agentleFS
Sign inStart free
sergeeeysergeeey/Claude-cod-top-2026/agents/CLAUDE.md

Claude-cod-top-2026 / agents

CLAUDE.md9 starsChanged 6 months agoMITView on GitHub

Required frontmatter fields: Optional fields: maxTurns, isolation, effort, permissionMode, whenToUse - whenToUse — One-sentence trigger condition — used by dispatcher and skill-scout for agent routing.

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Read .claude/memory/activeContext.md before taking any action.

    line 20
  2. Distinctive:

    Do NOT write to memory files directly — return results to orchestrator.

    line 22
  3. Distinctive:

    Only list tools the agent actually needs.

    line 25
  4. Distinctive:

    Add context-loading step (read activeContext.md)

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 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

Agents — Local Rules

Structure

Each agent is a single markdown file with YAML frontmatter + instruction body.

Required frontmatter fields:

---
name: <agent-name>
description: <one-line — used for routing decisions>
tools: Read, Edit, Write, Bash, Glob   # list only what the agent needs
model: sonnet | opus | haiku
---

Optional fields: maxTurns, isolation, effort, permissionMode, whenToUse

  • whenToUse — One-sentence trigger condition — used by dispatcher and skill-scout for agent routing.

Context Protocol (every agent must do this)

Read .claude/memory/activeContext.md before taking any action. Return results tagged with the context item they address. Do NOT write to memory files directly — return results to orchestrator.

Tool Scope — Minimum Viable

Only list tools the agent actually needs.

  • Read-only agents: Read, Glob, Grep
  • Builder agents: Read, Edit, Write, Bash, Glob
  • Research agents: Read, Glob, Grep, WebSearch, WebFetch

Teams (in teams/)

Teams run 2+ agents in parallel. Use for:

  • review-squad — reviewer + sec-auditor simultaneously
  • build-squad — builder + tester simultaneously
  • research-squad — explorer + verifier simultaneously

Adding a New Agent

  1. Copy closest existing agent as template
  2. Set minimum tool scope
  3. Add context-loading step (read activeContext.md)
  4. Register in README agents table

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