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

exosuit / rules

CLAUDE.md9 starsChanged 3 months agoMITView on GitHub

Auto-loaded markdown rules that Claude Code injects based on file path matching.

The file

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

3 rules. About 0 are common, 3 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every rule includes a tracking event emitter for effectiveness measurement

    line 31
  2. Distinctive:

    Keep rules under 100 lines — they load into every matching interaction

    line 32
  3. Distinctive:

    Put enforcement here, guidance in skills — rules cannot be skipped

    line 33

≈ “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

Rules Directory

Auto-loaded markdown rules that Claude Code injects based on file path matching.

How Rules Work

  • Rules with paths: frontmatter load ONLY when Claude edits files matching those globs
  • Rules WITHOUT path scoping load for ALL interactions
  • Rules are deterministic enforcement — Claude cannot skip them (unlike skills)

Path Scoping Example

---
paths:
  - "docs/**"
  - "**/*.md"
---

Current Rules

  • code-slop.md — bans AI filler patterns (no path scope — always active)
  • dependencies.md — dependency management guardrails
  • documentation.md — doc creation/update constraints (scoped to docs/** and *.md)
  • edit-recovery.md — edit failure recovery protocol
  • git.md — git workflow enforcement
  • research.md — research output quality standards
  • security.md — secrets detection and security patterns
  • testing.md — TDD enforcement and test quality
  • verification.md — evidence-based completion claims

Conventions

  • Every rule includes a tracking event emitter for effectiveness measurement
  • Keep rules under 100 lines — they load into every matching interaction
  • Put enforcement here, guidance in skills — rules cannot be skipped

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