agentleFS
Sign inStart free
whoaskedssselerywhoaskedssselery/claude-workspace/skills/core/codegraph/SKILL.md

codegraph

Skill0 starsChanged 3 months agoMITView on GitHub

Use the CodeGraph MCP tools as the primary way to navigate and understand this codebase before writing or editing code.

  • Pipes a download into a shell

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use codebase-design and grill-me.

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.
  • GoogleSkill

    codebase-design

    Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 1

    Distinctive

    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
  1. Very specific:

    If the codegraph_* tools below are not available, the server isn't connected yet — install it first, then reload.

    line 20
  2. Distinctive:

    Before touching a function, check what depends on it so a change doesn't silently break a caller.

    line 29
  3. Very specific:

    Read a symbol's source/signature → codegraph_node.

    line 38

“Common” is measured: kept by at least 6 in 10 of the 13 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

CodeGraph

Requires the CodeGraph MCP server

This skill only works once CodeGraph is installed and indexing this project — it is a separate tool, not something claude-workspace bundles:

curl -fsSL https://raw.githubusercontent.com/colbymchenry/codegraph/main/install.sh | sh
codegraph install   # wires the MCP server into Claude Code
codegraph init      # builds this project's index

If the codegraph_* tools below are not available, the server isn't connected yet — install it first, then reload.

Purpose

CodeGraph indexes every symbol, edge and file in this workspace. Reads are near-instant and stay close to the true state of the code. Consult it before writing or editing code, not while guessing from memory.

When to reach for it

  • "How does X work?", "where is Y defined?", "what calls this?" — answer directly with CodeGraph rather than delegating to a sub-task or running an ad-hoc grep/read loop.
  • Before touching a function, check what depends on it so a change doesn't silently break a caller.

Tool selection

  • Symbol lookup by name → codegraph_search
  • "What's the deal with this feature/area?" → codegraph_context (composes search + callers + callees)
  • "How does X reach Y?" → codegraph_trace
  • "What calls this?" / "what does this call?" → codegraph_callers / codegraph_callees
  • "What would changing this break?" → codegraph_impact
  • Read a symbol's source/signature → codegraph_node; survey several related symbols → codegraph_explore

Fall back to plain Read/Grep only to confirm a specific detail CodeGraph did not cover.

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