agentleFS
Sign inStart free
notquenotque/claude-code-toolkit/CLAUDE.md

claude-code-toolkit

CLAUDE.md444 starsChanged 9 days agoMITView on GitHub

Read AGENTS.md first. It holds the shared rules (communication standard, Jev loop, trust boundary, writing style, merge gate, project conventions). This file adds Claude Code-specific dispatch. The main thread is an orchestrator. It classifies requests, picks and loads the skill, and evaluates results. It runs Trivial and Simple work itself, since a dispatched agent cold-reloads ~12k tokens of instructions and re-reads files the main thread already holds. Dispatch an agent via the Agent tool only when it pays: parallel fan-out…

We split this CLAUDE.md into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read AGENTS.md first. It holds the shared rules (communication standard, Jev loop, trust boundary, writing style, merge gate, project …

    line 3

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md 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.

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

VexJoy Agent -- Claude Code

Read AGENTS.md first. It holds the shared rules (communication standard, Jev loop, trust boundary, writing style, merge gate, project conventions). This file adds Claude Code-specific dispatch.

Claude Code dispatch

The main thread is an orchestrator. It classifies requests, picks and loads the skill, and evaluates results. It runs Trivial and Simple work itself, since a dispatched agent cold-reloads ~12k tokens of instructions and re-reads files the main thread already holds. Dispatch an agent via the Agent tool only when it pays: parallel fan-out over independent parts, long lanes (about 5+ files, or work that would bloat main context), worktree isolation, read-only Haiku gathering, and Medium or Complex work. Rules: skills/meta/do/SKILL.md.

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