agentleFS
Sign inStart free
joris887joris887/exosuit/.claude/agents/CLAUDE.md

exosuit / agents

CLAUDE.md9 starsChanged 3 months agoMITView on GitHub

Native Claude Code agents (subagents) that provide specialized personas for focused tasks.

The file

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

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Keep agent files under 100 lines — agents are personas, not encyclopedias

    line 24
  2. Distinctive:

    Never add tool permissions beyond what the agent's role requires

    line 26

≈ “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 Directory

Native Claude Code agents (subagents) that provide specialized personas for focused tasks.

Usage

  • Invoked via claude --agent <name> or from skills using subagent delegation
  • Each .md file defines one agent persona with specific expertise and constraints
  • Agents inherit project rules and hooks — they are not independent of the framework

Available Agents

  • code-reviewer — PR and code review with checklist enforcement
  • architecture-reviewer — architectural fitness evaluation
  • codebase-explorer — read-only exploration and analysis
  • integration-tester — independent dynamic verification (runs tests and commands)
  • research-analyst — web research with source quality scoring
  • security-analyst — security-focused code audit
  • spec-reviewer — specification and requirements review
  • performance-engineer — performance analysis and optimization

Important

Native agents are dispatch targets for skills and parallel review, NOT replacements for quality gate skills. For quality gates, use the skills (/code-quality, /security-audit, /architecture-check, /performance-check), not the agents directly.

Conventions

  • Keep agent files under 100 lines — agents are personas, not encyclopedias
  • Agents should reference project rules/docs by path, not inline content
  • Never add tool permissions beyond what the agent's role requires

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