "SKILL.md"
return Path.home() / ".config" / "agents" / "skills" / "graphify" / "SKILL.md"
if platform_name == "agents":
# The generic Agent-Skills target: project ./.agents/skills, global the
# spec's user-global ~/.agents/skills (read by `npx skills` and compliant
# frameworks), NOT amp's ~/.config/agents/skills.
if project:
return (project_dir or Path(".")) / ".agents" / "skills" / "graphify" / "SKILL.md"
return Path.home() / ".agents" / "skills" / "graphify" / "SKILL.md"
if platform_name in ("antigravity", "antigravity-windows"):
if project:
return (project_dir or Path(".")) / ".agents" / "skills" / "graphify" / "SKILL.md"
@@ -550,6 +558,16 @@ _PLATFORM_CONFIG: dict[str, dict] = {
"claude_md": False,
"skill_refs": "amp",
},
"agents": {
# The generic cross-framework Agent-Skills target. Global: ~/.agents/skills
# (the spec's user-global location, read by `npx skills` and compliant
# frameworks); project: ./.agents/skills. The CLI accepts `skills` as an
# alias (see _canonical_platform). Ships its own rendered bundle.
"skill_file": "skill-agents.md",
"skill_dst": Path(".agents") / "skills" / "graphify" / "SKILL.md",
"claude_md": False,
"skill_refs": "agents",
},
"devin": {
# Monolith: devin ships the full SKILL.md inline, no references/ sidecar.
"skill_file": "skill-devin.md",
@@ -560,6 +578,16 @@ _PLATFORM_CONFIG: dict[str, dict] = {
},
}
# CLI-only platform aliases, resolved to a real _PLATFORM_CONFIG key before
# dispatch. `skills` is the friendly alias for the generic `agents` platform
# (the Agent-Skills ecosystem calls them "skills").
_PLATFORM_ALIASES: dict[str, str] = {"skills": "agents"}
def _canonical_platform(platform_name: str) -> str:
"""Resolve a CLI platform alias to its real _PLATFORM_CONFIG key."""
return _PLATFORM_ALIASES.get(platform_name, platform_name)
def _replace_or_append_section(content: str, marker: str, new_section: str) -> str:
"""Idempotently update or append a graphify-owned section in shared files.
@@ -638,6 +666,7 @@ def _print_banner() -> None:
def install(platform: str = "claude", *, project: bool = False, project_dir: Path | None = None) -> None:
_print_banner()
platform = _canonical_platform(platform)
if platform == "gemini":
gemini_install(project_dir=project_dir, project=project)
return
@@ -1627,9 +1656,32 @@ def _amp_uninstall(project_dir: Path | None = None) -> None:
_agents_uninstall(project_dir or Path("."), platform="amp")
def _agents_platform_install(project_dir: Path | None = None) -> None:
"""`graphify agents install`: skill into ~/.agents/skills + AGENTS.md.
The amp-twin of the generic Agent-Skills target. Mirrors _amp_install but
lands the skill at the spec's user-global ~/.agents/skills (set in
_platform_skill_destination). Wiring AGENTS.md keeps it honest with the
rendered hooks reference, which points at `graphify agents install`. The bare
`graphify install --platform agents` path stays skill-only (via install()),
exactly as amp's `--platform amp` does.
"""
_copy_skill_file("agents")
_agents_install(project_dir or Path("."), "agents")
def _agents_platform_uninstall(project_dir: Path | None = None) -> None:
"""`graphify agents uninstall`: remove the skill and the AGENTS.md section."""
removed = _remove_skill_file("agents")
if removed:
print("skill removed")
_agents_uninstall(project_dir or Path("."), platform="agents")
def _project_install(platform_name: str, project_dir: Path | None = None) -> None:
"""Install platform skill/config files in the current project."""
project_dir = project_dir or Path(".")
platform_name = _canonical_platform(platform_name)
if platform_name in ("claude", "windows"):
install(platform=platform_name, project=True, project_dir=project_dir)
claude_install(project_dir)
@@ -1662,7 +1714,9 @@ def _project_install(platform_name: str, project_dir: Path | None = None) -> Non
skill_dst = _copy_skill_file("antigravity", project=True, project_dir=project_dir)
_antigravity_finalize(skill_dst, project_dir)
_print_project_git_add_hint([_project_scope_root(skill_dst, project_dir), project_dir / ".agents"])
elif platform_name in ("copilot", "pi", "kimi"):
elif platform_name in ("copilot", "pi", "kimi", "agents"):
# Skill-only project install: drop SKILL.md (+ references) at the scope
# root. `agents` -> ./.agents/skills/graphify/SKILL.md.
skill_dst = _copy_skill_file(platform_name, project=True, project_dir=project_dir)
_print_project_git_add_hint([_project_scope_root(skill_dst, project_dir)])
else:
@@ -1672,6 +1726,7 @@ def _project_install(platform_name: str, project_dir: Path | None = None) -> Non
def _project_uninstall(platform_name: str, project_dir: Path | None = None) -> None:
"""Remove project-scoped platform skill/config files only."""
project_dir = project_dir or Path(".")
platform_name = _canonical_platform(platform_name)
if platform_name in ("claude", "windows"):
_remove_skill_file(platform_name, project=True, project_dir=project_dir)
_remove_claude_skill_registration(project_dir)
@@ -1694,7 +1749,7 @@ def _project_uninstall(platform_name: str, project_dir: Path | None = None) -> N
_devin_rules_uninstall(project_dir)
if not removed:
print("nothing to remove")
elif platform_name in ("copilot", "pi", "kimi"):
elif platform_name in ("copilot", "pi", "kimi", "agents"):
removed = _remove_skill_file(platform_name, project=True, project_dir=project_dir)
if not removed:
print("nothing to remove")
@@ -1885,6 +1940,9 @@ def uninstall_all(project_dir: Path | None = None, purge: bool = False) -> None:
# Amp also drops a user-scope skill at ~/.config/agents/skills, which the
# AGENTS.md cleanup above does not touch.
_remove_skill_file("amp")
# The generic agents platform's user-scope skill lives at ~/.agents/skills,
# which neither the AGENTS.md cleanup nor amp's removal reaches.
_remove_skill_file("agents")
_uninstall_opencode_plugin(pd)
_uninstall_codex_hook(pd)
@@ -2131,7 +2189,7 @@ def main() -> None:
print("Usage: graphify <command>")
print()
print("Commands:")
print(" install [--platform P] copy skill to platform config dir (claude|windows|codebuddy|codex|opencode|aider|amp|claw|droid|trae|trae-cn|gemini|cursor|antigravity|hermes|kiro|pi|devin)")
print(" install [--platform P] copy skill to platform config dir (claude|windows|codebuddy|codex|opencode|aider|amp|agents|claw|droid|trae|trae-cn|gemini|cursor|antigravity|hermes|kiro|pi|devin)")
print(" uninstall remove graphify from all detected platforms in one shot")
print(" --purge also delete graphify-out/ directory")
print(" path \"A\" \"B\" shortest path between two nodes in graph.json")
@@ -2517,6 +2575,21 @@ def main() -> None:
else:
print("Usage: graphify amp [install|uninstall]", file=sys.stderr)
sys.exit(1)
elif cmd in ("agents", "skills"):
subcmd = sys.argv[2] if len(sys.argv) > 2 else ""
if subcmd == "install":
if "--project" in sys.argv[3:]:
_project_install("agents", Path("."))
else:
_agents_platform_install(Path("."))
elif subcmd == "uninstall":
if "--project" in sys.argv[3:]:
_project_uninstall("agents", Path("."))
else:
_agents_platform_uninstall(Path("."))
else:
print(f"Usage: graphify {cmd} [install|uninstall]", file=sys.stderr)
sys.exit(1)
elif cmd in ("aider", "codex", "opencode", "claw", "droid", "trae", "trae-cn", "hermes"):
subcmd = sys.argv[2] if len(sys.argv) > 2 else ""
if subcmd == "install":
graphify/skill-agents.md
+672
View File
@@ -0,0 +1,672 @@
---
name: graphify
description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
---
# /graphify
Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md.
## Usage
```
/graphify # full pipeline on current directory → Obsidian vault
/graphify <path> # full pipeline on specific path
/graphify https://github.com/<owner>/<repo> # clone repo then run full pipeline on it
/graphify https://github.com/<owner>/<repo> --branch <branch> # clone a specific branch
/graphify <url1> <url2> ... # clone multiple repos, build each, merge into one cross-repo graph
/graphify <path> --mode deep # thorough extraction, richer INFERRED edges
/graphify <path> --update # incremental - re-extract only new/changed files
/graphify <path> --directed # build directed graph (preserves edge direction: source→target)
/graphify <path> --whisper-model medium # use a larger Whisper model for better transcription accuracy
/graphify <path> --cluster-only # rerun clustering on existing graph
/graphify <path> --no-viz # skip visualization, just report + JSON
/graphify <path> --html # (HTML is generated by default - this flag is a no-op)
/graphify <path> --svg # also export graph.svg (embeds in Notion, GitHub)
/graphify <path> --graphml # export graph.graphml (Gephi, yEd)
/graphify <path> --neo4j # generate graphify-out/cypher.txt for Neo4j
/graphify <path> --neo4j-push bolt://localhost:7687 # push directly to Neo4j
/graphify <path> --falkordb # generate graphify-out/cypher.txt for FalkorDB
/graphify <path> --falkordb-push falkordb://localhost:6379 # push directly to FalkorDB
/graphify <path> --mcp # start MCP stdio server for agent access
/graphify <path> --watch # watch folder, auto-rebuild on code changes (no LLM needed)
/graphify <path> --wiki # build agent-crawlable wiki (index.md + one article per community)
/graphify <path> --obsidian --obsidian-dir ~/vaults/my-project # write vault to custom path (e.g. existing vault)
/graphify add <url> # fetch URL, save to ./raw, update graph
/graphify add <url> --author "Name" # tag who wrote it
/graphify add <url> --contributor "Name" # tag who added it to the corpus
/graphify query "<question>" # BFS traversal - broad context
/graphify query "<question>" --dfs # DFS - trace a specific path
/graphify query "<question>" --budget 1500 # cap answer at N tokens
/graphify path "AuthModule" "Database" # shortest path between two concepts
/graphify explain "SwinTransformer" # plain-language explanation of a node
```
## What graphify is for
Drop any folder of code, docs, papers, images, or video into graphify and get a queryable knowledge graph. Persistent across sessions, honest audit trail (EXTRACTED/INFERRED/AMBIGUOUS), community detection surfaces cross-document connections you wouldn't think to ask about.
## What You Must Do When Invoked
If the user invoked `/graphify --help` or `/graphify -h` (with no other arguments), print the contents of the `## Usage` section above verbatim and stop. Do not run any commands, do not detect files, do not default the path to `.`. Just print the Usage block and return.
**Fast path — existing graph:** Before doing anything else, check whether `graphify-out/graph.json` exists. The expected location is `graphify-out/graph.json` relative to the **current working directory** (i.e. the project root where you are running commands). If it exists AND the user's request is a natural-language question about the codebase (e.g. "How does X work?", "What calls Y?", "Trace the data flow through Z") and NOT an explicit rebuild command (`--update`, `--cluster-only`, or a bare path/URL that implies fresh extraction): **skip Steps 1–5 entirely and jump straight to `## For /graphify query`.** Run `graphify query "<question>"` immediately. Do not run detect. Do not check corpus size. Do not ask the user to narrow. The graph is already built — use it.
If no path was given, use `.` (current directory). Do not ask the user for a path.
If the path argument starts with `https://github.com/` or `http://github.com/`, treat it as a GitHub URL - run Step 0 before anything else, then continue with the resolved local path.
Follow these steps in order. Do not skip steps.
### Step 0 - GitHub repos and multi-path merge (only if a URL or several paths)
Only when the path is one or more `https://github.com/...` URLs, or several local subfolders to merge. See `references/github-and-merge.md` for the clone, cross-repo merge, and monorepo flow, then continue with the resolved local path. A plain local path skips this step.
### Step 1 - Ensure graphify is installed
```bash
# Detect the correct Python interpreter (handles uv tool, pipx, venv, system installs)
PYTHON=""
GRAPHIFY_BIN=$(which graphify 2>/dev/null)
# 1. uv tool installs — most reliable on modern Mac/Linux
if [ -z "$PYTHON" ] && command -v uv >/dev/null 2>&1; then
_UV_PY=$(uv tool run graphifyy python -c "import sys; print(sys.executable)" 2>/dev/null)
if [ -n "$_UV_PY" ]; then PYTHON="$_UV_PY"; fi
fi
# 2. Read shebang from graphify binary (pipx and direct pip installs)
if [ -z "$PYTHON" ] && [ -n "$GRAPHIFY_BIN" ]; then
_SHEBANG=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!')
case "$_SHEBANG" in
*[!a-zA-Z0-9/_.-]*) ;;
*) "$_SHEBANG" -c "import graphify" 2>/dev/null && PYTHON="$_SHEBANG" ;;
esac
fi
# 3. Fall back to python3
if [ -z "$PYTHON" ]; then PYTHON="python3"; fi
if ! "$PYTHON" -c "import graphify" 2>/dev/null; then
if command -v uv >/dev/null 2>&1; then
uv tool install --upgrade graphifyy -q 2>&1 | tail -3
_UV_PY=$(uv tool run graphifyy python -c "import sys; print(sys.executable)" 2>/dev/null)
if [ -n "$_UV_PY" ]; then PYTHON="$_UV_PY"; fi
else
"$PYTHON" -m pip install graphifyy -q 2>/dev/null \
|| "$PYTHON" -m pip install graphifyy -q --break-system-packages 2>&1 | tail -3
fi
fi
# Write interpreter path for all subsequent steps (persists across invocations)
mkdir -p graphify-out
"$PYTHON" -c "import sys; open('graphify-out/.graphify_python', 'w', encoding='utf-8').write(sys.executable)"
# Save scan root so `graphify update` (no args) knows where to look next time
echo "$(cd INPUT_PATH && pwd)" > graphify-out/.graphify_root
```
If the import succeeds, print nothing and move straight to Step 2.
**In every subsequent bash block, replace `python3` with `$(cat graphify-out/.graphify_python)` to use the correct interpreter.**
### Step 2 - Detect files
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.detect import detect
from pathlib import Path
result = detect(Path('INPUT_PATH'))
print(json.dumps(result, ensure_ascii=False))
" > graphify-out/.graphify_detect.json
```
Replace INPUT_PATH with the actual path the user provided. Do NOT cat or print the JSON - read it silently and present a clean summary instead:
```
Corpus: X files · ~Y words
code: N files (.py .ts .go ...)
docs: N files (.md .txt ...)
papers: N files (.pdf ...)
images: N files
video: N files (.mp4 .mp3 ...)
```
Omit any category with 0 files from the summary.
Then act on it:
- If `total_files` is 0: stop with "No supported files found in [path]."
- If `skipped_sensitive` is non-empty: mention file count skipped, not the file names.
- If `total_words` > 2,000,000 OR `total_files` > 500: show the warning. Then compute the top 5 first-level subdirectories by file count:
- Read `scan_root` from the detect JSON (always an absolute path to the resolved INPUT_PATH).
- Concatenate all file lists across all types (`code`, `document`, `paper`, `image`, `video`).
- Filter out any path that starts with `scan_root + "/graphify-out/"` to exclude converted sidecars.
- For each file, strip the `scan_root` prefix and take the first path component. Files directly in `scan_root` with no subdirectory count as `(root)`.
- If all files are in `(root)` with no subdirectories, do not ask to narrow — no subfolders exist. Instead suggest `--no-cluster` to skip the expensive clustering step and proceed.
- Otherwise rank by count, show the top 5 with file counts, then ask which subfolder to run on. Wait for the user's answer before proceeding.
- Otherwise: proceed directly to Step 2.5 if video files were detected, or Step 3 if not.
### Step 2.5 - Video and audio (only if video files detected)
Skip this step entirely if `detect` returned zero `video` files. When the corpus has video or audio, see `references/transcribe.md` to transcribe them to text first, then treat the transcripts as doc files in Step 3.
### Step 3 - Extract entities and relationships
**Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it.
This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (LLM, costs tokens).
**Before dispatching subagents:** check whether `GEMINI_API_KEY` or `GOOGLE_API_KEY` is set. If neither is set, print this one-liner to the user:
> Tip: set `GEMINI_API_KEY` or `GOOGLE_API_KEY` to use Gemini for semantic extraction (`pip install 'graphifyy[gemini]'`).
Print it once, then continue. If `GEMINI_API_KEY` or `GOOGLE_API_KEY` IS set, use `graphify.llm.extract_corpus_parallel(files, backend="gemini")` for semantic extraction instead of dispatching Claude subagents. The default Gemini model is `gemini-3-flash-preview`; set `GRAPHIFY_GEMINI_MODEL` or pass `--model` in headless CLI flows to override it.
> **No other API keys are read.** If `GEMINI_API_KEY`/`GOOGLE_API_KEY` are unset, fall straight through to Claude Code subagent dispatch (Part B below) — the host session itself is the LLM. graphify does **not** read `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, or any other provider key from the environment. If a host agent prompts the user for `ANTHROPIC_API_KEY` to run extraction, that prompt is a misread of this skill — ignore it and dispatch subagents as written.
**Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.**
Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is deterministic and fast; start it while subagents are processing docs/papers.
#### Part A - Structural extraction for code files
For any code files detected, run AST extraction in parallel with Part B subagents:
```bash
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.extract import collect_files, extract
from pathlib import Path
import json
code_files = []
detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\"))
for f in detect.get('files', {}).get('code', []):
code_files.extend(collect_files(Path(f)) if Path(f).is_dir() else [Path(f)])
if code_files:
result = extract(code_files, cache_root=Path('INPUT_PATH'))
Path('graphify-out/.graphify_ast.json').write_text(json.dumps(result, indent=2, ensure_ascii=False), encoding=\"utf-8\")
print(f'AST: {len(result[\"nodes\"])} nodes, {len(result[\"edges\"])} edges')
else:
Path('graphify-out/.graphify_ast.json').write_text(json.dumps({'nodes':[],'edges':[],'input_tokens':0,'output_tokens':0}, ensure_ascii=False), encoding=\"utf-8\")
print('No code files - skipping AST extraction')
"
```
#### Part B - Semantic extraction (parallel subagents)
**Fast path:** If detection found zero docs, papers, and images (code-only corpus), skip Part B entirely and go straight to Part C. AST handles code - there is nothing for semantic subagents to do. **First write an empty semantic file** so Part C's merge has its input (it reads `.graphify_semantic.json` unconditionally; without this a code-only run hits `FileNotFoundError`):
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
Path('graphify-out/.graphify_semantic.json').write_text(json.dumps({'nodes':[],'edges':[],'hyperedges':[],'input_tokens':0,'output_tokens':0}), encoding='utf-8')
"
```
**MANDATORY: You MUST use the Agent tool here. Reading files yourself one-by-one is forbidden - it is 5-10x slower. If you do not use the Agent tool you are doing this wrong.**
Before dispatching subagents, print a timing estimate:
- Load `total_words` and file counts from `graphify-out/.graphify_detect.json`
- Estimate agents needed: `ceil(uncached_non_code_files / 22)` (chunk size is 20-25)
- Estimate time: ~45s per agent batch (they run in parallel, so total ≈ 45s × ceil(agents/parallel_limit))
- Print: "Semantic extraction: ~N files → X agents, estimated ~Ys"
**Step B0 - Check extraction cache first**
Before dispatching any subagents, check which files already have cached extraction results:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import check_semantic_cache
from pathlib import Path
detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\"))
# Only content files go to semantic extraction. Code is already covered structurally
# by the AST pass (Part A); flattening every category here makes subagents re-read
# every source file (#1392). Video is transcribed to a document in Step 2.5 first.
all_files = [f for cat in ('document', 'paper', 'image') for f in detect['files'].get(cat, [])]
cached_nodes, cached_edges, cached_hyperedges, uncached = check_semantic_cache(all_files, root='INPUT_PATH')
# Always (re)write the cache file: write hits, else DELETE any leftover from a prior
# run so Part C never merges a stale .graphify_cached.json (#1392).
if cached_nodes or cached_edges or cached_hyperedges:
Path('graphify-out/.graphify_cached.json').write_text(json.dumps({'nodes': cached_nodes, 'edges': cached_edges, 'hyperedges': cached_hyperedges}, ensure_ascii=False), encoding=\"utf-8\")
else:
Path('graphify-out/.graphify_cached.json').unlink(missing_ok=True)
Path('graphify-out/.graphify_uncached.txt').write_text('\n'.join(uncached), encoding=\"utf-8\")
print(f'Cache: {len(all_files)-len(uncached)} files hit, {len(uncached)} files need extraction')
"
```
Only dispatch subagents for files listed in `graphify-out/.graphify_uncached.txt`. If all files are cached, skip to Part C directly.
**Step B1 - Split into chunks**
Load files from `graphify-out/.graphify_uncached.txt`. Split into chunks of 20-25 files each. Each image gets its own chunk (vision needs separate context). When splitting, group files from the same directory together so related artifacts land in the same chunk and cross-file relationships are more likely to be extracted.
