Install
$ agentstack add skill-danielc000-loom-graphify ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
graphify
graphify builds a local, code-only call graph with tree-sitter — no API key, no LLM backend, no token cost. Use it as a forward-orientation aid: given a symbol, see what it calls and how two symbols connect. It is fast and accurate for that.
The one thing to internalize: graphify is strong going forward (explain / path) and unreliable going backward (affected — "what breaks if I change X"). Treat forward queries as trustworthy orientation and reverse queries as a lead to confirm with grep — never as ground truth.
Setup (opt-in — assume it's present)
One-time, human-installed like any host tool: uv tool install graphifyy (or pipx install graphifyy, or pip install graphifyy). This skill assumes it's already there. If graphify isn't on PATH, say so and fall back to grep/Read — don't try to install it yourself.
Build the graph (code-only)
graphify update
Point ` at your source root (e.g. src). This writes /graphify-out/graph.json. **Only ever use update.** Never run extract` or point it at a semantic/LLM backend, and never pass an API key — code-only keeps it free and local. Rebuild after substantial code changes; the graph is a snapshot.
Use it — forward orientation (the strength)
Pass --graph /graphify-out/graph.json to each query.
graphify explain ""— what this symbol touches: its outgoing calls and immediate
neighbors. The go-to "what does this do / what does it reach" query.
graphify path "" ""— how two symbols connect, if they do. Good for "does this handler
actually reach that writer".
The affected warning (load-bearing)
graphify affected "" claims to list callers ("what depends on this"). It under-reports, and silently — a confident-looking short answer that misses real callers. It does not build caller edges for method calls on a locally-constructed instance (const x = new Foo(); x.method()) or on a closure/parameter receiver (a callback closing over an injected service). So a method that is called can come back "No affected nodes found".
Therefore: never trust affected for "what breaks if I change X" — grep for the symbol to confirm reverse-dependency completeness. (Verified on graphify 0.9.5; tracked upstream as safishamsi/graphify#1630.)
Other caveats
- Skip the natural-language
querycommand — it's a noisy keyword search, not useful for orientation. [INFERRED]edges are verify-before-trust — confirm them against the code;[EXTRACTED]edges are
the reliable ones.
- Not everything is a node — config-object fields and bare module-level
consts don't appear in the
graph. Grep for those instead of expecting explain/affected to find them.
Keep it reversible and trust-safe
- Never commit the graph. Add
graphify-out/to.git/info/excludeso the artifacts stay untracked
and local.
- Never run
graphify hook installor any export/integration subcommand — they edit files like
CLAUDE.md or add git hooks. Build the graph on demand, query it, and leave the repo otherwise untouched.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: DanielC000
- Source: DanielC000/loom
- License: MIT
- Homepage: https://danielc000.github.io/loom/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.