agentleFS
Sign inStart free
ritamghritamgh/claude-skills/skills/graphify/SKILL.md

graphify

Skill0 starsChanged 26 days agoMITView on GitHub

Build and query a local code map (graph of files, functions, calls) with the graphify CLI. Use for "how is this code connected", "what calls X", "what depends on X", "map this repo", "path between A and B", or before reading many files to orient in an unfamiliar codebase.

115 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use remotion-maps, remotion-saas and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • OpenAISkill

    remotion-maps

    Remotion Map animation knowledge

    Also in 4 projects that use this

  • OpenAISkill

    remotion-saas

    Build an app with Remotion

    Also in 4 projects that use this

  • royaluniondesign-sysSkill

    deployment-patterns

    Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.

    Also in 4 projects that use this

  • mstuder-slalomSkill

    django-verification

    Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

    Also in 3 projects that use this

  • ttmouseSkill

    prompt-master

    提示词主控 - 智能选择合适的领域skill并生成提示词，支持自动领域分类和调度

    Also in 4 projects that use this

  • seikaikyoSkill

    doubt-driven-development

    對非平凡決策啟動新鮮 context 對抗審查（找碴不背書），在修正還便宜的時候抓出錯誤方向。適用：高風險改動（production、資安敏感邏輯、不可逆操作）、不熟的程式碼、要宣稱「這樣是安全的 / 可行的」之前。機械性操作與一行修改不適用。

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 113 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Never drop it, and never run graphify label, --backend, or semantic/doc extraction, unless the user asks.

    line 20
  2. Very specific:

    Do not run graphify install, graphify claude install or graphify hook install: they edit CLAUDE.md, settings.json or git hooks.

    line 24
  3. Very specific:

    Read graphify-out/GRAPH_REPORT.md first (god nodes, communities, surprising links).

    line 29

“Common” is measured: kept by at least 6 in 10 of the 113 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

graphify: local code map, no LLM spend

CLI graphify (PyPI graphifyy, pinned 0.9.91, installed with uv tool). Output goes to graphify-out/ in the repo root. It is git-ignored globally (~/.config/git/ignore); never commit it.

Build (code only, offline)

graphify extract . --code-only
graphify cluster-only . --no-label
  • --code-only is pure tree-sitter, free. --no-label is mandatory: without it cluster-only finds the claude CLI on PATH and silently spends subscription tokens naming communities. Never drop it, and never run graphify label, --backend, or semantic/doc extraction, unless the user asks. No env var or config disables the LLM backend, so the flag is the only guard.
  • Refresh after code changes: graphify update . (local, no LLM). Use --force only after refactors that delete code.
  • Do not run graphify install, graphify claude install or graphify hook install: they edit CLAUDE.md, settings.json or git hooks. Not needed.

Query

  1. Read graphify-out/GRAPH_REPORT.md first (god nodes, communities, surprising links).
  2. graphify explain "Name" for one node and its neighbours (--all for every edge).
  3. graphify path "A" "B" --undirected for how two things connect. Without --undirected it reports a false "no path".
  4. graphify query "question" --budget 2000 for a BFS slice (always pass --budget). Exit code 3 means an ambiguous name; retry with a more specific one.

Labels read Community N by design. Trust the graph for structure, then read the real files before acting on it.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free