**Step B2 - Dispatch ALL subagents in a single message**
> Uses the `Task` tool for parallel subagent dispatch.
> Call `Task` once per chunk — ALL in the same response so they run in parallel.
Pass the extraction prompt as the task description:
```
Task(description="Your task is to perform the following. Follow the instructions below exactly.\n\n<agent-instructions>\n[extraction prompt, with FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE substituted]\n</agent-instructions>\n\nExecute this now. Output ONLY the structured JSON response.")
```
Each subagent writes its result to its own `graphify-out/.graphify_chunk_NN.json`. Collect results as each `Task` completes and parse each as JSON.
CHUNK_PATH must be an **absolute** path — derive it before dispatching:
```bash
PROJECT_ROOT=$(pwd) # cwd — where Part C globs graphify-out/ (NOT .graphify_root/scan dir, #1392)
# Then for chunk N: CHUNK_PATH="${PROJECT_ROOT}/graphify-out/.graphify_chunk_0N.json"
```
Subagent prompt template:
See `references/extraction-spec.md` for the exact subagent prompt (JSON schema, node-ID rules, confidence rubric, hyperedge, and vision rules). Load it only here, only when at least one chunk holds a doc, paper, or image; a pure-code corpus has skipped Part B and never reads it. Pass each subagent that prompt verbatim with FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE, and CHUNK_PATH substituted, and have it write the result to CHUNK_PATH.
**Step B3 - Collect, cache, and merge**
Wait for all subagents. For each result:
- Check that `graphify-out/.graphify_chunk_NN.json` exists on disk — this is the success signal
- If the file exists and contains valid JSON with `nodes` and `edges`, include it and save to cache
- If the file is missing, the subagent was likely dispatched as read-only (Explore type) — print a warning: "chunk N missing from disk — subagent may have been read-only. Re-run with general-purpose agent." Do not silently skip.
- If a subagent failed or returned invalid JSON, print a warning and skip that chunk - do not abort
If more than half the chunks failed or are missing, stop and tell the user to re-run and ensure `subagent_type="general-purpose"` is used.
Merge all chunk files into `.graphify_semantic_new.json`. **After each Agent call completes, read the real token counts from the Agent tool result's `usage` field and write them back into the chunk JSON before merging** — the chunk JSON itself always has placeholder zeros. Then run:
```bash
$(cat graphify-out/.graphify_python) -c "
import json, glob
from pathlib import Path
chunks = sorted(glob.glob('graphify-out/.graphify_chunk_*.json'))
all_nodes, all_edges, all_hyperedges = [], [], []
total_in, total_out = 0, 0
for c in chunks:
d = json.loads(Path(c).read_text(encoding=\"utf-8\"))
all_nodes += d.get('nodes', [])
all_edges += d.get('edges', [])
all_hyperedges += d.get('hyperedges', [])
total_in += d.get('input_tokens', 0)
total_out += d.get('output_tokens', 0)
Path('graphify-out/.graphify_semantic_new.json').write_text(json.dumps({
'nodes': all_nodes, 'edges': all_edges, 'hyperedges': all_hyperedges,
'input_tokens': total_in, 'output_tokens': total_out,
}, indent=2, ensure_ascii=False), encoding=\"utf-8\")
print(f'Merged {len(chunks)} chunks: {total_in:,} in / {total_out:,} out tokens')
"
```
Save new results to cache:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import save_semantic_cache
from pathlib import Path
new = json.loads(Path('graphify-out/.graphify_semantic_new.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]}
saved = save_semantic_cache(new.get('nodes', []), new.get('edges', []), new.get('hyperedges', []), root='INPUT_PATH')
print(f'Cached {saved} files')
"
```
Merge cached + new results into `graphify-out/.graphify_semantic.json`:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
cached = json.loads(Path('graphify-out/.graphify_cached.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_cached.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]}
new = json.loads(Path('graphify-out/.graphify_semantic_new.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]}
all_nodes = cached['nodes'] + new.get('nodes', [])
all_edges = cached['edges'] + new.get('edges', [])
all_hyperedges = cached.get('hyperedges', []) + new.get('hyperedges', [])
seen = set()
deduped = []
for n in all_nodes:
if n['id'] not in seen:
seen.add(n['id'])
deduped.append(n)
merged = {
'nodes': deduped,
'edges': all_edges,
'hyperedges': all_hyperedges,
'input_tokens': new.get('input_tokens', 0),
'output_tokens': new.get('output_tokens', 0),
}
Path('graphify-out/.graphify_semantic.json').write_text(json.dumps(merged, indent=2, ensure_ascii=False), encoding=\"utf-8\")
print(f'Extraction complete - {len(deduped)} nodes, {len(all_edges)} edges ({len(cached[\"nodes\"])} from cache, {len(new.get(\"nodes\",[]))} new)')
"
```
Clean up temp files: `rm -f graphify-out/.graphify_cached.json graphify-out/.graphify_uncached.txt graphify-out/.graphify_semantic_new.json`
#### Part C - Merge AST + semantic into final extraction
```bash
$(cat graphify-out/.graphify_python) -c "
import sys, json
from pathlib import Path
ast = json.loads(Path('graphify-out/.graphify_ast.json').read_text(encoding=\"utf-8\"))
sem = json.loads(Path('graphify-out/.graphify_semantic.json').read_text(encoding=\"utf-8\"))
# Merge: AST nodes first, semantic nodes deduplicated by id
seen = {n['id'] for n in ast['nodes']}
merged_nodes = list(ast['nodes'])
for n in sem['nodes']:
if n['id'] not in seen:
merged_nodes.append(n)
seen.add(n['id'])
merged_edges = ast['edges'] + sem['edges']
merged_hyperedges = sem.get('hyperedges', [])
merged = {
'nodes': merged_nodes,
'edges': merged_edges,
'hyperedges': merged_hyperedges,
'input_tokens': sem.get('input_tokens', 0),
'output_tokens': sem.get('output_tokens', 0),
}
Path('graphify-out/.graphify_extract.json').write_text(json.dumps(merged, indent=2, ensure_ascii=False), encoding=\"utf-8\")
total = len(merged_nodes)
edges = len(merged_edges)
print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(sem[\"nodes\"])} semantic)')
"
```
### Step 4 - Build graph, cluster, analyze, generate outputs
**Before starting:** the code blocks below pass `directed=IS_DIRECTED` to `build_from_json()`. Replace `IS_DIRECTED` with `True` if `--directed` was given (builds a `DiGraph` preserving edge direction source→target), otherwise `False` (the default undirected `Graph`). Substitute it the same way you substitute `INPUT_PATH` — do not leave the literal `IS_DIRECTED` in the code.
```bash
mkdir -p graphify-out
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections, suggest_questions
from graphify.report import generate
from graphify.export import to_json
from pathlib import Path
extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
detection = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\"))
# root= mirrors the --update runbook (#1361): relativize source_file to the same
# base so the full build and incremental --update never drift apart on re-extract.
G = build_from_json(extraction, root='INPUT_PATH', directed=IS_DIRECTED)
# Guard BEFORE any write: an empty extraction must not clobber a good graph.json /
# GRAPH_REPORT.md / analysis sidecar. Check immediately after build (#1392).
if G.number_of_nodes() == 0:
print('ERROR: Graph is empty - extraction produced no nodes.')
print('Possible causes: all files were skipped, binary-only corpus, or extraction failed.')
raise SystemExit(1)
communities = cluster(G)
cohesion = score_all(G, communities)
tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)}
gods = god_nodes(G)
surprises = surprising_connections(G, communities)
labels = {cid: 'Community ' + str(cid) for cid in communities}
# Placeholder questions - regenerated with real labels in Step 5
questions = suggest_questions(G, communities, labels)
# Export FIRST and honor the #479 shrink-guard: to_json returns False (writing
# nothing) when the new graph is smaller than the existing graph.json. Only write
# GRAPH_REPORT.md + the analysis sidecar when the graph was actually written, so
# they never describe a graph that graph.json doesn't contain (#1392).
wrote = to_json(G, communities, 'graphify-out/graph.json')
if not wrote:
print('ERROR: refused to shrink graphify-out/graph.json (existing graph has more nodes; #479).')
print('If this shrink is intentional (you deleted files), re-run a full build with --force.')
raise SystemExit(1)
report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, 'INPUT_PATH', suggested_questions=questions)
Path('graphify-out/GRAPH_REPORT.md').write_text(report, encoding=\"utf-8\")
analysis = {
'communities': {str(k): v for k, v in communities.items()},
'cohesion': {str(k): v for k, v in cohesion.items()},
'gods': gods,
'surprises': surprises,
'questions': questions,
}
Path('graphify-out/.graphify_analysis.json').write_text(json.dumps(analysis, indent=2, ensure_ascii=False), encoding=\"utf-8\")
print(f'Graph: {G.number_of_nodes()} nodes, {G.number_of_edges()} edges, {len(communities)} communities')
"
```
If this step prints `ERROR: Graph is empty`, stop and tell the user what happened - do not proceed to labeling or visualization.
Replace INPUT_PATH with the actual path.
### Step 4.5 - Graph health check (read-only integrity gate)
A non-destructive diagnostic on the extraction, before labeling. It surfaces edge collapse, dangling/missing endpoints, and self-loops — the silent-corruption modes of incremental updates and AST/LLM id mismatches. Read-only; never aborts.
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from graphify.diagnostics import diagnose_extraction, format_diagnostic_report
extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
summary = diagnose_extraction(extraction, directed=IS_DIRECTED, root='INPUT_PATH')
print(format_diagnostic_report(summary))
flags = [f'{summary[k]} {label}' for k, label in (
('dangling_endpoint_edges', 'dangling-endpoint edges'),
('missing_endpoint_edges', 'missing-endpoint edges'),
('self_loop_edges', 'self-loop edges'),
('directed_same_endpoint_collapsed_edges', 'collapsed (directed) edges'),
('undirected_same_endpoint_collapsed_edges', 'collapsed (undirected) edges'),
) if summary.get(k, 0)]
print('GRAPH HEALTH WARNING: ' + '; '.join(flags) + ' - graph may be incomplete/corrupt.' if flags else 'Graph health: OK (no dangling/missing/collapsed edges).')
"
```
Substitute `IS_DIRECTED` and `INPUT_PATH` as in Step 4. If a `GRAPH HEALTH WARNING` prints, surface it in the final summary (do not abort — the graph is still usable, but the integrity issue must be visible, per the Honesty Rules).
### Step 5 - Label communities
Read `graphify-out/.graphify_analysis.json`. For each community key, look at its node labels and write a 2-5 word plain-language name (e.g. "Attention Mechanism", "Training Pipeline", "Data Loading").
Then regenerate the report and save the labels for the visualizer:
```bash
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import score_all
from graphify.analyze import god_nodes, surprising_connections, suggest_questions
from graphify.report import generate
from pathlib import Path
extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
detection = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\"))
analysis = json.loads(Path('graphify-out/.graphify_analysis.json').read_text(encoding=\"utf-8\"))
# root= as in Step 4 / the --update runbook (#1361) — same base for node-key parity.
G = build_from_json(extraction, root='INPUT_PATH', directed=IS_DIRECTED)
communities = {int(k): v for k, v in analysis['communities'].items()}
cohesion = {int(k): v for k, v in analysis['cohesion'].items()}
tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)}
# LABELS - replace these with the names you chose above
labels = LABELS_DICT
# Regenerate questions with real community labels (labels affect question phrasing)
questions = suggest_questions(G, communities, labels)
report = generate(G, communities, cohesion, labels, analysis['gods'], analysis['surprises'], detection, tokens, 'INPUT_PATH', suggested_questions=questions)
Path('graphify-out/GRAPH_REPORT.md').write_text(report, encoding=\"utf-8\")
Path('graphify-out/.graphify_labels.json').write_text(json.dumps({str(k): v for k, v in labels.items()}, ensure_ascii=False), encoding=\"utf-8\")
print('Report updated with community labels')
"
```
Replace `LABELS_DICT` with the actual dict you constructed (e.g. `{0: "Attention Mechanism", 1: "Training Pipeline"}`).
Replace INPUT_PATH with the actual path.
### Step 6 - Generate Obsidian vault (opt-in) + HTML
**Generate HTML always** (unless `--no-viz`). **Obsidian vault only if `--obsidian` was explicitly given** — skip it otherwise, it generates one file per node.
If `--obsidian` was given:
- If `--obsidian-dir <path>` was also given, pass it via `--dir`. Otherwise defaults to `graphify-out/obsidian`.
```bash
graphify export obsidian
# or with custom dir: graphify export obsidian --dir ~/vaults/my-project
```
Generate the HTML graph (always, unless `--no-viz`):
```bash
graphify export html # auto-aggregates to community view if graph > 5000 nodes
# or: graphify export html --no-viz
```
### Steps 6b-8 - Wiki, Neo4j, FalkorDB, SVG, GraphML, MCP, benchmark (only on their flags)
These run only when their flag is present (`--wiki`, `--neo4j`/`--neo4j-push`, `--falkordb`/`--falkordb-push`, `--svg`, `--graphml`, `--mcp`) or, for the token-reduction benchmark, when `total_words` exceeds 5,000. A default run with no export flags skips all of them. See `references/exports.md` for each one. Run any `--wiki` export before Step 9 cleanup so `.graphify_labels.json` is still available.
---
### Step 9 - Save manifest, update cost tracker, clean up, and report
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from datetime import datetime, timezone
from graphify.detect import save_manifest
# Save manifest for --update
detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\"))
# In --update mode, 'all_files' carries the full corpus; 'files' is the changed
# subset. Full-rebuild mode populates only 'files', so the fallback handles that.
# root= relativizes the manifest keys to the scan root (same base as the build),
# so the on-disk manifest is portable across clones/machines and a later --update
# matches cached files instead of missing every one (#1417).
save_manifest(detect.get('all_files') or detect['files'], root='INPUT_PATH')
# Update cumulative cost tracker
extract = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
input_tok = extract.get('input_tokens', 0)
output_tok = extract.get('output_tokens', 0)
cost_path = Path('graphify-out/cost.json')
if cost_path.exists():
cost = json.loads(cost_path.read_text(encoding=\"utf-8\"))
else:
cost = {'runs': [], 'total_input_tokens': 0, 'total_output_tokens': 0}
cost['runs'].append({
'date': datetime.now(timezone.utc).isoformat(),
'input_tokens': input_tok,
'output_tokens': output_tok,
'files': detect.get('total_files', 0),
})
cost['total_input_tokens'] += input_tok
cost['total_output_tokens'] += output_tok
cost_path.write_text(json.dumps(cost, indent=2, ensure_ascii=False), encoding=\"utf-8\")
print(f'This run: {input_tok:,} input tokens, {output_tok:,} output tokens')
print(f'All time: {cost[\"total_input_tokens\"]:,} input, {cost[\"total_output_tokens\"]:,} output ({len(cost[\"runs\"])} runs)')
"
rm -f graphify-out/.graphify_detect.json graphify-out/.graphify_extract.json graphify-out/.graphify_ast.json graphify-out/.graphify_semantic.json graphify-out/.graphify_analysis.json
find graphify-out -maxdepth 1 -name '.graphify_chunk_*.json' -delete 2>/dev/null
rm -f graphify-out/.needs_update 2>/dev/null || true
```
Replace INPUT_PATH with the actual path (same value used in Steps 4-5) so the manifest is relativized to the scan root.
Tell the user (omit the obsidian line unless --obsidian was given):
```
Graph complete. Outputs in PATH_TO_DIR/graphify-out/
graph.html - interactive graph, open in browser
GRAPH_REPORT.md - audit report
graph.json - raw graph data
obsidian/ - Obsidian vault (only if --obsidian was given)
```
If graphify saved you time, consider supporting it: https://github.com/sponsors/safishamsi
Replace PATH_TO_DIR with the actual absolute path of the directory that was processed.
Then paste these sections from GRAPH_REPORT.md directly into the chat:
- God Nodes
- Surprising Connections
- Suggested Questions
Do NOT paste the full report - just those three sections. Keep it concise.
Then immediately offer to explore. Pick the single most interesting suggested question from the report - the one that crosses the most community boundaries or has the most surprising bridge node - and ask:
> "The most interesting question this graph can answer: **[question]**. Want me to trace it?"
If the user says yes, run `/graphify query "[question]"` on the graph and walk them through the answer using the graph structure - which nodes connect, which community boundaries get crossed, what the path reveals. Keep going as long as they want to explore. Each answer should end with a natural follow-up ("this connects to X - want to go deeper?") so the session feels like navigation, not a one-shot report.
The graph is the map. Your job after the pipeline is to be the guide.
---
## Interpreter guard for subcommands
Before running any subcommand below (`--update`, `--cluster-only`, `query`, `path`, `explain`, `add`), check that `.graphify_python` exists. If it's missing (e.g. user deleted `graphify-out/`), re-resolve the interpreter first:
```bash
if [ ! -f graphify-out/.graphify_python ]; then
GRAPHIFY_BIN=$(which graphify 2>/dev/null)
if [ -n "$GRAPHIFY_BIN" ]; then
PYTHON=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!')
case "$PYTHON" in *[!a-zA-Z0-9/_.-]*) PYTHON="python3" ;; esac
else
PYTHON="python3"
fi
mkdir -p graphify-out
"$PYTHON" -c "import sys; open('graphify-out/.graphify_python', 'w', encoding='utf-8').write(sys.executable)"
fi
```
## For --update and --cluster-only
Both are non-default subcommands. `--update` re-extracts only new or changed files; `--cluster-only` reruns clustering on the existing graph. See `references/update.md` for both flows.
---
## For /graphify query
When `graphify-out/graph.json` already exists and the user asks a question about the corpus, answer from the graph rather than rebuilding it:
```bash
graphify query "<question>"
```
Before traversal, expand the question against the graph's own vocabulary so a wording mismatch does not collapse the answer to noise. If the `graphify query` CLI is unavailable, fall back to an inline NetworkX traversal of `graphify-out/graph.json`. Answer using only what the graph output contains, and quote `source_location` when citing a specific fact. For that vocab-expansion step, the BFS/DFS traversal modes, the `--budget` cap, the NetworkX fallback, `save-result` feedback, and the `/graphify path` and `/graphify explain` flows, see `references/query.md`.
---
## For /graphify add and --watch
Neither is part of the default build. When the user runs `/graphify add <url>` to fetch a URL into the corpus, or passes `--watch` to auto-rebuild on file changes, see `references/add-watch.md`.
---
## For the commit hook and native AGENTS.md integration
When the user asks to install the post-commit auto-rebuild hook or wire graphify into a project's AGENTS.md, see `references/hooks.md`.
---
## Honesty Rules
- Never invent an edge. If unsure, use AMBIGUOUS.
- Never skip the corpus check warning.
- Always show token cost in the report.
- Never hide cohesion scores behind symbols - show the raw number.
- Never run HTML viz on a graph with more than 5,000 nodes without warning the user.
graphify/skills/agents/references/add-watch.md
+56
View File
@@ -0,0 +1,56 @@
# graphify reference: add a URL and watch a folder
Load this when the user ran `/graphify add <url>` or passed `--watch`. Neither is part of the default build.
## For /graphify add
Fetch a URL and add it to the corpus, then update the graph.
```bash
$(cat graphify-out/.graphify_python) -c "
import sys
from graphify.ingest import ingest
from pathlib import Path
try:
out = ingest('URL', Path('./raw'), author='AUTHOR', contributor='CONTRIBUTOR')
print(f'Saved to {out}')
except ValueError as e:
print(f'error: {e}', file=sys.stderr)
sys.exit(1)
except RuntimeError as e:
print(f'error: {e}', file=sys.stderr)
sys.exit(1)
"
```
Replace `URL` with the actual URL, `AUTHOR` with the user's name if provided, `CONTRIBUTOR` likewise. If the command exits with an error, tell the user what went wrong - do not silently continue. After a successful save, automatically run the `--update` pipeline on `./raw` to merge the new file into the existing graph.
Supported URL types (auto-detected):
- YouTube / any video URL → audio downloaded via yt-dlp, transcribed to `.txt` on next run (requires `pip install 'graphifyy[video]'`)
- Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author
- arXiv → abstract + metadata saved as `.md`
- PDF → downloaded as `.pdf`
- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run
- Any webpage → converted to markdown via html2text
---
## For --watch
Start a background watcher that monitors a folder and auto-updates the graph when files change.
```bash
$(cat graphify-out/.graphify_python) -m graphify.watch INPUT_PATH --debounce 3
```
Replace INPUT_PATH with the folder to watch. Behavior depends on what changed:
- **Code files only (.py, .ts, .go, etc.):** re-runs AST extraction + rebuild + cluster immediately, no LLM needed. `graph.json` and `GRAPH_REPORT.md` are updated automatically.
- **Docs, papers, or images:** writes a `graphify-out/needs_update` flag and prints a notification to run `/graphify --update` (LLM semantic re-extraction required).
Debounce (default 3s): waits until file activity stops before triggering, so a wave of parallel agent writes doesn't trigger a rebuild per file.
