map-first
Skill18 starsChanged 2 days agoMITView on GitHub
Map the whole project with graphify before reading files or changing anything. Use at the start of work on an unfamiliar or large codebase, or when you need to know how two parts connect.
In this repository6 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- dep-auditSkill
- rea-triageSkill
- release-hardenSkill
- reverse-and-hardenSkill
- ship-checkSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 40
Every edge is tagged EXTRACTED (read from the source) or INFERRED (resolved by graphify).
- Very specific: line 44
After edits run /graphify .
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Map first (graphify)
Graphify-Labs/graphify, Apache-2.0. One knowledge graph of the project, so you walk the map instead of grepping raw files.
1. Build the map
Install once per machine (install.sh does this):
uv tool install graphifyy # or: pipx install graphifyy
graphify install # registers the /graphify skill for Claude CodeThen, from the project root:
/graphify .It writes graphify-out/:
graph.html- the architecture as one clickable map.GRAPH_REPORT.md- key concepts, surprising connections, suggested questions. Read this first.
Code is parsed locally with tree-sitter: no LLM, nothing leaves the machine. Docs, PDFs and images use the model for a semantic pass.
2. Ask the map, not the files
graphify query "what connects auth to the database?" # scoped subgraph for a question
graphify path "A" "B" # how two things connect
graphify explain "A" # everything one thing touchesEvery edge is tagged EXTRACTED (read from the source) or INFERRED (resolved by graphify). Treat INFERRED as a lead to check in the code, not a fact.
3. Keep it fresh
After edits run /graphify . --update (re-extracts only changed files). After git pull run graphify update ..
Then
Built output goes to REA (rea-triage) to see what the release exposes, and to BLA (release-harden) before shipping. Map, then reverse, then harden.
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
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.

