agentleFS
Sign inStart free
littlebearappslittlebearapps/contextdocs/CLAUDE.md

contextdocs

CLAUDE.md5 starsChanged 6 months agoMITView on GitHub

Canonical description (use this in all listings and submissions): Your AI agent maintains its own context files — a Claude Code plugin with an AGENTS-first model that covers Codex, Copilot, Cursor, Gemini, and 3 more tools. Pure Markdown Claude Code plugin — no JavaScript, no Python, no build step, no runtime dependencies. Signal Gate filtering, Context Guard hooks, and 0-100 health scoring.

The file

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

4 rules. About 0 are common, 1 is distinctive, and 3 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.

  • 3

    Very specific

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

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

    Add a skill: Create .claude/skills/<name>/SKILL.md + commands/<name>.md, update README.md, AGENTS.md, llms.txt, and AGENTS-first generation …

    line 31
  2. Very specific:

    Add a command: Create commands/<name>.md with YAML frontmatter, update README.md, AGENTS.md, llms.txt

    line 32
  3. Very specific:

    Add an agent: Create .claude/agents/<name>.md with frontmatter, update AGENTS.md, llms.txt, context-guard SKILL.md

    line 33
  4. Distinctive:

    Change shared conventions: Update AGENTS.md first, then only the bridge docs whose tool-specific notes change

    line 35

≈ “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

ContextDocs

Canonical description (use this in all listings and submissions):

Your AI agent maintains its own context files — a Claude Code plugin with an AGENTS-first model that covers Codex, Copilot, Cursor, Gemini, and 3 more tools.

Pure Markdown Claude Code plugin — no JavaScript, no Python, no build step, no runtime dependencies. Signal Gate filtering, Context Guard hooks, and 0-100 health scoring.

Commands

  • Token budget test: bash tests/check-token-budgets.sh
  • llms.txt validation: bash tests/validate-llms-txt.sh
  • Spell check: typos (config: _typos.toml, Australian English)
  • Frontmatter lint: python3 tests/validate-frontmatter.py

Conventions

  • Australian English: realise, colour, behaviour, licence (noun), license (verb)
  • Conventional Commits: feat:, fix:, docs:, chore: — release-please automates versioning
  • Line budgets: CLAUDE.md bridge <80, AGENTS.md <120, other bridge files <60

Architecture

  • AGENTS-first generation: AGENTS.md is the canonical shared context for commands, conventions, constraints, and security notes
  • Thin bridges: CLAUDE.md, .cursor/rules/agents.mdc, optional Copilot instructions, .clinerules/agents.md, .windsurfrules, and GEMINI.md should add only tool-specific behaviour
  • Modern formats: Modern Cursor uses .cursor/rules/*.mdc with frontmatter (description / globs / alwaysApply); modern Cline uses the .clinerules/ directory with optional paths: per-file frontmatter. Legacy .cursorrules and flat .clinerules are preserved only when already present
  • Optional bridges: .github/copilot-instructions.md is optional — Copilot's coding agent loads AGENTS.md natively (since Aug 2025); only emit when adding tool-specific scoping
  • Compatibility bridges: .windsurfrules and GEMINI.md remain generated for now for tool compatibility

When Modifying

  • Add a skill: Create .claude/skills/<name>/SKILL.md + commands/<name>.md, update README.md, AGENTS.md, llms.txt, and AGENTS-first generation guidance if shared output behaviour changed
  • Add a command: Create commands/<name>.md with YAML frontmatter, update README.md, AGENTS.md, llms.txt
  • Add an agent: Create .claude/agents/<name>.md with frontmatter, update AGENTS.md, llms.txt, context-guard SKILL.md
  • Change quality standards: Edit .claude/rules/context-quality.md — propagates automatically
  • Change shared conventions: Update AGENTS.md first, then only the bridge docs whose tool-specific notes change
  • Bump version: Handled by release-please from conventional commit messages

Key Files

FilePurpose
AGENTS.mdCanonical shared product context — inventory, command model, and AGENTS-first architecture
.claude-plugin/plugin.jsonPlugin manifest — name, version, keywords
.claude/rules/context-quality.mdAuto-loaded quality rule — AGENTS-to-bridge consistency, path verification, sync points
.claude/rules/context-awareness.mdAuto-loaded trigger map — suggests ContextDocs commands when relevant, includes autonomous action triggers
.claude/agents/context-updater.mdAutonomous agent — launched by hooks to update stale context files with an AGENTS-first workflow
.claude/agents/docs-freshness.mdRead-only agent — checks documentation freshness, suggests PitchDocs commands (PitchDocs)
.claude/rules/doc-standards.mdAuto-loaded quality rule — 4-Question Test, Lobby Principle, banned phrases (PitchDocs)
.claude/rules/docs-awareness.mdAuto-loaded trigger map — suggests PitchDocs commands when docs-relevant work is detected (PitchDocs)
docs/faq/faq.mdSynced FAQ — emits Schema.org FAQPage JSON-LD on littlebearapps.com/help/contextdocs/faq/ via the marketing-site sync (issue #25, renamed from index.md per #29). Do not delete or move — upstream build hard-fails. Update only when an answer goes stale, not on every release

Known Limitations

  • Headless mode skill activation: Skills don't reliably auto-trigger via claude -p. This is a Claude Code platform issue (anthropics/claude-code#32184), not a ContextDocs bug. Interactive mode works correctly. Activation evals using claude -p will show artificially low pass rates.

Relationship to PitchDocs

ContextDocs was extracted from PitchDocs v1.19.3. PitchDocs handles public-facing docs (README, CHANGELOG, ROADMAP). ContextDocs handles AI IDE context files. Both work independently.

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