Press Ctrl+C to stop.
For agentic workflows: run `--watch` in a background terminal. Code changes from agent waves are picked up automatically between waves. If agents are also writing docs or notes, you'll need a manual `/graphify --update` after those waves.
graphify/skills/agents/references/exports.md
+87
View File
@@ -0,0 +1,87 @@
# graphify reference: extra exports and benchmark
Load this when the user passed one of the export flags (`--wiki`, `--neo4j`, `--neo4j-push`, `--falkordb`, `--falkordb-push`, `--svg`, `--graphml`, `--mcp`), or when the corpus is large enough for the token-reduction benchmark. Each step runs only for its own flag.
### Step 6b - Wiki (only if --wiki flag)
**Only run this step if `--wiki` was explicitly given in the original command.**
Run this before Step 9 (cleanup) so `.graphify_labels.json` is still available.
```bash
graphify export wiki
```
### Step 7 - Neo4j export (only if --neo4j or --neo4j-push flag)
**If `--neo4j`** - generate a Cypher file for manual import:
```bash
graphify export neo4j
```
**If `--neo4j-push <uri>`** - push directly to a running Neo4j instance. Ask the user for credentials if not provided:
```bash
graphify export neo4j --push bolt://localhost:7687 --user neo4j --password PASSWORD
```
Default URI is `bolt://localhost:7687`, default user is `neo4j`. Uses MERGE - safe to re-run without creating duplicates.
### Step 7a - FalkorDB export (only if --falkordb or --falkordb-push flag)
**If `--falkordb`** - generate a Cypher file. The statements are OpenCypher, but FalkorDB's `GRAPH.QUERY` runs one statement at a time (no bulk script import like Neo4j's `cypher-shell`), so prefer `--falkordb-push` to load a graph. Use this only when you want the portable `cypher.txt` artifact:
```bash
graphify export falkordb
```
**If `--falkordb-push <uri>`** - push directly to a running FalkorDB instance. Credentials are optional; ask the user only if the instance requires auth:
```bash
graphify export falkordb --push falkordb://localhost:6379
```
Default URI is `falkordb://localhost:6379` (the scheme is informational - `redis://` or a bare `host:port` work too), auth is optional, and the target graph defaults to `graphify`. Uses MERGE - safe to re-run without creating duplicates.
### Step 7b - SVG export (only if --svg flag)
```bash
graphify export svg
```
### Step 7c - GraphML export (only if --graphml flag)
```bash
graphify export graphml
```
### Step 7d - MCP server (only if --mcp flag)
```bash
$(cat graphify-out/.graphify_python) -m graphify.serve graphify-out/graph.json
```
This starts a stdio MCP server that exposes tools: `query_graph`, `get_node`, `get_neighbors`, `get_community`, `god_nodes`, `graph_stats`, `shortest_path`. Add to Claude Desktop or any MCP-compatible agent orchestrator so other agents can query the graph live.
To configure in Claude Desktop, add to `claude_desktop_config.json`. Claude Desktop can't run `$(...)`, and under `uv tool install` the system `python3` can't import graphify — so set `command` to the **absolute interpreter path** printed by `cat graphify-out/.graphify_python`:
```json
{
"mcpServers": {
"graphify": {
"command": "<absolute path from: cat graphify-out/.graphify_python>",
"args": ["-m", "graphify.serve", "/absolute/path/to/graphify-out/graph.json"]
}
}
}
```
### Step 8 - Token reduction benchmark (only if total_words > 5000)
If `total_words` from `graphify-out/.graphify_detect.json` is greater than 5,000, run:
```bash
graphify benchmark
```
Print the output directly in chat. If `total_words <= 5000`, skip silently - the graph value is structural clarity, not token compression, for small corpora.
graphify/skills/agents/references/extraction-spec.md
+70
View File
@@ -0,0 +1,70 @@
# graphify reference: extraction subagent prompt
Load this in Step 3 Part B when the corpus has at least one doc, paper, or image chunk. A pure-code corpus skips Part B and never reads this file. Each semantic subagent receives the prompt below verbatim (substitute FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE, and CHUNK_PATH).
```
You are a graphify extraction subagent. Read the files listed and extract a knowledge graph fragment.
Output ONLY valid JSON matching the schema below - no explanation, no markdown fences, no preamble.
Files (chunk CHUNK_NUM of TOTAL_CHUNKS):
FILE_LIST
Rules:
- EXTRACTED: relationship explicit in source (import, call, citation, "see §3.2")
- INFERRED: reasonable inference (shared data structure, implied dependency)
- AMBIGUOUS: uncertain - flag for review, do not omit
Code files: focus on semantic edges AST cannot find (call relationships, shared data, arch patterns).
Do not re-extract imports - AST already has those.
Doc/paper files: extract named concepts, entities, citations. For rationale (WHY decisions were made, trade-offs, design intent): store as a `rationale` attribute on the relevant concept node — do NOT create a separate rationale node or fragment node. Only create a node for something that is itself a named entity or concept. Use `file_type:"rationale"` for concept-like nodes (ideas, principles, mechanisms, design patterns). `file_type` MUST be one of exactly these six values: `code`, `document`, `paper`, `image`, `rationale`, `concept`. Any other value is invalid and will be rejected.
Code files: when adding `calls` edges, source MUST be the caller (the function/class doing the calling), target MUST be the callee. Never reverse this direction. `calls` edges MUST stay within one language: a Python function cannot `calls` a JS/TS/Go/Rust/Java symbol and vice versa — cross-language call edges are phantom artifacts, never emit them.
Image files: use vision to understand what the image IS - do not just OCR.
UI screenshot: layout patterns, design decisions, key elements, purpose.
Chart: metric, trend/insight, data source.
Tweet/post: claim as node, author, concepts mentioned.
Diagram: components and connections.
Research figure: what it demonstrates, method, result.
Handwritten/whiteboard: ideas and arrows, mark uncertain readings AMBIGUOUS.
DEEP_MODE (if --mode deep was given): be aggressive with INFERRED edges - indirect deps,
shared assumptions, latent couplings. Mark uncertain ones AMBIGUOUS instead of omitting.
Semantic similarity: if two concepts in this chunk solve the same problem or represent the same idea without any structural link (no import, no call, no citation), add a `semantically_similar_to` edge marked INFERRED with a confidence_score reflecting how similar they are (0.6-0.95). Examples:
- Two functions that both validate user input but never call each other
- A class in code and a concept in a paper that describe the same algorithm
- Two error types that handle the same failure mode differently
Only add these when the similarity is genuinely non-obvious and cross-cutting. Do not add them for trivially similar things.
Hyperedges: if 3 or more nodes clearly participate together in a shared concept, flow, or pattern that is not captured by pairwise edges alone, add a hyperedge to a top-level `hyperedges` array. Examples:
- All classes that implement a common protocol or interface
- All functions in an authentication flow (even if they don't all call each other)
- All concepts from a paper section that form one coherent idea
Use sparingly — only when the group relationship adds information beyond the pairwise edges. Maximum 3 hyperedges per chunk.
If a file has YAML frontmatter (--- ... ---), copy source_url, captured_at, author,
contributor onto every node from that file.
confidence_score is REQUIRED on every edge - never omit it, never use 0.5 as a default:
- EXTRACTED edges: confidence_score = 1.0 always
- INFERRED edges: pick exactly ONE value from this set — never 0.5:
0.95 direct structural evidence (shared data structure, named cross-file reference).
0.85 strong inference (clear functional alignment, no direct symbol link).
0.75 reasonable inference (shared problem domain + similar shape, requires interpretation).
0.65 weak inference (thematically related, no shape evidence).
0.55 speculative but plausible (surface-level co-occurrence only).
Models follow discrete rubrics better than continuous ranges; the bimodal
distribution observed in production (>50% at 0.5, >40% at 0.85+) shows the
range guidance is being collapsed to a binary. If no value above fits, mark
the edge AMBIGUOUS rather than picking 0.4 or below.
- AMBIGUOUS edges: 0.1-0.3
Node ID format: lowercase, only `[a-z0-9_]`, no dots or slashes. Format: `{stem}_{entity}` where stem is `{parent_dir}_{filename_without_ext}` (the **immediate** parent directory name + the filename stem, both lowercased with non-alphanumeric chars replaced by `_`) and entity is the symbol name similarly normalized. Only one level of parent is used — not the full path. Examples: `src/auth/session.py` + `ValidateToken` → `auth_session_validatetoken`; `lib/utils/helpers.py` + `parse_url` → `utils_helpers_parse_url`; `tests/test_foo.py` + `_helper` → `tests_test_foo_helper`. Top-level files (no parent dir, e.g. `setup.py`) use just the filename stem: `setup_my_func`. This must match the ID the AST extractor generates — using just the filename (e.g., `session_validatetoken`) or the full path (e.g., `src_auth_session_validatetoken`) will create orphan ghost-duplicate nodes. If you are re-extracting a project that had ghost duplicates under the old format, the user should run `graphify extract --force` to rebuild cleanly. CRITICAL: never append chunk numbers, sequence numbers, or any suffix to an ID (no `_c1`, `_c2`, `_chunk2`, etc.). IDs must be deterministic from the label alone — the same entity must always produce the same ID regardless of which chunk processes it.
Generate the extraction JSON matching this schema exactly:
{"nodes":[{"id":"auth_session_validatetoken","label":"Human Readable Name","file_type":"code|document|paper|image|rationale|concept","source_file":"<FILE_LIST path verbatim>","source_location":null,"source_url":null,"captured_at":null,"author":null,"contributor":null}],"edges":[{"source":"node_id","target":"node_id","relation":"calls|implements|references|cites|conceptually_related_to|shares_data_with|semantically_similar_to|rationale_for","confidence":"EXTRACTED|INFERRED|AMBIGUOUS","confidence_score":1.0,"source_file":"<FILE_LIST path verbatim>","source_location":null,"weight":1.0}],"hyperedges":[{"id":"snake_case_id","label":"Human Readable Label","nodes":["node_id1","node_id2","node_id3"],"relation":"participate_in|implement|form","confidence":"EXTRACTED|INFERRED","confidence_score":0.75,"source_file":"<FILE_LIST path verbatim>"}],"input_tokens":0,"output_tokens":0}
source_file RULE (every node, edge, and hyperedge): set source_file to the path of the originating file EXACTLY as it appears in FILE_LIST — verbatim and absolute. Do NOT shorten to a basename, do NOT re-relativize, do NOT strip any directory prefix, and do NOT change separators (the engine canonicalizes separators and relativizes against the build root downstream). Copy the FILE_LIST entry character-for-character. This keeps the full build and incremental --update on the same base, so build_merge's replace-on-re-extract matches the existing node instead of accumulating a duplicate.
Then write the JSON to disk using the Write tool at this exact absolute path (no relative paths — Write resolves relative paths against an undefined cwd and the file will be silently lost):
CHUNK_PATH
```
graphify/skills/agents/references/github-and-merge.md
+46
View File
@@ -0,0 +1,46 @@
# graphify reference: GitHub clone and cross-repo merge
Load this when the user passed one or more `https://github.com/...` URLs, or named several local subfolders to merge into one graph.
### Step 0 - Clone GitHub repo(s) (only if a GitHub URL was given)
**Single repo:**
```bash
LOCAL_PATH=$(graphify clone <github-url> [--branch <branch>])
# Use LOCAL_PATH as the target for all subsequent steps
```
**Multiple repos (cross-repo graph):**
```bash
# Clone each repo, run the full pipeline on each, then merge
graphify clone <url1> # → ~/.graphify/repos/<owner1>/<repo1>
graphify clone <url2> # → ~/.graphify/repos/<owner2>/<repo2>
# Run /graphify on each local path to produce their graph.json files
# Then merge:
graphify merge-graphs \
~/.graphify/repos/<owner1>/<repo1>/graphify-out/graph.json \
~/.graphify/repos/<owner2>/<repo2>/graphify-out/graph.json \
--out graphify-out/cross-repo-graph.json
```
Graphify clones into `~/.graphify/repos/<owner>/<repo>` and reuses existing clones on repeat runs. Each node in the merged graph carries a `repo` attribute so you can filter by origin.
**Multiple local subfolders (monorepo or multi-service layout):**
The skill pipeline writes all intermediate and final outputs to `graphify-out/` in the current working directory. Running the skill on each subfolder separately will clobber the same output dir. Instead, use the CLI directly for each subfolder — it places `graphify-out/` *inside* the scanned path:
```bash
graphify extract ./core/ # → ./core/graphify-out/graph.json
graphify extract ./service/ # → ./service/graphify-out/graph.json
graphify extract ./platform/ # → ./platform/graphify-out/graph.json
# Add --backend gemini|kimi|openai|deepseek|claude-cli depending on which API key you have set
# Then merge at the project root:
graphify merge-graphs \
./core/graphify-out/graph.json \
./service/graphify-out/graph.json \
./platform/graphify-out/graph.json \
--out graphify-out/graph.json
```
Once `graphify-out/graph.json` exists, the fast path above takes over: any codebase question runs `graphify query` directly on the merged graph — no re-extraction, no size gate.
graphify/skills/agents/references/hooks.md
+33
View File
@@ -0,0 +1,33 @@
# graphify reference: commit hook and native AGENTS.md integration
Load this when the user asked to install the post-commit hook or wire graphify into a project's AGENTS.md.
## For git commit hook
Install a post-commit hook that auto-rebuilds the graph after every commit. No background process needed - triggers once per commit, works with any editor.
```bash
graphify hook install # install
graphify hook uninstall # remove
graphify hook status # check
```
After every `git commit`, the hook detects which code files changed (via `git diff HEAD~1`), re-runs AST extraction on those files, and rebuilds `graph.json` and `GRAPH_REPORT.md`. Doc/image changes are ignored by the hook - run `/graphify --update` manually for those.
If a post-commit hook already exists, graphify appends to it rather than replacing it.
---
## For native AGENTS.md integration
Run once per project to make graphify always-on in your agent sessions:
```bash
graphify agents install
```
This writes a `## graphify` section to the local `AGENTS.md` that instructs your agent to check the graph before answering codebase questions and rebuild it after code changes. No manual `/graphify` needed in future sessions.
```bash
graphify agents uninstall # remove the section
```
graphify/skills/agents/references/query.md
+303
View File
@@ -0,0 +1,303 @@
# graphify reference: query, path, explain
Load this when the user asks a question against an existing graph, or runs `/graphify path` or `/graphify explain`. The core's query stub points here for the full traversal flow. These flows use the `graphify query` CLI when it is available and fall back to an inline NetworkX traversal otherwise.
Two traversal modes - choose based on the question:
| Mode | Flag | Best for |
|------|------|----------|
| BFS (default) | _(none)_ | "What is X connected to?" - broad context, nearest neighbors first |
| DFS | `--dfs` | "How does X reach Y?" - trace a specific chain or dependency path |
First check the graph exists:
```bash
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
raise SystemExit(1)
"
```
If it fails, stop and tell the user to run `/graphify <path>` first.
### Step 0 — Constrained query expansion (REQUIRED before traversal)
graphify's `query` CLI matches nodes via case-folded substring + IDF — there is **no stemming, no synonyms, no cross-language match** inside the binary, and the inline fallback below matches the same way. If the user's question uses different language or different domain vocabulary than the graph's labels (user says "обработчик" / graph says "handler"; user says "authentication" / graph says "Guardian"), the literal matcher returns 0 hits and the answer collapses to noise.
Fix this **without inventing tokens** by expanding the query against the actual graph vocabulary first:
1. Extract the token vocabulary from node labels:
```bash
$(cat graphify-out/.graphify_python) -c "
import json, re
from pathlib import Path
data = json.loads(Path('graphify-out/graph.json').read_text())
vocab = set()
for n in data['nodes']:
for c in re.findall(r'[^\W\d_]+', n.get('label','') or '', re.UNICODE):
parts = re.findall(r'[A-Z]+(?=[A-Z][a-z])|[A-Z]?[a-z]+|[A-Z]+', c) or [c]
for p in parts:
t = p.lower()
if 3 <= len(t) <= 30:
vocab.add(t)
Path('graphify-out/.vocab.txt').write_text('\n'.join(sorted(vocab)))
print(f'vocab: {len(vocab)} tokens')
"
```
2. Read `graphify-out/.vocab.txt`. Then for the user's question, select **up to 12 tokens from this exact list** that semantically match the query intent. Hard constraints:
- You MUST pick only tokens present in the vocabulary file. Do NOT invent tokens.
- If a query concept has no plausible token in the vocab, skip it — do not substitute a near-synonym from training memory.
- If **no** vocab tokens match the query at all, output an empty list and tell the user the corpus has no relevant vocabulary for this question. Do not fabricate a search.
- Translate cross-language: Russian "аутентификация" → look for `auth`, `credential`, `token`, `security` IFF present in vocab.
- Morphology: "handlers" maps to `handler` IFF present; "todos" maps to `todo` IFF present.
3. Print the selection explicitly to the user before running the query, so the expansion is auditable:
```
Query expanded to (from graph vocab, N tokens): [token1, token2, ...]
```
If the list is empty, say so plainly and stop — do not proceed to traversal.
### Step 1 — Traversal
Build the **expanded query string** by joining the selected tokens with spaces. Use this string as `QUESTION` below — NOT the original user question. (The original question is preserved only for `save-result` at the end.)
Prefer the CLI when it is installed:
```bash
graphify query "QUESTION"
# or: graphify query "QUESTION" --dfs --budget 3000
```
If the CLI is unavailable, load `graphify-out/graph.json` and run the traversal inline:
1. Find the 1-3 nodes whose label best matches the expanded tokens.
2. Run the appropriate traversal from each starting node.
3. Read the subgraph - node labels, edge relations, confidence tags, source locations.
4. Answer using **only** what the graph contains. Quote `source_location` when citing a specific fact.
5. If the graph lacks enough information, say so - do not hallucinate edges.
```bash
$(cat graphify-out/.graphify_python) -c "
import sys, json
from networkx.readwrite import json_graph
import networkx as nx
from pathlib import Path
data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')
question = 'QUESTION'
mode = 'MODE' # 'bfs' or 'dfs'
terms = [t.lower() for t in question.split() if len(t) >= 3] # match the vocab threshold; keeps api/jwt/ios (#1392)
# Find best-matching start nodes
scored = []
for nid, ndata in G.nodes(data=True):
label = ndata.get('label', '').lower()
score = sum(1 for t in terms if t in label)
if score > 0:
scored.append((score, nid))
scored.sort(reverse=True)
start_nodes = [nid for _, nid in scored[:3]]
if not start_nodes:
print('No matching nodes found for query terms:', terms)
sys.exit(0)
subgraph_nodes = set()
subgraph_edges = []
if mode == 'dfs':
# DFS: follow one path as deep as possible before backtracking.
# Depth-limited to 6 to avoid traversing the whole graph.
visited = set()
stack = [(n, 0) for n in reversed(start_nodes)]
while stack:
node, depth = stack.pop()
if node in visited or depth > 6:
continue
visited.add(node)
subgraph_nodes.add(node)
for neighbor in G.neighbors(node):
if neighbor not in visited:
stack.append((neighbor, depth + 1))
subgraph_edges.append((node, neighbor))
else:
# BFS: explore all neighbors layer by layer up to depth 3.
frontier = set(start_nodes)
subgraph_nodes = set(start_nodes)
for _ in range(3):
next_frontier = set()
for n in frontier:
for neighbor in G.neighbors(n):
if neighbor not in subgraph_nodes:
next_frontier.add(neighbor)
subgraph_edges.append((n, neighbor))
subgraph_nodes.update(next_frontier)
frontier = next_frontier
# Token-budget aware output: rank by relevance, cut at budget (~4 chars/token)
token_budget = BUDGET # default 2000
char_budget = token_budget * 4
# Score each node by term overlap for ranked output
def relevance(nid):
label = G.nodes[nid].get('label', '').lower()
return sum(1 for t in terms if t in label)
ranked_nodes = sorted(subgraph_nodes, key=relevance, reverse=True)
lines = [f'Traversal: {mode.upper()} | Start: {[G.nodes[n].get(\"label\",n) for n in start_nodes]} | {len(subgraph_nodes)} nodes']
for nid in ranked_nodes:
d = G.nodes[nid]
lines.append(f' NODE {d.get(\"label\", nid)} [src={d.get(\"source_file\",\"\")} loc={d.get(\"source_location\",\"\")}]')
for u, v in subgraph_edges:
if u in subgraph_nodes and v in subgraph_nodes:
_raw = G[u][v]; d = next(iter(_raw.values()), {}) if isinstance(G, nx.MultiGraph) else _raw
lines.append(f' EDGE {G.nodes[u].get(\"label\",u)} --{d.get(\"relation\",\"\")} [{d.get(\"confidence\",\"\")}]--> {G.nodes[v].get(\"label\",v)}')
output = '\n'.join(lines)
if len(output) > char_budget:
output = output[:char_budget] + f'\n... (truncated at ~{token_budget} token budget - use --budget N for more)'
print(output)
"
```
Replace `QUESTION` with the **expanded** query string, `MODE` with `bfs` or `dfs`, and `BUDGET` with the token budget (default `2000`, or whatever `--budget N` specifies). Then answer based on the subgraph output above, using only what the graph contains.
After writing the answer, save it back into the graph so it improves future queries. Include the expanded tokens inside the `--answer` text (e.g. `"Expanded from original query via vocab: [tokens]. Then traversed..."`) so the next `--update` extracts the expansion history as a graph node:
```bash
$(cat graphify-out/.graphify_python) -m graphify save-result --question "ORIGINAL_QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
```
Replace `ORIGINAL_QUESTION` with the user's verbatim question, `ANSWER` with your full answer text (containing the expanded-token trace), `NODE1 NODE2` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
---
## For /graphify path
Find the shortest path between two named concepts in the graph. Prefer the CLI when installed:
```bash
graphify path "NODE_A" "NODE_B"
```
If the CLI is unavailable, run it inline:
```bash
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
from pathlib import Path
data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')
a_term = 'NODE_A'
b_term = 'NODE_B'
def find_node(term):
term = term.lower()
scored = sorted(
[(sum(1 for w in term.split() if w in G.nodes[n].get('label','').lower()), n)
for n in G.nodes()],
reverse=True
)
return scored[0][1] if scored and scored[0][0] > 0 else None
src = find_node(a_term)
tgt = find_node(b_term)
if not src or not tgt:
print(f'Could not find nodes matching: {a_term!r} or {b_term!r}')
sys.exit(0)
try:
path = nx.shortest_path(G, src, tgt)
print(f'Shortest path ({len(path)-1} hops):')
for i, nid in enumerate(path):
label = G.nodes[nid].get('label', nid)
if i < len(path) - 1:
_raw = G[nid][path[i+1]]; edge = next(iter(_raw.values()), {}) if isinstance(G, nx.MultiGraph) else _raw
rel = edge.get('relation', '')
conf = edge.get('confidence', '')
print(f' {label} --{rel}--> [{conf}]')
else:
print(f' {label}')
except nx.NetworkXNoPath:
print(f'No path found between {a_term!r} and {b_term!r}')
except nx.NodeNotFound as e:
print(f'Node not found: {e}')
"
```
Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then explain the path in plain language - what each hop means, why it's significant.
After writing the explanation, save it back:
```bash
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
```
---
## For /graphify explain
Give a plain-language explanation of a single node - everything connected to it. Prefer the CLI when installed:
```bash
graphify explain "NODE_NAME"
```
If the CLI is unavailable, run it inline:
```bash
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
from pathlib import Path
data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')
term = 'NODE_NAME'
term_lower = term.lower()
# Find best matching node
scored = sorted(
[(sum(1 for w in term_lower.split() if w in G.nodes[n].get('label','').lower()), n)
for n in G.nodes()],
reverse=True
)
if not scored or scored[0][0] == 0:
print(f'No node matching {term!r}')
sys.exit(0)
nid = scored[0][1]
data_n = G.nodes[nid]
print(f'NODE: {data_n.get(\"label\", nid)}')
print(f' source: {data_n.get(\"source_file\",\"unknown\")}')
print(f' type: {data_n.get(\"file_type\",\"unknown\")}')
print(f' degree: {G.degree(nid)}')
print()
print('CONNECTIONS:')
for neighbor in G.neighbors(nid):
_raw = G[nid][neighbor]; edge = next(iter(_raw.values()), {}) if isinstance(G, nx.MultiGraph) else _raw
nlabel = G.nodes[neighbor].get('label', neighbor)
rel = edge.get('relation', '')
conf = edge.get('confidence', '')
src_file = G.nodes[neighbor].get('source_file', '')
print(f' --{rel}--> {nlabel} [{conf}] ({src_file})')
"
```
Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sentence explanation of what this node is, what it connects to, and why those connections are significant. Use the source locations as citations.
After writing the explanation, save it back:
```bash
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
```
graphify/skills/agents/references/transcribe.md
+52
View File
@@ -0,0 +1,52 @@
# graphify reference: transcribe video and audio
Load this only when `detect` reported one or more `video` files. A corpus with no video never reads this.
### Step 2.5 - Transcribe video / audio files (only if video files detected)
Skip this step entirely if `detect` returned zero `video` files.
Video and audio files cannot be read directly. Transcribe them to text first, then treat the transcripts as doc files in Step 3.
**Strategy:** Read the god nodes from `graphify-out/.graphify_detect.json` (or the analysis file if it exists from a previous run). You are already a language model — write a one-sentence domain hint yourself from those labels. Then pass it to Whisper as the initial prompt. No separate API call needed.
**However**, if the corpus has *only* video files and no other docs/code, use the generic fallback prompt: `"Use proper punctuation and paragraph breaks."`
**Step 1 - Write the Whisper prompt yourself.**
Read the top god node labels from detect output or analysis, then compose a short domain hint sentence, for example:
- Labels: `transformer, attention, encoder, decoder` → `"Machine learning research on transformer architectures and attention mechanisms. Use proper punctuation and paragraph breaks."`
- Labels: `kubernetes, deployment, pod, helm` → `"DevOps discussion about Kubernetes deployments and Helm charts. Use proper punctuation and paragraph breaks."`
**Export** it as `GRAPHIFY_WHISPER_PROMPT` (the exact name the transcriber reads — and it must be `export`ed so the child Python process sees it) for the next command.
**Step 2 - Transcribe:**
```bash
export GRAPHIFY_WHISPER_MODEL=base # or whatever --whisper-model the user passed (must be exported)
export GRAPHIFY_WHISPER_PROMPT="<the one-sentence domain hint you composed in Step 1>"
$(cat graphify-out/.graphify_python) -c "
import json, os, sys
from pathlib import Path
from graphify.transcribe import transcribe_all
detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\"))
video_files = detect.get('files', {}).get('video', [])
prompt = os.environ.get('GRAPHIFY_WHISPER_PROMPT', 'Use proper punctuation and paragraph breaks.')
transcript_paths = transcribe_all(video_files, initial_prompt=prompt)
# Write the JSON from Python (NOT a shell '>' redirect): transcribe_all/Whisper
# print progress to stdout, which would otherwise corrupt the JSON file (#1392).
Path('graphify-out/.graphify_transcripts.json').write_text(json.dumps(transcript_paths, ensure_ascii=False), encoding=\"utf-8\")
print(f'Transcribed {len(transcript_paths)} file(s)', file=sys.stderr)
"
```
After transcription:
- Read the transcript paths from `graphify-out/.graphify_transcripts.json`
- Add them to the docs list before dispatching semantic subagents in Step 3B
- Print how many transcripts were created: `Transcribed N video file(s) -> treating as docs`
- If transcription fails for a file, print a warning and continue with the rest
**Whisper model:** Default is `base`. If the user passed `--whisper-model <name>`, `export GRAPHIFY_WHISPER_MODEL=<name>` (it must be exported, not just assigned) before running the command above.
graphify/skills/agents/references/update.md
+192
View File
@@ -0,0 +1,192 @@
# graphify reference: incremental update and cluster-only
Load this only when the user passed `--update` or `--cluster-only`. A first-time full build never reads this file.
## For --update (incremental re-extraction)
Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time.
```bash
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.detect import detect_incremental, save_manifest
from pathlib import Path
result = detect_incremental(Path('INPUT_PATH'))
new_total = result.get('new_total', 0)
print(json.dumps(result, indent=2, ensure_ascii=False))
Path('graphify-out/.graphify_incremental.json').write_text(json.dumps(result, ensure_ascii=False), encoding=\"utf-8\")
deleted = list(result.get('deleted_files', []))
if new_total == 0 and not deleted:
print('No files changed since last run. Nothing to update.')
raise SystemExit(0)
if deleted:
print(f'{len(deleted)} deleted file(s) to prune.')
if new_total > 0:
print(f'{new_total} new/changed file(s) to re-extract.')
"
```
Then populate `.graphify_detect.json` so Steps 3A–6 (which read it unconditionally) see the right state for an incremental run. `files` carries the changed subset (drives Step 3A AST + Step 3B0 cache check on only what changed); `all_files` carries the full corpus for any step that needs corpus-wide context:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
r = json.loads(Path('graphify-out/.graphify_incremental.json').read_text(encoding=\"utf-8\"))
Path('graphify-out/.graphify_detect.json').write_text(json.dumps({
'files': r.get('new_files', {}),
'all_files': r.get('files', {}),
'total_files': r.get('new_total', 0),
'total_words': r.get('total_words', 0),
'skipped_sensitive': r.get('skipped_sensitive', []),
'needs_graph': True,
}, ensure_ascii=False), encoding=\"utf-8\")
"
```
If new files exist, first check whether all changed files are code files:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
result = json.loads(open('graphify-out/.graphify_incremental.json', encoding='utf-8').read()) if Path('graphify-out/.graphify_incremental.json').exists() else {}
code_exts = {'.py','.ts','.js','.go','.rs','.java','.cpp','.c','.rb','.swift','.kt','.cs','.scala','.php','.cc','.cxx','.hpp','.h','.kts','.lua','.toc','.f','.F','.f90','.F90','.f95','.F95','.f03','.F03','.f08','.F08'}
new_files = result.get('new_files', {})
all_changed = [f for files in new_files.values() for f in files]
code_only = all(Path(f).suffix.lower() in code_exts for f in all_changed)
print('code_only:', code_only)
"
```
If `code_only` is True: print `[graphify update] Code-only changes detected - skipping semantic extraction (no LLM needed)`, run only Step 3A (AST) on the changed files, skip Step 3B entirely (no subagents), then go straight to merge and Steps 4–8.
If `code_only` is False (any changed file is a doc/paper/image/video): **first, if any changed file is in `new_files['video']`, run `references/transcribe.md` (Step 2.5) on those files, then rewrite `.graphify_detect.json` to move the resulting transcript paths into `files['document']` and drop `files['video']`** — otherwise raw `.mp4/.mp3` paths are fed to semantic subagents as unreadable media (#1392). Then run the full Steps 3A–3C pipeline as normal.
If no new files exist (only deletions), create an empty extraction so the merge step can prune:
```bash
if [ ! -f graphify-out/.graphify_extract.json ]; then
echo '[graphify update] Only deletions -- creating empty extraction for merge.'
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
Path('graphify-out/.graphify_extract.json').write_text(json.dumps({'nodes':[],'edges':[],'hyperedges':[],'input_tokens':0,'output_tokens':0}), encoding='utf-8')
"
fi
```
Then:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from graphify.build import build_merge
from graphify.detect import save_manifest
# Load new extraction and incremental state
new_extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
incremental = json.loads(Path('graphify-out/.graphify_incremental.json').read_text(encoding=\"utf-8\"))
deleted = list(incremental.get('deleted_files', []))
# prune_sources is ONLY for genuinely DELETED files. Changed/re-extracted files are
# handled by build_merge's replace-on-re-extract (#1344): every source_file in
# new_chunks is dropped from the base before merge, so old/stale nodes don't survive.
# Do NOT add `changed` here: with root= passed, prune_set relativizes to the same base
# as the freshly merged nodes and would DELETE the re-extracted content (#1178 is moot
# now that replace — not the dedup pass — reconciles changed files).
prune = list(deleted) or None
# Use build_merge() — reads graph.json directly without NetworkX round-trip
# so edge direction (calls, implements, imports) is always preserved (#801).
# Pass root= so prune_sources (absolute paths from detect_incremental) are
# relativized to match the graph's relative source_file values; without it
# nothing is pruned and stale nodes accumulate on every update (#1361).
# directed=IS_DIRECTED: replace IS_DIRECTED with True if --directed was given, else
# False. Without it a --directed --update silently rebuilds undirected and collapses
# reciprocal A<->B edges (#1392).
G = build_merge(
[new_extraction],
graph_path='graphify-out/graph.json',
prune_sources=prune,
root='INPUT_PATH',
directed=IS_DIRECTED,
)
print(f'[graphify update] Merged: {G.number_of_nodes()} nodes, {G.number_of_edges()} edges')
# Write merged result back to .graphify_extract.json so Step 4 sees the full graph
merged_out = {
'nodes': [{'id': n, **d} for n, d in G.nodes(data=True)],
'edges': [
# Explicit source/target last so they win over any stale attrs in d.
{**{k: val for k, val in d.items() if k not in ('_src', '_tgt', 'source', 'target')},
'source': d.get('_src', u), 'target': d.get('_tgt', v)}
for u, v, d in G.edges(data=True)
],
# G.graph["hyperedges"] holds hyperedges from both existing graph.json
# and new_extraction (build_merge combines them). Falling back to
# new_extraction only would silently drop prior-run hyperedges (#801).
'hyperedges': list(G.graph.get('hyperedges', [])),
'input_tokens': new_extraction.get('input_tokens', 0),
'output_tokens': new_extraction.get('output_tokens', 0),
}
Path('graphify-out/.graphify_extract.json').write_text(json.dumps(merged_out, ensure_ascii=False), encoding=\"utf-8\")
print(f'[graphify update] Merged extraction written ({len(merged_out[\"nodes\"])} nodes, {len(merged_out[\"edges\"])} edges)')
# Save manifest so next --update diffs against today's state, not the
# prior run's baseline (prevents ghost-node reports on subsequent updates).
# root= matches the build_merge call above so the manifest keys stay relative to
# the scan root — portable across clones/machines, so --update keeps matching
# cached files instead of missing every one after a move (#1417).
save_manifest(incremental['files'], root='INPUT_PATH')
print('[graphify update] Manifest saved.')
"
```
Then run Steps 4–8 on the merged graph as normal.
After Step 4, show the graph diff:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.analyze import graph_diff
from graphify.build import build_from_json
from networkx.readwrite import json_graph
import networkx as nx
from pathlib import Path
# Load old graph (before update) from backup written before merge
old_data = json.loads(Path('graphify-out/.graphify_old.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_old.json').exists() else None
new_extract = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
G_new = build_from_json(new_extract, directed=IS_DIRECTED)
if old_data:
G_old = json_graph.node_link_graph(old_data, edges='links')
diff = graph_diff(G_old, G_new)
print(diff['summary'])
if diff['new_nodes']:
print('New nodes:', ', '.join(n['label'] for n in diff['new_nodes'][:5]))
if diff['new_edges']:
print('New edges:', len(diff['new_edges']))
"
```
Before the merge step, save the old graph: `cp graphify-out/graph.json graphify-out/.graphify_old.json`
Clean up after: `rm -f graphify-out/.graphify_old.json`
---
## For --cluster-only
Skip Steps 1–3. Re-run clustering on the existing graph:
```bash
graphify cluster-only .
```
`graphify cluster-only .` is **self-contained**: it re-clusters, names communities, and regenerates `GRAPH_REPORT.md`, `graph.json`, and `graph.html` from the existing graph. **Do not re-run Steps 5–9** — they read intermediate files (`.graphify_extract.json`, `.graphify_detect.json`, `.graphify_analysis.json`) that a prior build's cleanup (Step 9) already deleted, so they raise `FileNotFoundError` (#1392). When it finishes, present the refreshed `GRAPH_REPORT.md` summary as usual.
pyproject.toml
+1 -1
View File
@@ -113,7 +113,7 @@ include-package-data = false
# under graphify/skills/<host>/references/, and the always-on injection blocks
# under graphify/always_on/. There is no graphify/skills/<host>/SKILL.md in the
# repo, so no SKILL.md glob is needed here.
graphify = ["skill.md", "skill-codex.md", "skill-opencode.md", "skill-kilo.md", "command-kilo.md", "skill-aider.md", "skill-amp.md", "skill-copilot.md", "skill-claw.md", "skill-windows.md", "skill-droid.md", "skill-trae.md", "skill-kiro.md", "skill-vscode.md", "skill-pi.md", "skill-devin.md", "skills/*/references/*.md", "always_on/*.md"]
graphify = ["skill.md", "skill-codex.md", "skill-opencode.md", "skill-kilo.md", "command-kilo.md", "skill-aider.md", "skill-amp.md", "skill-agents.md", "skill-copilot.md", "skill-claw.md", "skill-windows.md", "skill-droid.md", "skill-trae.md", "skill-kiro.md", "skill-vscode.md", "skill-pi.md", "skill-devin.md", "skills/*/references/*.md", "always_on/*.md"]
[tool.pytest.ini_options]
testpaths = ["tests"]
tests/test_agents_platform.py
+235
View File
@@ -0,0 +1,235 @@
"""Tests for the generic `agents` platform and its `skills` alias (#1432).
`graphify install --platform agents` (and the friendly `--platform skills`
alias) installs the skill to the cross-framework Agent-Skills locations: the
spec's user-global ``~/.agents/skills`` and project ``./.agents/skills`` — the
directories ``npx skills`` and spec-compliant frameworks read.
The bare ``graphify install`` behaviour (claude/windows only) is unchanged; the
named platform is opt-in. The ``graphify agents install`` subcommand is the
amp-twin: it also wires AGENTS.md, matching the rendered hooks reference.
"""
import os
import sys
from pathlib import Path
from unittest.mock import patch
import pytest
import graphify.__main__ as mainmod
# --- destination map -----------------------------------------------------------
def test_agents_user_destination_is_user_global_dot_agents(tmp_path):
"""Global agents skill lands at ~/.agents/skills (the spec's user-global dir),
NOT amp's ~/.config/agents/skills."""
with patch("graphify.__main__.Path.home", return_value=tmp_path):
dst = mainmod._platform_skill_destination("agents", project=False)
assert dst == tmp_path / ".agents" / "skills" / "graphify" / "SKILL.md"
def test_agents_project_destination_is_dot_agents(tmp_path):
"""Project agents skill lands at ./.agents/skills."""
dst = mainmod._platform_skill_destination("agents", project=True, project_dir=tmp_path)
assert dst == tmp_path / ".agents" / "skills" / "graphify" / "SKILL.md"
# --- the skills alias ----------------------------------------------------------
def test_skills_alias_resolves_to_agents():
assert mainmod._canonical_platform("skills") == "agents"
assert mainmod._canonical_platform("agents") == "agents"
# A non-aliased platform is returned unchanged.
assert mainmod._canonical_platform("amp") == "amp"
# --- end-to-end install / uninstall via the CLI --------------------------------
def _run(tmp_path, argv, home):
"""Drive main() with argv, cwd at tmp_path, and Path.home redirected."""
old_cwd = Path.cwd()
try:
os.chdir(tmp_path)
with patch.object(sys, "argv", ["graphify", *argv]):
with patch("graphify.__main__.Path.home", return_value=home):
mainmod.main()
finally:
os.chdir(old_cwd)
@pytest.mark.parametrize("platform_arg", ["agents", "skills"])
def test_install_platform_agents_writes_user_global_skill_only(tmp_path, platform_arg):
"""`graphify install --platform agents|skills` writes ~/.agents/skills/...
SKILL.md (+ references) and nothing else — no AGENTS.md (skill-only, like
`--platform amp`)."""
home = tmp_path / "home"
cwd = tmp_path / "cwd"
home.mkdir()
cwd.mkdir()
_run(cwd, ["install", "--platform", platform_arg], home)
skill = home / ".agents" / "skills" / "graphify" / "SKILL.md"
assert skill.exists()
assert (skill.parent / ".graphify_version").read_text() == mainmod.__version__
assert (skill.parent / "references" / "extraction-spec.md").exists()
# Skill-only: the --platform path must not write an AGENTS.md.
assert not (cwd / "AGENTS.md").exists()
def test_uninstall_platform_agents_removes_user_global_skill(tmp_path):
"""Bare `graphify uninstall` clears the ~/.agents/skills skill the AGENTS.md and
amp cleanups never reach."""
home = tmp_path / "home"
cwd = tmp_path / "cwd"
home.mkdir()
cwd.mkdir()
_run(cwd, ["install", "--platform", "agents"], home)
skill = home / ".agents" / "skills" / "graphify" / "SKILL.md"
assert skill.exists()
_run(cwd, ["uninstall"], home)
assert not skill.exists()
# The now-empty skill tree is walked away.
assert not (home / ".agents" / "skills").exists()
@pytest.mark.parametrize("platform_arg", ["agents", "skills"])
def test_uninstall_platform_flag_global_removes_skill(tmp_path, platform_arg):
"""`graphify uninstall --platform agents|skills` (global) clears ~/.agents/skills.
The global uninstall dispatch ignores the selected platform and always runs
uninstall_all; this locks in that the CLI form is accepted and that
uninstall_all's `_remove_skill_file("agents")` reaches the skill.
"""
home = tmp_path / "home"
cwd = tmp_path / "cwd"
home.mkdir()
cwd.mkdir()
_run(cwd, ["install", "--platform", platform_arg], home)
skill = home / ".agents" / "skills" / "graphify" / "SKILL.md"
assert skill.exists()
_run(cwd, ["uninstall", "--platform", platform_arg], home)
assert not skill.exists()
def test_project_uninstall_all_removes_agents_skill(tmp_path):
"""`graphify uninstall --project` (no platform) removes the agents project skill
via the _PLATFORM_CONFIG loop — cleanly, despite agents/amp/antigravity sharing
the ./.agents/skills path (the loop hits an already-removed tree harmlessly)."""
home = tmp_path / "home"
proj = tmp_path / "proj"
home.mkdir()
proj.mkdir()
_run(proj, ["install", "--project", "--platform", "agents"], home)
project_skill = proj / ".agents" / "skills" / "graphify" / "SKILL.md"
assert project_skill.exists()
_run(proj, ["uninstall", "--project"], home)
assert not project_skill.exists()
def test_install_platform_agents_project_writes_dot_agents(tmp_path):
"""`graphify install --project --platform agents` writes ./.agents/skills and
leaves user scope untouched."""
home = tmp_path / "home"
proj = tmp_path / "proj"
home.mkdir()
proj.mkdir()
_run(proj, ["install", "--project", "--platform", "agents"], home)
project_skill = proj / ".agents" / "skills" / "graphify" / "SKILL.md"
assert project_skill.exists()
assert (project_skill.parent / "references" / "extraction-spec.md").exists()
# User scope was not touched.
assert not (home / ".agents" / "skills").exists()
_run(proj, ["uninstall", "--project", "--platform", "agents"], home)
assert not project_skill.exists()
# --- the amp-twin subcommand (graphify agents install) -------------------------
def test_agents_subcommand_install_also_wires_agents_md(tmp_path):
"""`graphify agents install` is the amp-twin: skill at ~/.agents/skills PLUS a
`## graphify` section in AGENTS.md (so the rendered hooks reference, which
points at `graphify agents install`, stays honest)."""
home = tmp_path / "home"
cwd = tmp_path / "cwd"
home.mkdir()
cwd.mkdir()
_run(cwd, ["agents", "install"], home)
skill = home / ".agents" / "skills" / "graphify" / "SKILL.md"
agents_md = cwd / "AGENTS.md"
assert skill.exists()
assert agents_md.exists()
assert "## graphify" in agents_md.read_text(encoding="utf-8")
_run(cwd, ["agents", "uninstall"], home)
assert not skill.exists()
# The section is stripped unconditionally: the file is either removed (it held
# only our section) or no longer contains the marker.
assert not agents_md.exists() or "## graphify" not in agents_md.read_text(encoding="utf-8")
def test_agents_subcommand_install_is_idempotent(tmp_path):
"""Running `graphify agents install` twice leaves a single AGENTS.md section."""
home = tmp_path / "home"
cwd = tmp_path / "cwd"
home.mkdir()
cwd.mkdir()
_run(cwd, ["agents", "install"], home)
_run(cwd, ["agents", "install"], home)
body = (cwd / "AGENTS.md").read_text(encoding="utf-8")
assert body.count("## graphify") == 1, "AGENTS.md gained a duplicate graphify section"
def test_skills_subcommand_is_the_agents_subcommand(tmp_path):
"""`graphify skills install`/`uninstall` behaves exactly like the agents form:
skill at ~/.agents/skills (with references) PLUS the AGENTS.md section."""
home = tmp_path / "home"
cwd = tmp_path / "cwd"
home.mkdir()
cwd.mkdir()
_run(cwd, ["skills", "install"], home)
skill = home / ".agents" / "skills" / "graphify" / "SKILL.md"
agents_md = cwd / "AGENTS.md"
assert skill.exists()
assert (skill.parent / "references" / "extraction-spec.md").exists()
assert agents_md.exists()
assert "## graphify" in agents_md.read_text(encoding="utf-8")
# The `skills` alias of the uninstall subcommand tears it back down.
_run(cwd, ["skills", "uninstall"], home)
assert not skill.exists()
assert not agents_md.exists() or "## graphify" not in agents_md.read_text(encoding="utf-8")
# --- bare install is unchanged -------------------------------------------------
def test_bare_install_does_not_touch_dot_agents(tmp_path):
"""`graphify install` (no platform) stays single-platform claude/windows and
never populates ~/.agents/skills (the #1432 out-of-scope guarantee)."""
home = tmp_path / "home"
cwd = tmp_path / "cwd"
home.mkdir()
cwd.mkdir()
_run(cwd, ["install"], home)
assert not (home / ".agents" / "skills").exists()
tests/test_skillgen.py
+56
View File
@@ -823,3 +823,59 @@ def test_amp_audit_coverage_passes_against_its_own_v8():
assert gen._v8_baseline_ref("amp") == "47042beb05d1f6dd2186c0c499ae2840ce604ead:graphify/skill-amp.md"
problems = gen.audit_coverage(platforms["amp"])
assert problems == [], "\n".join(problems)
# --- the generic agents platform (#1432) ---------------------------------------
def test_agents_renders_its_own_agents_md_hooks_wording():
"""`agents` re-homes amp's agents-md body but with its OWN install wording.
It shares amp's bare, caveat-free `## For native AGENTS.md integration`
section (no `(Trae)` suffix, no PreToolUse note) but points at
`graphify agents install` and is worded for an unspecified host.
"""
core, refs = _platform_artifacts("agents")
hooks = refs["hooks.md"]
assert "## For native AGENTS.md integration" in hooks
assert "## For native AGENTS.md integration (Trae)" not in hooks
assert "make graphify always-on in your agent sessions" in hooks
assert "graphify agents install" in hooks
assert "graphify agents uninstall # remove the section" in hooks
# No amp/trae/claude wording leaks into the agents render.
assert "graphify amp install" not in hooks
assert "graphify trae" not in hooks
assert "graphify claude install" not in hooks
assert "PreToolUse" not in hooks and "PreToolUse" not in core
# The lean-core pointer names AGENTS.md, not CLAUDE.md.
assert "## For the commit hook and native AGENTS.md integration" in core
assert "native CLAUDE.md integration" not in core
def test_agents_body_matches_amp_modulo_hooks_wording():
"""The agents skill body is amp's body verbatim (it re-homes amp's bundle).
The two platforms differ only in the hooks reference's install/uninstall
command wording — everything else (core, query, extraction spec, the other
six references) is byte-identical, which is why agents audits cleanly against
amp's v8 baseline.
"""
platforms = gen.load_platforms()
amp = {a.path.rsplit("/", 1)[-1]: a.content for a in gen.render(platforms["amp"])}
agents = {a.path.rsplit("/", 1)[-1]: a.content for a in gen.render(platforms["agents"])}
# The lean-core skill body is identical (frontmatter + steps, no hooks ref).
assert amp["skill-amp.md"] == agents["skill-agents.md"]
# Every reference except hooks.md is byte-identical.
for name in amp:
if name in ("skill-amp.md", "hooks.md"):
continue
assert amp[name] == agents[name], f"{name} drifted between amp and agents"
assert amp["hooks.md"] != agents["hooks.md"]
def test_agents_audit_baseline_is_amps_v8_body():
"""`agents` is a post-v8 platform, so its audit baseline is amp's v8 body."""
platforms = gen.load_platforms()
assert gen._v8_baseline_ref("agents") == "47042beb05d1f6dd2186c0c499ae2840ce604ead:graphify/skill-amp.md"
problems = gen.audit_coverage(platforms["agents"])
assert problems == [], "\n".join(problems)
tests/test_wheel_packaging.py
+15 -2
View File
@@ -29,14 +29,27 @@ def _has_build() -> bool:
return False
def _skill_bodies() -> list[Path]:
"""Every distinct skill body a platform installs (the SKILL.md is copied from
one of these). A body missing from the wheel makes `graphify install
--platform <host>` hard-exit "not found in package" — the exact failure that
motivated adding the agents platform's skill-agents.md to package-data."""
from graphify.__main__ import _PLATFORM_CONFIG
names = {cfg["skill_file"] for cfg in _PLATFORM_CONFIG.values()}
return sorted({PKG / name for name in names})
def _expected_artifacts() -> list[Path]:
"""Every committed references/*.md (per host) + always_on/*.md block."""
"""Every committed skill body + references/*.md (per host) + always_on/*.md block."""
bodies = _skill_bodies()
refs = sorted((PKG / "skills").glob("*/references/*.md"))
always = sorted((PKG / "always_on").glob("*.md"))
# Sanity: if these are empty the test wiring is broken, not the wheel.
assert bodies, "no platform skill bodies found — packaging test mis-wired"
assert refs, "no skills/*/references/*.md found in repo — packaging test mis-wired"
assert always, "no always_on/*.md found in repo — packaging test mis-wired"
return refs + always
return bodies + refs + always
@pytest.fixture(scope="module")
tools/skillgen/expected/graphify__skill-agents.md
+672
View File
@@ -0,0 +1,672 @@
---
name: graphify
description: "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
---
# /graphify
Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPH_REPORT.md.
## Usage
```
/graphify # full pipeline on current directory → Obsidian vault
/graphify <path> # full pipeline on specific path
/graphify https://github.com/<owner>/<repo> # clone repo then run full pipeline on it
/graphify https://github.com/<owner>/<repo> --branch <branch> # clone a specific branch
/graphify <url1> <url2> ... # clone multiple repos, build each, merge into one cross-repo graph
/graphify <path> --mode deep # thorough extraction, richer INFERRED edges
/graphify <path> --update # incremental - re-extract only new/changed files
/graphify <path> --directed # build directed graph (preserves edge direction: source→target)
/graphify <path> --whisper-model medium # use a larger Whisper model for better transcription accuracy
/graphify <path> --cluster-only # rerun clustering on existing graph
/graphify <path> --no-viz # skip visualization, just report + JSON
/graphify <path> --html # (HTML is generated by default - this flag is a no-op)
/graphify <path> --svg # also export graph.svg (embeds in Notion, GitHub)
/graphify <path> --graphml # export graph.graphml (Gephi, yEd)
/graphify <path> --neo4j # generate graphify-out/cypher.txt for Neo4j
/graphify <path> --neo4j-push bolt://localhost:7687 # push directly to Neo4j
/graphify <path> --falkordb # generate graphify-out/cypher.txt for FalkorDB
/graphify <path> --falkordb-push falkordb://localhost:6379 # push directly to FalkorDB
/graphify <path> --mcp # start MCP stdio server for agent access
/graphify <path> --watch # watch folder, auto-rebuild on code changes (no LLM needed)
/graphify <path> --wiki # build agent-crawlable wiki (index.md + one article per community)
/graphify <path> --obsidian --obsidian-dir ~/vaults/my-project # write vault to custom path (e.g. existing vault)
/graphify add <url> # fetch URL, save to ./raw, update graph
/graphify add <url> --author "Name" # tag who wrote it
/graphify add <url> --contributor "Name" # tag who added it to the corpus
/graphify query "<question>" # BFS traversal - broad context
/graphify query "<question>" --dfs # DFS - trace a specific path
/graphify query "<question>" --budget 1500 # cap answer at N tokens
/graphify path "AuthModule" "Database" # shortest path between two concepts
/graphify explain "SwinTransformer" # plain-language explanation of a node
```
## What graphify is for
Drop any folder of code, docs, papers, images, or video into graphify and get a queryable knowledge graph. Persistent across sessions, honest audit trail (EXTRACTED/INFERRED/AMBIGUOUS), community detection surfaces cross-document connections you wouldn't think to ask about.
## What You Must Do When Invoked
If the user invoked `/graphify --help` or `/graphify -h` (with no other arguments), print the contents of the `## Usage` section above verbatim and stop. Do not run any commands, do not detect files, do not default the path to `.`. Just print the Usage block and return.
**Fast path — existing graph:** Before doing anything else, check whether `graphify-out/graph.json` exists. The expected location is `graphify-out/graph.json` relative to the **current working directory** (i.e. the project root where you are running commands). If it exists AND the user's request is a natural-language question about the codebase (e.g. "How does X work?", "What calls Y?", "Trace the data flow through Z") and NOT an explicit rebuild command (`--update`, `--cluster-only`, or a bare path/URL that implies fresh extraction): **skip Steps 1–5 entirely and jump straight to `## For /graphify query`.** Run `graphify query "<question>"` immediately. Do not run detect. Do not check corpus size. Do not ask the user to narrow. The graph is already built — use it.
If no path was given, use `.` (current directory). Do not ask the user for a path.
If the path argument starts with `https://github.com/` or `http://github.com/`, treat it as a GitHub URL - run Step 0 before anything else, then continue with the resolved local path.
Follow these steps in order. Do not skip steps.
### Step 0 - GitHub repos and multi-path merge (only if a URL or several paths)
Only when the path is one or more `https://github.com/...` URLs, or several local subfolders to merge. See `references/github-and-merge.md` for the clone, cross-repo merge, and monorepo flow, then continue with the resolved local path. A plain local path skips this step.
### Step 1 - Ensure graphify is installed
```bash
# Detect the correct Python interpreter (handles uv tool, pipx, venv, system installs)
PYTHON=""
GRAPHIFY_BIN=$(which graphify 2>/dev/null)
# 1. uv tool installs — most reliable on modern Mac/Linux
if [ -z "$PYTHON" ] && command -v uv >/dev/null 2>&1; then
_UV_PY=$(uv tool run graphifyy python -c "import sys; print(sys.executable)" 2>/dev/null)
if [ -n "$_UV_PY" ]; then PYTHON="$_UV_PY"; fi
fi
# 2. Read shebang from graphify binary (pipx and direct pip installs)
if [ -z "$PYTHON" ] && [ -n "$GRAPHIFY_BIN" ]; then
_SHEBANG=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!')
case "$_SHEBANG" in
*[!a-zA-Z0-9/_.-]*) ;;
*) "$_SHEBANG" -c "import graphify" 2>/dev/null && PYTHON="$_SHEBANG" ;;
esac
fi
# 3. Fall back to python3
if [ -z "$PYTHON" ]; then PYTHON="python3"; fi
if ! "$PYTHON" -c "import graphify" 2>/dev/null; then
if command -v uv >/dev/null 2>&1; then
uv tool install --upgrade graphifyy -q 2>&1 | tail -3
_UV_PY=$(uv tool run graphifyy python -c "import sys; print(sys.executable)" 2>/dev/null)
if [ -n "$_UV_PY" ]; then PYTHON="$_UV_PY"; fi
else
"$PYTHON" -m pip install graphifyy -q 2>/dev/null \
|| "$PYTHON" -m pip install graphifyy -q --break-system-packages 2>&1 | tail -3
fi
fi
# Write interpreter path for all subsequent steps (persists across invocations)
mkdir -p graphify-out
"$PYTHON" -c "import sys; open('graphify-out/.graphify_python', 'w', encoding='utf-8').write(sys.executable)"
# Save scan root so `graphify update` (no args) knows where to look next time
echo "$(cd INPUT_PATH && pwd)" > graphify-out/.graphify_root
```
If the import succeeds, print nothing and move straight to Step 2.
**In every subsequent bash block, replace `python3` with `$(cat graphify-out/.graphify_python)` to use the correct interpreter.**
### Step 2 - Detect files
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.detect import detect
from pathlib import Path
result = detect(Path('INPUT_PATH'))
print(json.dumps(result, ensure_ascii=False))
" > graphify-out/.graphify_detect.json
```
Replace INPUT_PATH with the actual path the user provided. Do NOT cat or print the JSON - read it silently and present a clean summary instead:
```
Corpus: X files · ~Y words
code: N files (.py .ts .go ...)
docs: N files (.md .txt ...)
papers: N files (.pdf ...)
images: N files
video: N files (.mp4 .mp3 ...)
```
Omit any category with 0 files from the summary.
Then act on it:
- If `total_files` is 0: stop with "No supported files found in [path]."
- If `skipped_sensitive` is non-empty: mention file count skipped, not the file names.
- If `total_words` > 2,000,000 OR `total_files` > 500: show the warning. Then compute the top 5 first-level subdirectories by file count:
- Read `scan_root` from the detect JSON (always an absolute path to the resolved INPUT_PATH).
- Concatenate all file lists across all types (`code`, `document`, `paper`, `image`, `video`).
- Filter out any path that starts with `scan_root + "/graphify-out/"` to exclude converted sidecars.
- For each file, strip the `scan_root` prefix and take the first path component. Files directly in `scan_root` with no subdirectory count as `(root)`.
- If all files are in `(root)` with no subdirectories, do not ask to narrow — no subfolders exist. Instead suggest `--no-cluster` to skip the expensive clustering step and proceed.
- Otherwise rank by count, show the top 5 with file counts, then ask which subfolder to run on. Wait for the user's answer before proceeding.
- Otherwise: proceed directly to Step 2.5 if video files were detected, or Step 3 if not.
### Step 2.5 - Video and audio (only if video files detected)
Skip this step entirely if `detect` returned zero `video` files. When the corpus has video or audio, see `references/transcribe.md` to transcribe them to text first, then treat the transcripts as doc files in Step 3.
### Step 3 - Extract entities and relationships
**Before starting:** note whether `--mode deep` was given. You must pass `DEEP_MODE=true` to every subagent in Step B2 if it was. Track this from the original invocation - do not lose it.
This step has two parts: **structural extraction** (deterministic, free) and **semantic extraction** (LLM, costs tokens).
**Before dispatching subagents:** check whether `GEMINI_API_KEY` or `GOOGLE_API_KEY` is set. If neither is set, print this one-liner to the user:
> Tip: set `GEMINI_API_KEY` or `GOOGLE_API_KEY` to use Gemini for semantic extraction (`pip install 'graphifyy[gemini]'`).
Print it once, then continue. If `GEMINI_API_KEY` or `GOOGLE_API_KEY` IS set, use `graphify.llm.extract_corpus_parallel(files, backend="gemini")` for semantic extraction instead of dispatching Claude subagents. The default Gemini model is `gemini-3-flash-preview`; set `GRAPHIFY_GEMINI_MODEL` or pass `--model` in headless CLI flows to override it.
> **No other API keys are read.** If `GEMINI_API_KEY`/`GOOGLE_API_KEY` are unset, fall straight through to Claude Code subagent dispatch (Part B below) — the host session itself is the LLM. graphify does **not** read `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, or any other provider key from the environment. If a host agent prompts the user for `ANTHROPIC_API_KEY` to run extraction, that prompt is a misread of this skill — ignore it and dispatch subagents as written.
**Run Part A (AST) and Part B (semantic) in parallel. Dispatch all semantic subagents AND start AST extraction in the same message. Both can run simultaneously since they operate on different file types. Merge results in Part C as before.**
Note: Parallelizing AST + semantic saves 5-15s on large corpora. AST is deterministic and fast; start it while subagents are processing docs/papers.
#### Part A - Structural extraction for code files
For any code files detected, run AST extraction in parallel with Part B subagents:
```bash
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.extract import collect_files, extract
from pathlib import Path
import json
code_files = []
detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\"))
for f in detect.get('files', {}).get('code', []):
code_files.extend(collect_files(Path(f)) if Path(f).is_dir() else [Path(f)])
if code_files:
result = extract(code_files, cache_root=Path('INPUT_PATH'))
Path('graphify-out/.graphify_ast.json').write_text(json.dumps(result, indent=2, ensure_ascii=False), encoding=\"utf-8\")
print(f'AST: {len(result[\"nodes\"])} nodes, {len(result[\"edges\"])} edges')
else:
Path('graphify-out/.graphify_ast.json').write_text(json.dumps({'nodes':[],'edges':[],'input_tokens':0,'output_tokens':0}, ensure_ascii=False), encoding=\"utf-8\")
print('No code files - skipping AST extraction')
"
```
#### Part B - Semantic extraction (parallel subagents)
**Fast path:** If detection found zero docs, papers, and images (code-only corpus), skip Part B entirely and go straight to Part C. AST handles code - there is nothing for semantic subagents to do. **First write an empty semantic file** so Part C's merge has its input (it reads `.graphify_semantic.json` unconditionally; without this a code-only run hits `FileNotFoundError`):
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
Path('graphify-out/.graphify_semantic.json').write_text(json.dumps({'nodes':[],'edges':[],'hyperedges':[],'input_tokens':0,'output_tokens':0}), encoding='utf-8')
"
```
**MANDATORY: You MUST use the Agent tool here. Reading files yourself one-by-one is forbidden - it is 5-10x slower. If you do not use the Agent tool you are doing this wrong.**
Before dispatching subagents, print a timing estimate:
- Load `total_words` and file counts from `graphify-out/.graphify_detect.json`
- Estimate agents needed: `ceil(uncached_non_code_files / 22)` (chunk size is 20-25)
- Estimate time: ~45s per agent batch (they run in parallel, so total ≈ 45s × ceil(agents/parallel_limit))
- Print: "Semantic extraction: ~N files → X agents, estimated ~Ys"
**Step B0 - Check extraction cache first**
Before dispatching any subagents, check which files already have cached extraction results:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import check_semantic_cache
from pathlib import Path
detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\"))
# Only content files go to semantic extraction. Code is already covered structurally
# by the AST pass (Part A); flattening every category here makes subagents re-read
# every source file (#1392). Video is transcribed to a document in Step 2.5 first.
all_files = [f for cat in ('document', 'paper', 'image') for f in detect['files'].get(cat, [])]
cached_nodes, cached_edges, cached_hyperedges, uncached = check_semantic_cache(all_files, root='INPUT_PATH')
# Always (re)write the cache file: write hits, else DELETE any leftover from a prior
# run so Part C never merges a stale .graphify_cached.json (#1392).
if cached_nodes or cached_edges or cached_hyperedges:
Path('graphify-out/.graphify_cached.json').write_text(json.dumps({'nodes': cached_nodes, 'edges': cached_edges, 'hyperedges': cached_hyperedges}, ensure_ascii=False), encoding=\"utf-8\")
else:
Path('graphify-out/.graphify_cached.json').unlink(missing_ok=True)
Path('graphify-out/.graphify_uncached.txt').write_text('\n'.join(uncached), encoding=\"utf-8\")
print(f'Cache: {len(all_files)-len(uncached)} files hit, {len(uncached)} files need extraction')
"
```
Only dispatch subagents for files listed in `graphify-out/.graphify_uncached.txt`. If all files are cached, skip to Part C directly.
**Step B1 - Split into chunks**
Load files from `graphify-out/.graphify_uncached.txt`. Split into chunks of 20-25 files each. Each image gets its own chunk (vision needs separate context). When splitting, group files from the same directory together so related artifacts land in the same chunk and cross-file relationships are more likely to be extracted.
**Step B2 - Dispatch ALL subagents in a single message**
> Uses the `Task` tool for parallel subagent dispatch.
> Call `Task` once per chunk — ALL in the same response so they run in parallel.
Pass the extraction prompt as the task description:
```
Task(description="Your task is to perform the following. Follow the instructions below exactly.\n\n<agent-instructions>\n[extraction prompt, with FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE substituted]\n</agent-instructions>\n\nExecute this now. Output ONLY the structured JSON response.")
```
Each subagent writes its result to its own `graphify-out/.graphify_chunk_NN.json`. Collect results as each `Task` completes and parse each as JSON.
CHUNK_PATH must be an **absolute** path — derive it before dispatching:
```bash
PROJECT_ROOT=$(pwd) # cwd — where Part C globs graphify-out/ (NOT .graphify_root/scan dir, #1392)
# Then for chunk N: CHUNK_PATH="${PROJECT_ROOT}/graphify-out/.graphify_chunk_0N.json"
```
Subagent prompt template:
See `references/extraction-spec.md` for the exact subagent prompt (JSON schema, node-ID rules, confidence rubric, hyperedge, and vision rules). Load it only here, only when at least one chunk holds a doc, paper, or image; a pure-code corpus has skipped Part B and never reads it. Pass each subagent that prompt verbatim with FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE, and CHUNK_PATH substituted, and have it write the result to CHUNK_PATH.
**Step B3 - Collect, cache, and merge**
Wait for all subagents. For each result:
- Check that `graphify-out/.graphify_chunk_NN.json` exists on disk — this is the success signal
- If the file exists and contains valid JSON with `nodes` and `edges`, include it and save to cache
- If the file is missing, the subagent was likely dispatched as read-only (Explore type) — print a warning: "chunk N missing from disk — subagent may have been read-only. Re-run with general-purpose agent." Do not silently skip.
- If a subagent failed or returned invalid JSON, print a warning and skip that chunk - do not abort
If more than half the chunks failed or are missing, stop and tell the user to re-run and ensure `subagent_type="general-purpose"` is used.
Merge all chunk files into `.graphify_semantic_new.json`. **After each Agent call completes, read the real token counts from the Agent tool result's `usage` field and write them back into the chunk JSON before merging** — the chunk JSON itself always has placeholder zeros. Then run:
```bash
$(cat graphify-out/.graphify_python) -c "
import json, glob
from pathlib import Path
chunks = sorted(glob.glob('graphify-out/.graphify_chunk_*.json'))
all_nodes, all_edges, all_hyperedges = [], [], []
total_in, total_out = 0, 0
for c in chunks:
d = json.loads(Path(c).read_text(encoding=\"utf-8\"))
all_nodes += d.get('nodes', [])
all_edges += d.get('edges', [])
all_hyperedges += d.get('hyperedges', [])
total_in += d.get('input_tokens', 0)
total_out += d.get('output_tokens', 0)
Path('graphify-out/.graphify_semantic_new.json').write_text(json.dumps({
'nodes': all_nodes, 'edges': all_edges, 'hyperedges': all_hyperedges,
'input_tokens': total_in, 'output_tokens': total_out,
}, indent=2, ensure_ascii=False), encoding=\"utf-8\")
print(f'Merged {len(chunks)} chunks: {total_in:,} in / {total_out:,} out tokens')
"
```
Save new results to cache:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.cache import save_semantic_cache
from pathlib import Path
new = json.loads(Path('graphify-out/.graphify_semantic_new.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]}
saved = save_semantic_cache(new.get('nodes', []), new.get('edges', []), new.get('hyperedges', []), root='INPUT_PATH')
print(f'Cached {saved} files')
"
```
Merge cached + new results into `graphify-out/.graphify_semantic.json`:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
cached = json.loads(Path('graphify-out/.graphify_cached.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_cached.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]}
new = json.loads(Path('graphify-out/.graphify_semantic_new.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_semantic_new.json').exists() else {'nodes':[],'edges':[],'hyperedges':[]}
all_nodes = cached['nodes'] + new.get('nodes', [])
all_edges = cached['edges'] + new.get('edges', [])
all_hyperedges = cached.get('hyperedges', []) + new.get('hyperedges', [])
seen = set()
deduped = []
for n in all_nodes:
if n['id'] not in seen:
seen.add(n['id'])
deduped.append(n)
merged = {
'nodes': deduped,
'edges': all_edges,
'hyperedges': all_hyperedges,
'input_tokens': new.get('input_tokens', 0),
'output_tokens': new.get('output_tokens', 0),
}
Path('graphify-out/.graphify_semantic.json').write_text(json.dumps(merged, indent=2, ensure_ascii=False), encoding=\"utf-8\")
print(f'Extraction complete - {len(deduped)} nodes, {len(all_edges)} edges ({len(cached[\"nodes\"])} from cache, {len(new.get(\"nodes\",[]))} new)')
"
```
Clean up temp files: `rm -f graphify-out/.graphify_cached.json graphify-out/.graphify_uncached.txt graphify-out/.graphify_semantic_new.json`
#### Part C - Merge AST + semantic into final extraction
```bash
$(cat graphify-out/.graphify_python) -c "
import sys, json
from pathlib import Path
ast = json.loads(Path('graphify-out/.graphify_ast.json').read_text(encoding=\"utf-8\"))
sem = json.loads(Path('graphify-out/.graphify_semantic.json').read_text(encoding=\"utf-8\"))
# Merge: AST nodes first, semantic nodes deduplicated by id
seen = {n['id'] for n in ast['nodes']}
merged_nodes = list(ast['nodes'])
for n in sem['nodes']:
if n['id'] not in seen:
merged_nodes.append(n)
seen.add(n['id'])
merged_edges = ast['edges'] + sem['edges']
merged_hyperedges = sem.get('hyperedges', [])
merged = {
'nodes': merged_nodes,
'edges': merged_edges,
'hyperedges': merged_hyperedges,
'input_tokens': sem.get('input_tokens', 0),
'output_tokens': sem.get('output_tokens', 0),
}
Path('graphify-out/.graphify_extract.json').write_text(json.dumps(merged, indent=2, ensure_ascii=False), encoding=\"utf-8\")
total = len(merged_nodes)
edges = len(merged_edges)
print(f'Merged: {total} nodes, {edges} edges ({len(ast[\"nodes\"])} AST + {len(sem[\"nodes\"])} semantic)')
"
```
### Step 4 - Build graph, cluster, analyze, generate outputs
**Before starting:** the code blocks below pass `directed=IS_DIRECTED` to `build_from_json()`. Replace `IS_DIRECTED` with `True` if `--directed` was given (builds a `DiGraph` preserving edge direction source→target), otherwise `False` (the default undirected `Graph`). Substitute it the same way you substitute `INPUT_PATH` — do not leave the literal `IS_DIRECTED` in the code.
```bash
mkdir -p graphify-out
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import cluster, score_all
from graphify.analyze import god_nodes, surprising_connections, suggest_questions
from graphify.report import generate
from graphify.export import to_json
from pathlib import Path
extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
detection = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\"))
# root= mirrors the --update runbook (#1361): relativize source_file to the same
# base so the full build and incremental --update never drift apart on re-extract.
G = build_from_json(extraction, root='INPUT_PATH', directed=IS_DIRECTED)
# Guard BEFORE any write: an empty extraction must not clobber a good graph.json /
# GRAPH_REPORT.md / analysis sidecar. Check immediately after build (#1392).
if G.number_of_nodes() == 0:
print('ERROR: Graph is empty - extraction produced no nodes.')
print('Possible causes: all files were skipped, binary-only corpus, or extraction failed.')
raise SystemExit(1)
communities = cluster(G)
cohesion = score_all(G, communities)
tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)}
gods = god_nodes(G)
surprises = surprising_connections(G, communities)
labels = {cid: 'Community ' + str(cid) for cid in communities}
# Placeholder questions - regenerated with real labels in Step 5
questions = suggest_questions(G, communities, labels)
# Export FIRST and honor the #479 shrink-guard: to_json returns False (writing
# nothing) when the new graph is smaller than the existing graph.json. Only write
# GRAPH_REPORT.md + the analysis sidecar when the graph was actually written, so
# they never describe a graph that graph.json doesn't contain (#1392).
wrote = to_json(G, communities, 'graphify-out/graph.json')
if not wrote:
print('ERROR: refused to shrink graphify-out/graph.json (existing graph has more nodes; #479).')
print('If this shrink is intentional (you deleted files), re-run a full build with --force.')
raise SystemExit(1)
report = generate(G, communities, cohesion, labels, gods, surprises, detection, tokens, 'INPUT_PATH', suggested_questions=questions)
Path('graphify-out/GRAPH_REPORT.md').write_text(report, encoding=\"utf-8\")
analysis = {
'communities': {str(k): v for k, v in communities.items()},
'cohesion': {str(k): v for k, v in cohesion.items()},
'gods': gods,
'surprises': surprises,
'questions': questions,
}
Path('graphify-out/.graphify_analysis.json').write_text(json.dumps(analysis, indent=2, ensure_ascii=False), encoding=\"utf-8\")
print(f'Graph: {G.number_of_nodes()} nodes, {G.number_of_edges()} edges, {len(communities)} communities')
"
```
If this step prints `ERROR: Graph is empty`, stop and tell the user what happened - do not proceed to labeling or visualization.
Replace INPUT_PATH with the actual path.
### Step 4.5 - Graph health check (read-only integrity gate)
A non-destructive diagnostic on the extraction, before labeling. It surfaces edge collapse, dangling/missing endpoints, and self-loops — the silent-corruption modes of incremental updates and AST/LLM id mismatches. Read-only; never aborts.
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from graphify.diagnostics import diagnose_extraction, format_diagnostic_report
extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
summary = diagnose_extraction(extraction, directed=IS_DIRECTED, root='INPUT_PATH')
print(format_diagnostic_report(summary))
flags = [f'{summary[k]} {label}' for k, label in (
('dangling_endpoint_edges', 'dangling-endpoint edges'),
('missing_endpoint_edges', 'missing-endpoint edges'),
('self_loop_edges', 'self-loop edges'),
('directed_same_endpoint_collapsed_edges', 'collapsed (directed) edges'),
('undirected_same_endpoint_collapsed_edges', 'collapsed (undirected) edges'),
) if summary.get(k, 0)]
print('GRAPH HEALTH WARNING: ' + '; '.join(flags) + ' - graph may be incomplete/corrupt.' if flags else 'Graph health: OK (no dangling/missing/collapsed edges).')
"
```
Substitute `IS_DIRECTED` and `INPUT_PATH` as in Step 4. If a `GRAPH HEALTH WARNING` prints, surface it in the final summary (do not abort — the graph is still usable, but the integrity issue must be visible, per the Honesty Rules).
### Step 5 - Label communities
Read `graphify-out/.graphify_analysis.json`. For each community key, look at its node labels and write a 2-5 word plain-language name (e.g. "Attention Mechanism", "Training Pipeline", "Data Loading").
Then regenerate the report and save the labels for the visualizer:
```bash
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.build import build_from_json
from graphify.cluster import score_all
from graphify.analyze import god_nodes, surprising_connections, suggest_questions
from graphify.report import generate
from pathlib import Path
extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
detection = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\"))
analysis = json.loads(Path('graphify-out/.graphify_analysis.json').read_text(encoding=\"utf-8\"))
# root= as in Step 4 / the --update runbook (#1361) — same base for node-key parity.
G = build_from_json(extraction, root='INPUT_PATH', directed=IS_DIRECTED)
communities = {int(k): v for k, v in analysis['communities'].items()}
cohesion = {int(k): v for k, v in analysis['cohesion'].items()}
tokens = {'input': extraction.get('input_tokens', 0), 'output': extraction.get('output_tokens', 0)}
# LABELS - replace these with the names you chose above
labels = LABELS_DICT
# Regenerate questions with real community labels (labels affect question phrasing)
questions = suggest_questions(G, communities, labels)
report = generate(G, communities, cohesion, labels, analysis['gods'], analysis['surprises'], detection, tokens, 'INPUT_PATH', suggested_questions=questions)
Path('graphify-out/GRAPH_REPORT.md').write_text(report, encoding=\"utf-8\")
Path('graphify-out/.graphify_labels.json').write_text(json.dumps({str(k): v for k, v in labels.items()}, ensure_ascii=False), encoding=\"utf-8\")
print('Report updated with community labels')
"
```
Replace `LABELS_DICT` with the actual dict you constructed (e.g. `{0: "Attention Mechanism", 1: "Training Pipeline"}`).
Replace INPUT_PATH with the actual path.
### Step 6 - Generate Obsidian vault (opt-in) + HTML
**Generate HTML always** (unless `--no-viz`). **Obsidian vault only if `--obsidian` was explicitly given** — skip it otherwise, it generates one file per node.
If `--obsidian` was given:
- If `--obsidian-dir <path>` was also given, pass it via `--dir`. Otherwise defaults to `graphify-out/obsidian`.
```bash
graphify export obsidian
# or with custom dir: graphify export obsidian --dir ~/vaults/my-project
```
Generate the HTML graph (always, unless `--no-viz`):
```bash
graphify export html # auto-aggregates to community view if graph > 5000 nodes
# or: graphify export html --no-viz
```
### Steps 6b-8 - Wiki, Neo4j, FalkorDB, SVG, GraphML, MCP, benchmark (only on their flags)
These run only when their flag is present (`--wiki`, `--neo4j`/`--neo4j-push`, `--falkordb`/`--falkordb-push`, `--svg`, `--graphml`, `--mcp`) or, for the token-reduction benchmark, when `total_words` exceeds 5,000. A default run with no export flags skips all of them. See `references/exports.md` for each one. Run any `--wiki` export before Step 9 cleanup so `.graphify_labels.json` is still available.
---
### Step 9 - Save manifest, update cost tracker, clean up, and report
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from datetime import datetime, timezone
from graphify.detect import save_manifest
# Save manifest for --update
detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\"))
# In --update mode, 'all_files' carries the full corpus; 'files' is the changed
# subset. Full-rebuild mode populates only 'files', so the fallback handles that.
# root= relativizes the manifest keys to the scan root (same base as the build),
# so the on-disk manifest is portable across clones/machines and a later --update
# matches cached files instead of missing every one (#1417).
save_manifest(detect.get('all_files') or detect['files'], root='INPUT_PATH')
# Update cumulative cost tracker
extract = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
input_tok = extract.get('input_tokens', 0)
output_tok = extract.get('output_tokens', 0)
cost_path = Path('graphify-out/cost.json')
if cost_path.exists():
cost = json.loads(cost_path.read_text(encoding=\"utf-8\"))
else:
cost = {'runs': [], 'total_input_tokens': 0, 'total_output_tokens': 0}
cost['runs'].append({
'date': datetime.now(timezone.utc).isoformat(),
'input_tokens': input_tok,
'output_tokens': output_tok,
'files': detect.get('total_files', 0),
})
cost['total_input_tokens'] += input_tok
cost['total_output_tokens'] += output_tok
cost_path.write_text(json.dumps(cost, indent=2, ensure_ascii=False), encoding=\"utf-8\")
print(f'This run: {input_tok:,} input tokens, {output_tok:,} output tokens')
print(f'All time: {cost[\"total_input_tokens\"]:,} input, {cost[\"total_output_tokens\"]:,} output ({len(cost[\"runs\"])} runs)')
"
rm -f graphify-out/.graphify_detect.json graphify-out/.graphify_extract.json graphify-out/.graphify_ast.json graphify-out/.graphify_semantic.json graphify-out/.graphify_analysis.json
find graphify-out -maxdepth 1 -name '.graphify_chunk_*.json' -delete 2>/dev/null
rm -f graphify-out/.needs_update 2>/dev/null || true
```
Replace INPUT_PATH with the actual path (same value used in Steps 4-5) so the manifest is relativized to the scan root.
Tell the user (omit the obsidian line unless --obsidian was given):
```
Graph complete. Outputs in PATH_TO_DIR/graphify-out/
graph.html - interactive graph, open in browser
GRAPH_REPORT.md - audit report
graph.json - raw graph data
obsidian/ - Obsidian vault (only if --obsidian was given)
```
If graphify saved you time, consider supporting it: https://github.com/sponsors/safishamsi
Replace PATH_TO_DIR with the actual absolute path of the directory that was processed.
Then paste these sections from GRAPH_REPORT.md directly into the chat:
- God Nodes
- Surprising Connections
- Suggested Questions
Do NOT paste the full report - just those three sections. Keep it concise.
Then immediately offer to explore. Pick the single most interesting suggested question from the report - the one that crosses the most community boundaries or has the most surprising bridge node - and ask:
> "The most interesting question this graph can answer: **[question]**. Want me to trace it?"
If the user says yes, run `/graphify query "[question]"` on the graph and walk them through the answer using the graph structure - which nodes connect, which community boundaries get crossed, what the path reveals. Keep going as long as they want to explore. Each answer should end with a natural follow-up ("this connects to X - want to go deeper?") so the session feels like navigation, not a one-shot report.
The graph is the map. Your job after the pipeline is to be the guide.
---
## Interpreter guard for subcommands
Before running any subcommand below (`--update`, `--cluster-only`, `query`, `path`, `explain`, `add`), check that `.graphify_python` exists. If it's missing (e.g. user deleted `graphify-out/`), re-resolve the interpreter first:
```bash
if [ ! -f graphify-out/.graphify_python ]; then
GRAPHIFY_BIN=$(which graphify 2>/dev/null)
if [ -n "$GRAPHIFY_BIN" ]; then
PYTHON=$(head -1 "$GRAPHIFY_BIN" | tr -d '#!')
case "$PYTHON" in *[!a-zA-Z0-9/_.-]*) PYTHON="python3" ;; esac
else
PYTHON="python3"
fi
mkdir -p graphify-out
"$PYTHON" -c "import sys; open('graphify-out/.graphify_python', 'w', encoding='utf-8').write(sys.executable)"
fi
```
## For --update and --cluster-only
Both are non-default subcommands. `--update` re-extracts only new or changed files; `--cluster-only` reruns clustering on the existing graph. See `references/update.md` for both flows.
---
## For /graphify query
When `graphify-out/graph.json` already exists and the user asks a question about the corpus, answer from the graph rather than rebuilding it:
```bash
graphify query "<question>"
```
Before traversal, expand the question against the graph's own vocabulary so a wording mismatch does not collapse the answer to noise. If the `graphify query` CLI is unavailable, fall back to an inline NetworkX traversal of `graphify-out/graph.json`. Answer using only what the graph output contains, and quote `source_location` when citing a specific fact. For that vocab-expansion step, the BFS/DFS traversal modes, the `--budget` cap, the NetworkX fallback, `save-result` feedback, and the `/graphify path` and `/graphify explain` flows, see `references/query.md`.
---
## For /graphify add and --watch
Neither is part of the default build. When the user runs `/graphify add <url>` to fetch a URL into the corpus, or passes `--watch` to auto-rebuild on file changes, see `references/add-watch.md`.
---
## For the commit hook and native AGENTS.md integration
When the user asks to install the post-commit auto-rebuild hook or wire graphify into a project's AGENTS.md, see `references/hooks.md`.
---
## Honesty Rules
- Never invent an edge. If unsure, use AMBIGUOUS.
- Never skip the corpus check warning.
- Always show token cost in the report.
- Never hide cohesion scores behind symbols - show the raw number.
- Never run HTML viz on a graph with more than 5,000 nodes without warning the user.
tools/skillgen/expected/graphify__skills__agents__references__add-watch.md
+56
View File
@@ -0,0 +1,56 @@
# graphify reference: add a URL and watch a folder
Load this when the user ran `/graphify add <url>` or passed `--watch`. Neither is part of the default build.
## For /graphify add
Fetch a URL and add it to the corpus, then update the graph.
```bash
$(cat graphify-out/.graphify_python) -c "
import sys
from graphify.ingest import ingest
from pathlib import Path
try:
out = ingest('URL', Path('./raw'), author='AUTHOR', contributor='CONTRIBUTOR')
print(f'Saved to {out}')
except ValueError as e:
print(f'error: {e}', file=sys.stderr)
sys.exit(1)
except RuntimeError as e:
print(f'error: {e}', file=sys.stderr)
sys.exit(1)
"
```
Replace `URL` with the actual URL, `AUTHOR` with the user's name if provided, `CONTRIBUTOR` likewise. If the command exits with an error, tell the user what went wrong - do not silently continue. After a successful save, automatically run the `--update` pipeline on `./raw` to merge the new file into the existing graph.
Supported URL types (auto-detected):
- YouTube / any video URL → audio downloaded via yt-dlp, transcribed to `.txt` on next run (requires `pip install 'graphifyy[video]'`)
- Twitter/X → fetched via oEmbed, saved as `.md` with tweet text and author
- arXiv → abstract + metadata saved as `.md`
- PDF → downloaded as `.pdf`
- Images (.png/.jpg/.webp) → downloaded, Claude vision extracts on next run
- Any webpage → converted to markdown via html2text
---
## For --watch
Start a background watcher that monitors a folder and auto-updates the graph when files change.
```bash
$(cat graphify-out/.graphify_python) -m graphify.watch INPUT_PATH --debounce 3
```
Replace INPUT_PATH with the folder to watch. Behavior depends on what changed:
- **Code files only (.py, .ts, .go, etc.):** re-runs AST extraction + rebuild + cluster immediately, no LLM needed. `graph.json` and `GRAPH_REPORT.md` are updated automatically.
- **Docs, papers, or images:** writes a `graphify-out/needs_update` flag and prints a notification to run `/graphify --update` (LLM semantic re-extraction required).
Debounce (default 3s): waits until file activity stops before triggering, so a wave of parallel agent writes doesn't trigger a rebuild per file.
Press Ctrl+C to stop.
For agentic workflows: run `--watch` in a background terminal. Code changes from agent waves are picked up automatically between waves. If agents are also writing docs or notes, you'll need a manual `/graphify --update` after those waves.
tools/skillgen/expected/graphify__skills__agents__references__exports.md
+87
View File
@@ -0,0 +1,87 @@
# graphify reference: extra exports and benchmark
Load this when the user passed one of the export flags (`--wiki`, `--neo4j`, `--neo4j-push`, `--falkordb`, `--falkordb-push`, `--svg`, `--graphml`, `--mcp`), or when the corpus is large enough for the token-reduction benchmark. Each step runs only for its own flag.
### Step 6b - Wiki (only if --wiki flag)
**Only run this step if `--wiki` was explicitly given in the original command.**
Run this before Step 9 (cleanup) so `.graphify_labels.json` is still available.
```bash
graphify export wiki
```
### Step 7 - Neo4j export (only if --neo4j or --neo4j-push flag)
**If `--neo4j`** - generate a Cypher file for manual import:
```bash
graphify export neo4j
```
**If `--neo4j-push <uri>`** - push directly to a running Neo4j instance. Ask the user for credentials if not provided:
```bash
graphify export neo4j --push bolt://localhost:7687 --user neo4j --password PASSWORD
```
Default URI is `bolt://localhost:7687`, default user is `neo4j`. Uses MERGE - safe to re-run without creating duplicates.
### Step 7a - FalkorDB export (only if --falkordb or --falkordb-push flag)
**If `--falkordb`** - generate a Cypher file. The statements are OpenCypher, but FalkorDB's `GRAPH.QUERY` runs one statement at a time (no bulk script import like Neo4j's `cypher-shell`), so prefer `--falkordb-push` to load a graph. Use this only when you want the portable `cypher.txt` artifact:
```bash
graphify export falkordb
```
**If `--falkordb-push <uri>`** - push directly to a running FalkorDB instance. Credentials are optional; ask the user only if the instance requires auth:
```bash
graphify export falkordb --push falkordb://localhost:6379
```
Default URI is `falkordb://localhost:6379` (the scheme is informational - `redis://` or a bare `host:port` work too), auth is optional, and the target graph defaults to `graphify`. Uses MERGE - safe to re-run without creating duplicates.
### Step 7b - SVG export (only if --svg flag)
```bash
graphify export svg
```
### Step 7c - GraphML export (only if --graphml flag)
```bash
graphify export graphml
```
### Step 7d - MCP server (only if --mcp flag)
```bash
$(cat graphify-out/.graphify_python) -m graphify.serve graphify-out/graph.json
```
This starts a stdio MCP server that exposes tools: `query_graph`, `get_node`, `get_neighbors`, `get_community`, `god_nodes`, `graph_stats`, `shortest_path`. Add to Claude Desktop or any MCP-compatible agent orchestrator so other agents can query the graph live.
To configure in Claude Desktop, add to `claude_desktop_config.json`. Claude Desktop can't run `$(...)`, and under `uv tool install` the system `python3` can't import graphify — so set `command` to the **absolute interpreter path** printed by `cat graphify-out/.graphify_python`:
```json
{
"mcpServers": {
"graphify": {
"command": "<absolute path from: cat graphify-out/.graphify_python>",
"args": ["-m", "graphify.serve", "/absolute/path/to/graphify-out/graph.json"]
}
}
}
```
### Step 8 - Token reduction benchmark (only if total_words > 5000)
If `total_words` from `graphify-out/.graphify_detect.json` is greater than 5,000, run:
```bash
graphify benchmark
```
Print the output directly in chat. If `total_words <= 5000`, skip silently - the graph value is structural clarity, not token compression, for small corpora.
tools/skillgen/expected/graphify__skills__agents__references__extraction-spec.md
+70
View File
@@ -0,0 +1,70 @@
# graphify reference: extraction subagent prompt
Load this in Step 3 Part B when the corpus has at least one doc, paper, or image chunk. A pure-code corpus skips Part B and never reads this file. Each semantic subagent receives the prompt below verbatim (substitute FILE_LIST, CHUNK_NUM, TOTAL_CHUNKS, DEEP_MODE, and CHUNK_PATH).
```
You are a graphify extraction subagent. Read the files listed and extract a knowledge graph fragment.
Output ONLY valid JSON matching the schema below - no explanation, no markdown fences, no preamble.
Files (chunk CHUNK_NUM of TOTAL_CHUNKS):
FILE_LIST
Rules:
- EXTRACTED: relationship explicit in source (import, call, citation, "see §3.2")
- INFERRED: reasonable inference (shared data structure, implied dependency)
- AMBIGUOUS: uncertain - flag for review, do not omit
Code files: focus on semantic edges AST cannot find (call relationships, shared data, arch patterns).
Do not re-extract imports - AST already has those.
Doc/paper files: extract named concepts, entities, citations. For rationale (WHY decisions were made, trade-offs, design intent): store as a `rationale` attribute on the relevant concept node — do NOT create a separate rationale node or fragment node. Only create a node for something that is itself a named entity or concept. Use `file_type:"rationale"` for concept-like nodes (ideas, principles, mechanisms, design patterns). `file_type` MUST be one of exactly these six values: `code`, `document`, `paper`, `image`, `rationale`, `concept`. Any other value is invalid and will be rejected.
Code files: when adding `calls` edges, source MUST be the caller (the function/class doing the calling), target MUST be the callee. Never reverse this direction. `calls` edges MUST stay within one language: a Python function cannot `calls` a JS/TS/Go/Rust/Java symbol and vice versa — cross-language call edges are phantom artifacts, never emit them.
Image files: use vision to understand what the image IS - do not just OCR.
UI screenshot: layout patterns, design decisions, key elements, purpose.
Chart: metric, trend/insight, data source.
Tweet/post: claim as node, author, concepts mentioned.
Diagram: components and connections.
Research figure: what it demonstrates, method, result.
Handwritten/whiteboard: ideas and arrows, mark uncertain readings AMBIGUOUS.
DEEP_MODE (if --mode deep was given): be aggressive with INFERRED edges - indirect deps,
shared assumptions, latent couplings. Mark uncertain ones AMBIGUOUS instead of omitting.
Semantic similarity: if two concepts in this chunk solve the same problem or represent the same idea without any structural link (no import, no call, no citation), add a `semantically_similar_to` edge marked INFERRED with a confidence_score reflecting how similar they are (0.6-0.95). Examples:
- Two functions that both validate user input but never call each other
- A class in code and a concept in a paper that describe the same algorithm
- Two error types that handle the same failure mode differently
Only add these when the similarity is genuinely non-obvious and cross-cutting. Do not add them for trivially similar things.
Hyperedges: if 3 or more nodes clearly participate together in a shared concept, flow, or pattern that is not captured by pairwise edges alone, add a hyperedge to a top-level `hyperedges` array. Examples:
- All classes that implement a common protocol or interface
- All functions in an authentication flow (even if they don't all call each other)
- All concepts from a paper section that form one coherent idea
Use sparingly — only when the group relationship adds information beyond the pairwise edges. Maximum 3 hyperedges per chunk.
If a file has YAML frontmatter (--- ... ---), copy source_url, captured_at, author,
contributor onto every node from that file.
confidence_score is REQUIRED on every edge - never omit it, never use 0.5 as a default:
- EXTRACTED edges: confidence_score = 1.0 always
- INFERRED edges: pick exactly ONE value from this set — never 0.5:
0.95 direct structural evidence (shared data structure, named cross-file reference).
0.85 strong inference (clear functional alignment, no direct symbol link).
0.75 reasonable inference (shared problem domain + similar shape, requires interpretation).
0.65 weak inference (thematically related, no shape evidence).
0.55 speculative but plausible (surface-level co-occurrence only).
Models follow discrete rubrics better than continuous ranges; the bimodal
distribution observed in production (>50% at 0.5, >40% at 0.85+) shows the
range guidance is being collapsed to a binary. If no value above fits, mark
the edge AMBIGUOUS rather than picking 0.4 or below.
- AMBIGUOUS edges: 0.1-0.3
Node ID format: lowercase, only `[a-z0-9_]`, no dots or slashes. Format: `{stem}_{entity}` where stem is `{parent_dir}_{filename_without_ext}` (the **immediate** parent directory name + the filename stem, both lowercased with non-alphanumeric chars replaced by `_`) and entity is the symbol name similarly normalized. Only one level of parent is used — not the full path. Examples: `src/auth/session.py` + `ValidateToken` → `auth_session_validatetoken`; `lib/utils/helpers.py` + `parse_url` → `utils_helpers_parse_url`; `tests/test_foo.py` + `_helper` → `tests_test_foo_helper`. Top-level files (no parent dir, e.g. `setup.py`) use just the filename stem: `setup_my_func`. This must match the ID the AST extractor generates — using just the filename (e.g., `session_validatetoken`) or the full path (e.g., `src_auth_session_validatetoken`) will create orphan ghost-duplicate nodes. If you are re-extracting a project that had ghost duplicates under the old format, the user should run `graphify extract --force` to rebuild cleanly. CRITICAL: never append chunk numbers, sequence numbers, or any suffix to an ID (no `_c1`, `_c2`, `_chunk2`, etc.). IDs must be deterministic from the label alone — the same entity must always produce the same ID regardless of which chunk processes it.
Generate the extraction JSON matching this schema exactly:
{"nodes":[{"id":"auth_session_validatetoken","label":"Human Readable Name","file_type":"code|document|paper|image|rationale|concept","source_file":"<FILE_LIST path verbatim>","source_location":null,"source_url":null,"captured_at":null,"author":null,"contributor":null}],"edges":[{"source":"node_id","target":"node_id","relation":"calls|implements|references|cites|conceptually_related_to|shares_data_with|semantically_similar_to|rationale_for","confidence":"EXTRACTED|INFERRED|AMBIGUOUS","confidence_score":1.0,"source_file":"<FILE_LIST path verbatim>","source_location":null,"weight":1.0}],"hyperedges":[{"id":"snake_case_id","label":"Human Readable Label","nodes":["node_id1","node_id2","node_id3"],"relation":"participate_in|implement|form","confidence":"EXTRACTED|INFERRED","confidence_score":0.75,"source_file":"<FILE_LIST path verbatim>"}],"input_tokens":0,"output_tokens":0}
source_file RULE (every node, edge, and hyperedge): set source_file to the path of the originating file EXACTLY as it appears in FILE_LIST — verbatim and absolute. Do NOT shorten to a basename, do NOT re-relativize, do NOT strip any directory prefix, and do NOT change separators (the engine canonicalizes separators and relativizes against the build root downstream). Copy the FILE_LIST entry character-for-character. This keeps the full build and incremental --update on the same base, so build_merge's replace-on-re-extract matches the existing node instead of accumulating a duplicate.
Then write the JSON to disk using the Write tool at this exact absolute path (no relative paths — Write resolves relative paths against an undefined cwd and the file will be silently lost):
CHUNK_PATH
```
tools/skillgen/expected/graphify__skills__agents__references__github-and-merge.md
+46
View File
@@ -0,0 +1,46 @@
# graphify reference: GitHub clone and cross-repo merge
Load this when the user passed one or more `https://github.com/...` URLs, or named several local subfolders to merge into one graph.
### Step 0 - Clone GitHub repo(s) (only if a GitHub URL was given)
**Single repo:**
```bash
LOCAL_PATH=$(graphify clone <github-url> [--branch <branch>])
# Use LOCAL_PATH as the target for all subsequent steps
```
**Multiple repos (cross-repo graph):**
```bash
# Clone each repo, run the full pipeline on each, then merge
graphify clone <url1> # → ~/.graphify/repos/<owner1>/<repo1>
graphify clone <url2> # → ~/.graphify/repos/<owner2>/<repo2>
# Run /graphify on each local path to produce their graph.json files
# Then merge:
graphify merge-graphs \
~/.graphify/repos/<owner1>/<repo1>/graphify-out/graph.json \
~/.graphify/repos/<owner2>/<repo2>/graphify-out/graph.json \
--out graphify-out/cross-repo-graph.json
```
Graphify clones into `~/.graphify/repos/<owner>/<repo>` and reuses existing clones on repeat runs. Each node in the merged graph carries a `repo` attribute so you can filter by origin.
**Multiple local subfolders (monorepo or multi-service layout):**
The skill pipeline writes all intermediate and final outputs to `graphify-out/` in the current working directory. Running the skill on each subfolder separately will clobber the same output dir. Instead, use the CLI directly for each subfolder — it places `graphify-out/` *inside* the scanned path:
```bash
graphify extract ./core/ # → ./core/graphify-out/graph.json
graphify extract ./service/ # → ./service/graphify-out/graph.json
graphify extract ./platform/ # → ./platform/graphify-out/graph.json
# Add --backend gemini|kimi|openai|deepseek|claude-cli depending on which API key you have set
# Then merge at the project root:
graphify merge-graphs \
./core/graphify-out/graph.json \
./service/graphify-out/graph.json \
./platform/graphify-out/graph.json \
--out graphify-out/graph.json
```
Once `graphify-out/graph.json` exists, the fast path above takes over: any codebase question runs `graphify query` directly on the merged graph — no re-extraction, no size gate.
tools/skillgen/expected/graphify__skills__agents__references__hooks.md
+33
View File
@@ -0,0 +1,33 @@
# graphify reference: commit hook and native AGENTS.md integration
Load this when the user asked to install the post-commit hook or wire graphify into a project's AGENTS.md.
## For git commit hook
Install a post-commit hook that auto-rebuilds the graph after every commit. No background process needed - triggers once per commit, works with any editor.
```bash
graphify hook install # install
graphify hook uninstall # remove
graphify hook status # check
```
After every `git commit`, the hook detects which code files changed (via `git diff HEAD~1`), re-runs AST extraction on those files, and rebuilds `graph.json` and `GRAPH_REPORT.md`. Doc/image changes are ignored by the hook - run `/graphify --update` manually for those.
If a post-commit hook already exists, graphify appends to it rather than replacing it.
---
## For native AGENTS.md integration
Run once per project to make graphify always-on in your agent sessions:
```bash
graphify agents install
```
This writes a `## graphify` section to the local `AGENTS.md` that instructs your agent to check the graph before answering codebase questions and rebuild it after code changes. No manual `/graphify` needed in future sessions.
```bash
graphify agents uninstall # remove the section
```
tools/skillgen/expected/graphify__skills__agents__references__query.md
+303
View File
@@ -0,0 +1,303 @@
# graphify reference: query, path, explain
Load this when the user asks a question against an existing graph, or runs `/graphify path` or `/graphify explain`. The core's query stub points here for the full traversal flow. These flows use the `graphify query` CLI when it is available and fall back to an inline NetworkX traversal otherwise.
Two traversal modes - choose based on the question:
| Mode | Flag | Best for |
|------|------|----------|
| BFS (default) | _(none)_ | "What is X connected to?" - broad context, nearest neighbors first |
| DFS | `--dfs` | "How does X reach Y?" - trace a specific chain or dependency path |
First check the graph exists:
```bash
$(cat graphify-out/.graphify_python) -c "
from pathlib import Path
if not Path('graphify-out/graph.json').exists():
print('ERROR: No graph found. Run /graphify <path> first to build the graph.')
raise SystemExit(1)
"
```
If it fails, stop and tell the user to run `/graphify <path>` first.
### Step 0 — Constrained query expansion (REQUIRED before traversal)
graphify's `query` CLI matches nodes via case-folded substring + IDF — there is **no stemming, no synonyms, no cross-language match** inside the binary, and the inline fallback below matches the same way. If the user's question uses different language or different domain vocabulary than the graph's labels (user says "обработчик" / graph says "handler"; user says "authentication" / graph says "Guardian"), the literal matcher returns 0 hits and the answer collapses to noise.
Fix this **without inventing tokens** by expanding the query against the actual graph vocabulary first:
1. Extract the token vocabulary from node labels:
```bash
$(cat graphify-out/.graphify_python) -c "
import json, re
from pathlib import Path
data = json.loads(Path('graphify-out/graph.json').read_text())
vocab = set()
for n in data['nodes']:
for c in re.findall(r'[^\W\d_]+', n.get('label','') or '', re.UNICODE):
parts = re.findall(r'[A-Z]+(?=[A-Z][a-z])|[A-Z]?[a-z]+|[A-Z]+', c) or [c]
for p in parts:
t = p.lower()
if 3 <= len(t) <= 30:
vocab.add(t)
Path('graphify-out/.vocab.txt').write_text('\n'.join(sorted(vocab)))
print(f'vocab: {len(vocab)} tokens')
"
```
2. Read `graphify-out/.vocab.txt`. Then for the user's question, select **up to 12 tokens from this exact list** that semantically match the query intent. Hard constraints:
- You MUST pick only tokens present in the vocabulary file. Do NOT invent tokens.
- If a query concept has no plausible token in the vocab, skip it — do not substitute a near-synonym from training memory.
- If **no** vocab tokens match the query at all, output an empty list and tell the user the corpus has no relevant vocabulary for this question. Do not fabricate a search.
- Translate cross-language: Russian "аутентификация" → look for `auth`, `credential`, `token`, `security` IFF present in vocab.
- Morphology: "handlers" maps to `handler` IFF present; "todos" maps to `todo` IFF present.
3. Print the selection explicitly to the user before running the query, so the expansion is auditable:
```
Query expanded to (from graph vocab, N tokens): [token1, token2, ...]
```
If the list is empty, say so plainly and stop — do not proceed to traversal.
### Step 1 — Traversal
Build the **expanded query string** by joining the selected tokens with spaces. Use this string as `QUESTION` below — NOT the original user question. (The original question is preserved only for `save-result` at the end.)
Prefer the CLI when it is installed:
```bash
graphify query "QUESTION"
# or: graphify query "QUESTION" --dfs --budget 3000
```
If the CLI is unavailable, load `graphify-out/graph.json` and run the traversal inline:
1. Find the 1-3 nodes whose label best matches the expanded tokens.
2. Run the appropriate traversal from each starting node.
3. Read the subgraph - node labels, edge relations, confidence tags, source locations.
4. Answer using **only** what the graph contains. Quote `source_location` when citing a specific fact.
5. If the graph lacks enough information, say so - do not hallucinate edges.
```bash
$(cat graphify-out/.graphify_python) -c "
import sys, json
from networkx.readwrite import json_graph
import networkx as nx
from pathlib import Path
data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')
question = 'QUESTION'
mode = 'MODE' # 'bfs' or 'dfs'
terms = [t.lower() for t in question.split() if len(t) >= 3] # match the vocab threshold; keeps api/jwt/ios (#1392)
# Find best-matching start nodes
scored = []
for nid, ndata in G.nodes(data=True):
label = ndata.get('label', '').lower()
score = sum(1 for t in terms if t in label)
if score > 0:
scored.append((score, nid))
scored.sort(reverse=True)
start_nodes = [nid for _, nid in scored[:3]]
if not start_nodes:
print('No matching nodes found for query terms:', terms)
sys.exit(0)
subgraph_nodes = set()
subgraph_edges = []
if mode == 'dfs':
# DFS: follow one path as deep as possible before backtracking.
# Depth-limited to 6 to avoid traversing the whole graph.
visited = set()
stack = [(n, 0) for n in reversed(start_nodes)]
while stack:
node, depth = stack.pop()
if node in visited or depth > 6:
continue
visited.add(node)
subgraph_nodes.add(node)
for neighbor in G.neighbors(node):
if neighbor not in visited:
stack.append((neighbor, depth + 1))
subgraph_edges.append((node, neighbor))
else:
# BFS: explore all neighbors layer by layer up to depth 3.
frontier = set(start_nodes)
subgraph_nodes = set(start_nodes)
for _ in range(3):
next_frontier = set()
for n in frontier:
for neighbor in G.neighbors(n):
if neighbor not in subgraph_nodes:
next_frontier.add(neighbor)
subgraph_edges.append((n, neighbor))
subgraph_nodes.update(next_frontier)
frontier = next_frontier
# Token-budget aware output: rank by relevance, cut at budget (~4 chars/token)
token_budget = BUDGET # default 2000
char_budget = token_budget * 4
# Score each node by term overlap for ranked output
def relevance(nid):
label = G.nodes[nid].get('label', '').lower()
return sum(1 for t in terms if t in label)
ranked_nodes = sorted(subgraph_nodes, key=relevance, reverse=True)
lines = [f'Traversal: {mode.upper()} | Start: {[G.nodes[n].get(\"label\",n) for n in start_nodes]} | {len(subgraph_nodes)} nodes']
for nid in ranked_nodes:
d = G.nodes[nid]
lines.append(f' NODE {d.get(\"label\", nid)} [src={d.get(\"source_file\",\"\")} loc={d.get(\"source_location\",\"\")}]')
for u, v in subgraph_edges:
if u in subgraph_nodes and v in subgraph_nodes:
_raw = G[u][v]; d = next(iter(_raw.values()), {}) if isinstance(G, nx.MultiGraph) else _raw
lines.append(f' EDGE {G.nodes[u].get(\"label\",u)} --{d.get(\"relation\",\"\")} [{d.get(\"confidence\",\"\")}]--> {G.nodes[v].get(\"label\",v)}')
output = '\n'.join(lines)
if len(output) > char_budget:
output = output[:char_budget] + f'\n... (truncated at ~{token_budget} token budget - use --budget N for more)'
print(output)
"
```
Replace `QUESTION` with the **expanded** query string, `MODE` with `bfs` or `dfs`, and `BUDGET` with the token budget (default `2000`, or whatever `--budget N` specifies). Then answer based on the subgraph output above, using only what the graph contains.
After writing the answer, save it back into the graph so it improves future queries. Include the expanded tokens inside the `--answer` text (e.g. `"Expanded from original query via vocab: [tokens]. Then traversed..."`) so the next `--update` extracts the expansion history as a graph node:
```bash
$(cat graphify-out/.graphify_python) -m graphify save-result --question "ORIGINAL_QUESTION" --answer "ANSWER" --type query --nodes NODE1 NODE2
```
Replace `ORIGINAL_QUESTION` with the user's verbatim question, `ANSWER` with your full answer text (containing the expanded-token trace), `NODE1 NODE2` with the list of node labels you cited. This closes the feedback loop: the next `--update` will extract this Q&A as a node in the graph.
---
## For /graphify path
Find the shortest path between two named concepts in the graph. Prefer the CLI when installed:
```bash
graphify path "NODE_A" "NODE_B"
```
If the CLI is unavailable, run it inline:
```bash
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
from pathlib import Path
data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')
a_term = 'NODE_A'
b_term = 'NODE_B'
def find_node(term):
term = term.lower()
scored = sorted(
[(sum(1 for w in term.split() if w in G.nodes[n].get('label','').lower()), n)
for n in G.nodes()],
reverse=True
)
return scored[0][1] if scored and scored[0][0] > 0 else None
src = find_node(a_term)
tgt = find_node(b_term)
if not src or not tgt:
print(f'Could not find nodes matching: {a_term!r} or {b_term!r}')
sys.exit(0)
try:
path = nx.shortest_path(G, src, tgt)
print(f'Shortest path ({len(path)-1} hops):')
for i, nid in enumerate(path):
label = G.nodes[nid].get('label', nid)
if i < len(path) - 1:
_raw = G[nid][path[i+1]]; edge = next(iter(_raw.values()), {}) if isinstance(G, nx.MultiGraph) else _raw
rel = edge.get('relation', '')
conf = edge.get('confidence', '')
print(f' {label} --{rel}--> [{conf}]')
else:
print(f' {label}')
except nx.NetworkXNoPath:
print(f'No path found between {a_term!r} and {b_term!r}')
except nx.NodeNotFound as e:
print(f'Node not found: {e}')
"
```
Replace `NODE_A` and `NODE_B` with the actual concept names from the user. Then explain the path in plain language - what each hop means, why it's significant.
After writing the explanation, save it back:
```bash
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Path from NODE_A to NODE_B" --answer "ANSWER" --type path_query --nodes NODE_A NODE_B
```
---
## For /graphify explain
Give a plain-language explanation of a single node - everything connected to it. Prefer the CLI when installed:
```bash
graphify explain "NODE_NAME"
```
If the CLI is unavailable, run it inline:
```bash
$(cat graphify-out/.graphify_python) -c "
import json, sys
import networkx as nx
from networkx.readwrite import json_graph
from pathlib import Path
data = json.loads(Path('graphify-out/graph.json').read_text())
G = json_graph.node_link_graph(data, edges='links')
term = 'NODE_NAME'
term_lower = term.lower()
# Find best matching node
scored = sorted(
[(sum(1 for w in term_lower.split() if w in G.nodes[n].get('label','').lower()), n)
for n in G.nodes()],
reverse=True
)
if not scored or scored[0][0] == 0:
print(f'No node matching {term!r}')
sys.exit(0)
nid = scored[0][1]
data_n = G.nodes[nid]
print(f'NODE: {data_n.get(\"label\", nid)}')
print(f' source: {data_n.get(\"source_file\",\"unknown\")}')
print(f' type: {data_n.get(\"file_type\",\"unknown\")}')
print(f' degree: {G.degree(nid)}')
print()
print('CONNECTIONS:')
for neighbor in G.neighbors(nid):
_raw = G[nid][neighbor]; edge = next(iter(_raw.values()), {}) if isinstance(G, nx.MultiGraph) else _raw
nlabel = G.nodes[neighbor].get('label', neighbor)
rel = edge.get('relation', '')
conf = edge.get('confidence', '')
src_file = G.nodes[neighbor].get('source_file', '')
print(f' --{rel}--> {nlabel} [{conf}] ({src_file})')
"
```
Replace `NODE_NAME` with the concept the user asked about. Then write a 3-5 sentence explanation of what this node is, what it connects to, and why those connections are significant. Use the source locations as citations.
After writing the explanation, save it back:
```bash
$(cat graphify-out/.graphify_python) -m graphify save-result --question "Explain NODE_NAME" --answer "ANSWER" --type explain --nodes NODE_NAME
```
tools/skillgen/expected/graphify__skills__agents__references__transcribe.md
+52
View File
@@ -0,0 +1,52 @@
# graphify reference: transcribe video and audio
Load this only when `detect` reported one or more `video` files. A corpus with no video never reads this.
### Step 2.5 - Transcribe video / audio files (only if video files detected)
Skip this step entirely if `detect` returned zero `video` files.
Video and audio files cannot be read directly. Transcribe them to text first, then treat the transcripts as doc files in Step 3.
**Strategy:** Read the god nodes from `graphify-out/.graphify_detect.json` (or the analysis file if it exists from a previous run). You are already a language model — write a one-sentence domain hint yourself from those labels. Then pass it to Whisper as the initial prompt. No separate API call needed.
**However**, if the corpus has *only* video files and no other docs/code, use the generic fallback prompt: `"Use proper punctuation and paragraph breaks."`
**Step 1 - Write the Whisper prompt yourself.**
Read the top god node labels from detect output or analysis, then compose a short domain hint sentence, for example:
- Labels: `transformer, attention, encoder, decoder` → `"Machine learning research on transformer architectures and attention mechanisms. Use proper punctuation and paragraph breaks."`
- Labels: `kubernetes, deployment, pod, helm` → `"DevOps discussion about Kubernetes deployments and Helm charts. Use proper punctuation and paragraph breaks."`
**Export** it as `GRAPHIFY_WHISPER_PROMPT` (the exact name the transcriber reads — and it must be `export`ed so the child Python process sees it) for the next command.
**Step 2 - Transcribe:**
```bash
export GRAPHIFY_WHISPER_MODEL=base # or whatever --whisper-model the user passed (must be exported)
export GRAPHIFY_WHISPER_PROMPT="<the one-sentence domain hint you composed in Step 1>"
$(cat graphify-out/.graphify_python) -c "
import json, os, sys
from pathlib import Path
from graphify.transcribe import transcribe_all
detect = json.loads(Path('graphify-out/.graphify_detect.json').read_text(encoding=\"utf-8\"))
video_files = detect.get('files', {}).get('video', [])
prompt = os.environ.get('GRAPHIFY_WHISPER_PROMPT', 'Use proper punctuation and paragraph breaks.')
transcript_paths = transcribe_all(video_files, initial_prompt=prompt)
# Write the JSON from Python (NOT a shell '>' redirect): transcribe_all/Whisper
# print progress to stdout, which would otherwise corrupt the JSON file (#1392).
Path('graphify-out/.graphify_transcripts.json').write_text(json.dumps(transcript_paths, ensure_ascii=False), encoding=\"utf-8\")
print(f'Transcribed {len(transcript_paths)} file(s)', file=sys.stderr)
"
```
After transcription:
- Read the transcript paths from `graphify-out/.graphify_transcripts.json`
- Add them to the docs list before dispatching semantic subagents in Step 3B
- Print how many transcripts were created: `Transcribed N video file(s) -> treating as docs`
- If transcription fails for a file, print a warning and continue with the rest
**Whisper model:** Default is `base`. If the user passed `--whisper-model <name>`, `export GRAPHIFY_WHISPER_MODEL=<name>` (it must be exported, not just assigned) before running the command above.
tools/skillgen/expected/graphify__skills__agents__references__update.md
+192
View File
@@ -0,0 +1,192 @@
# graphify reference: incremental update and cluster-only
Load this only when the user passed `--update` or `--cluster-only`. A first-time full build never reads this file.
## For --update (incremental re-extraction)
Use when you've added or modified files since the last run. Only re-extracts changed files - saves tokens and time.
```bash
$(cat graphify-out/.graphify_python) -c "
import sys, json
from graphify.detect import detect_incremental, save_manifest
from pathlib import Path
result = detect_incremental(Path('INPUT_PATH'))
new_total = result.get('new_total', 0)
print(json.dumps(result, indent=2, ensure_ascii=False))
Path('graphify-out/.graphify_incremental.json').write_text(json.dumps(result, ensure_ascii=False), encoding=\"utf-8\")
deleted = list(result.get('deleted_files', []))
if new_total == 0 and not deleted:
print('No files changed since last run. Nothing to update.')
raise SystemExit(0)
if deleted:
print(f'{len(deleted)} deleted file(s) to prune.')
if new_total > 0:
print(f'{new_total} new/changed file(s) to re-extract.')
"
```
Then populate `.graphify_detect.json` so Steps 3A–6 (which read it unconditionally) see the right state for an incremental run. `files` carries the changed subset (drives Step 3A AST + Step 3B0 cache check on only what changed); `all_files` carries the full corpus for any step that needs corpus-wide context:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
r = json.loads(Path('graphify-out/.graphify_incremental.json').read_text(encoding=\"utf-8\"))
Path('graphify-out/.graphify_detect.json').write_text(json.dumps({
'files': r.get('new_files', {}),
'all_files': r.get('files', {}),
'total_files': r.get('new_total', 0),
'total_words': r.get('total_words', 0),
'skipped_sensitive': r.get('skipped_sensitive', []),
'needs_graph': True,
}, ensure_ascii=False), encoding=\"utf-8\")
"
```
If new files exist, first check whether all changed files are code files:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
result = json.loads(open('graphify-out/.graphify_incremental.json', encoding='utf-8').read()) if Path('graphify-out/.graphify_incremental.json').exists() else {}
code_exts = {'.py','.ts','.js','.go','.rs','.java','.cpp','.c','.rb','.swift','.kt','.cs','.scala','.php','.cc','.cxx','.hpp','.h','.kts','.lua','.toc','.f','.F','.f90','.F90','.f95','.F95','.f03','.F03','.f08','.F08'}
new_files = result.get('new_files', {})
all_changed = [f for files in new_files.values() for f in files]
code_only = all(Path(f).suffix.lower() in code_exts for f in all_changed)
print('code_only:', code_only)
"
```
If `code_only` is True: print `[graphify update] Code-only changes detected - skipping semantic extraction (no LLM needed)`, run only Step 3A (AST) on the changed files, skip Step 3B entirely (no subagents), then go straight to merge and Steps 4–8.
If `code_only` is False (any changed file is a doc/paper/image/video): **first, if any changed file is in `new_files['video']`, run `references/transcribe.md` (Step 2.5) on those files, then rewrite `.graphify_detect.json` to move the resulting transcript paths into `files['document']` and drop `files['video']`** — otherwise raw `.mp4/.mp3` paths are fed to semantic subagents as unreadable media (#1392). Then run the full Steps 3A–3C pipeline as normal.
If no new files exist (only deletions), create an empty extraction so the merge step can prune:
```bash
if [ ! -f graphify-out/.graphify_extract.json ]; then
echo '[graphify update] Only deletions -- creating empty extraction for merge.'
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
Path('graphify-out/.graphify_extract.json').write_text(json.dumps({'nodes':[],'edges':[],'hyperedges':[],'input_tokens':0,'output_tokens':0}), encoding='utf-8')
"
fi
```
Then:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from pathlib import Path
from graphify.build import build_merge
from graphify.detect import save_manifest
# Load new extraction and incremental state
new_extraction = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
incremental = json.loads(Path('graphify-out/.graphify_incremental.json').read_text(encoding=\"utf-8\"))
deleted = list(incremental.get('deleted_files', []))
# prune_sources is ONLY for genuinely DELETED files. Changed/re-extracted files are
# handled by build_merge's replace-on-re-extract (#1344): every source_file in
# new_chunks is dropped from the base before merge, so old/stale nodes don't survive.
# Do NOT add `changed` here: with root= passed, prune_set relativizes to the same base
# as the freshly merged nodes and would DELETE the re-extracted content (#1178 is moot
# now that replace — not the dedup pass — reconciles changed files).
prune = list(deleted) or None
# Use build_merge() — reads graph.json directly without NetworkX round-trip
# so edge direction (calls, implements, imports) is always preserved (#801).
# Pass root= so prune_sources (absolute paths from detect_incremental) are
# relativized to match the graph's relative source_file values; without it
# nothing is pruned and stale nodes accumulate on every update (#1361).
# directed=IS_DIRECTED: replace IS_DIRECTED with True if --directed was given, else
# False. Without it a --directed --update silently rebuilds undirected and collapses
# reciprocal A<->B edges (#1392).
G = build_merge(
[new_extraction],
graph_path='graphify-out/graph.json',
prune_sources=prune,
root='INPUT_PATH',
directed=IS_DIRECTED,
)
print(f'[graphify update] Merged: {G.number_of_nodes()} nodes, {G.number_of_edges()} edges')
# Write merged result back to .graphify_extract.json so Step 4 sees the full graph
merged_out = {
'nodes': [{'id': n, **d} for n, d in G.nodes(data=True)],
'edges': [
# Explicit source/target last so they win over any stale attrs in d.
{**{k: val for k, val in d.items() if k not in ('_src', '_tgt', 'source', 'target')},
'source': d.get('_src', u), 'target': d.get('_tgt', v)}
for u, v, d in G.edges(data=True)
],
# G.graph["hyperedges"] holds hyperedges from both existing graph.json
# and new_extraction (build_merge combines them). Falling back to
# new_extraction only would silently drop prior-run hyperedges (#801).
'hyperedges': list(G.graph.get('hyperedges', [])),
'input_tokens': new_extraction.get('input_tokens', 0),
'output_tokens': new_extraction.get('output_tokens', 0),
}
Path('graphify-out/.graphify_extract.json').write_text(json.dumps(merged_out, ensure_ascii=False), encoding=\"utf-8\")
print(f'[graphify update] Merged extraction written ({len(merged_out[\"nodes\"])} nodes, {len(merged_out[\"edges\"])} edges)')
# Save manifest so next --update diffs against today's state, not the
# prior run's baseline (prevents ghost-node reports on subsequent updates).
# root= matches the build_merge call above so the manifest keys stay relative to
# the scan root — portable across clones/machines, so --update keeps matching
# cached files instead of missing every one after a move (#1417).
save_manifest(incremental['files'], root='INPUT_PATH')
print('[graphify update] Manifest saved.')
"
```
Then run Steps 4–8 on the merged graph as normal.
After Step 4, show the graph diff:
```bash
$(cat graphify-out/.graphify_python) -c "
import json
from graphify.analyze import graph_diff
from graphify.build import build_from_json
from networkx.readwrite import json_graph
import networkx as nx
from pathlib import Path
# Load old graph (before update) from backup written before merge
old_data = json.loads(Path('graphify-out/.graphify_old.json').read_text(encoding=\"utf-8\")) if Path('graphify-out/.graphify_old.json').exists() else None
new_extract = json.loads(Path('graphify-out/.graphify_extract.json').read_text(encoding=\"utf-8\"))
G_new = build_from_json(new_extract, directed=IS_DIRECTED)
if old_data:
G_old = json_graph.node_link_graph(old_data, edges='links')
diff = graph_diff(G_old, G_new)
print(diff['summary'])
if diff['new_nodes']:
print('New nodes:', ', '.join(n['label'] for n in diff['new_nodes'][:5]))
if diff['new_edges']:
print('New edges:', len(diff['new_edges']))
"
```
Before the merge step, save the old graph: `cp graphify-out/graph.json graphify-out/.graphify_old.json`
Clean up after: `rm -f graphify-out/.graphify_old.json`
---
## For --cluster-only
Skip Steps 1–3. Re-run clustering on the existing graph:
```bash
graphify cluster-only .
```
`graphify cluster-only .` is **self-contained**: it re-clusters, names communities, and regenerates `GRAPH_REPORT.md`, `graph.json`, and `graph.html` from the existing graph. **Do not re-run Steps 5–9** — they read intermediate files (`.graphify_extract.json`, `.graphify_detect.json`, `.graphify_analysis.json`) that a prior build's cleanup (Step 9) already deleted, so they raise `FileNotFoundError` (#1392). When it finishes, present the refreshed `GRAPH_REPORT.md` summary as usual.
tools/skillgen/gen.py
+16
View File
@@ -61,6 +61,12 @@ def _v8_baseline_ref(platform_key: str) -> str:
"""The git ref for a split host's own pre-split skill body."""
if platform_key == "claude":
return f"{_V8_BASELINE_SHA}:graphify/skill.md"
if platform_key == "agents":
# `agents` is a post-v8 platform with no own v8 body — it re-homes amp's
# agents-md body at the generic ~/.agents/skills location. Its render is
# amp's modulo the install/uninstall command wording (prose, not headings),
# so amp's v8 body is the correct per-host coverage baseline.
return f"{_V8_BASELINE_SHA}:graphify/skill-amp.md"
return f"{_V8_BASELINE_SHA}:graphify/skill-{platform_key}.md"
# Immutable baseline for --always-on-roundtrip. The six always-on instruction
@@ -153,6 +159,16 @@ _AGENTS_MD_HOOKS: dict[str, dict[str, str]] = {
"uninstall_block": "graphify amp uninstall # remove the section",
"pretooluse_note": "",
},
"agents": {
# The generic cross-framework Agent-Skills target. Mirrors amp's bare,
# caveat-free agents-md section, worded for an unspecified host and
# pointing at `graphify agents install` (which wires AGENTS.md, like amp).
"heading_suffix": "",
"host_display": "your agent",
"install_block": "graphify agents install",
"uninstall_block": "graphify agents uninstall # remove the section",
"pretooluse_note": "",
},
}
# The prose file name the lean-core hooks pointer names, per hooks variant.
_HOOKS_TARGET = {
tools/skillgen/platforms.toml
+17
View File
@@ -126,6 +126,23 @@ dispatch = "task-tool-disk"
extraction = "verbose"
hooks_variant = "agents-md"
[platform.agents]
bucket = "split"
core = "core"
skill_dst = "graphify/skill-agents.md"
refs_dst = "graphify/skills/agents/references"
description = "Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools."
# The generic cross-framework Agent-Skills target (~/.agents/skills and
# ./.agents/skills). Like amp, it reads AGENTS.md and wires always-on via
# `graphify agents install`, so it uses the plain task-tool-disk dispatch and the
# agents-md hooks variant. The rendered skill body is identical to amp's; only the
# hooks reference differs (its own caveat-free `graphify agents install` wording).
# It is a brand-new post-v8 platform, so its --audit-coverage baseline is amp's v8
# body (the body it re-homes); see _v8_baseline_ref in gen.py.
dispatch = "task-tool-disk"
extraction = "verbose"
hooks_variant = "agents-md"
[platform.trae]
bucket = "split"
core = "core"