agentleFS
Sign inStart free
abersonaberson/skill-mesh/skills/citation-review/providers/claude.md

skill-mesh / providers

CLAUDE.md2 starsChanged 2 months agoMITView on GitHub

Claude provider entry point for citation-review; loads the canonical shared core.

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. Distinctive:

    Use Claude session JSONL, scratchpad identity, Artifact actions, or VS Code deep links only where available and requested by the core.

    line 15
  2. Distinctive:

    Treat the Citation Needed CLI as the only database writer.

    line 17
  3. Distinctive:

    Never modify the reviewed artifact, and never report a failed commit as a review result.

    line 18
  4. Very specific:

    If a required Claude host tool is unavailable, use the core's documented fallback.

    line 26

≈ “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

citation-review - Claude entry point

See ../core.md for the full specification.

Provider-specific instructions

  • Load the core in full before acting. Use Claude Code's Skill tool for named-skill calls and Agent/Workflow tools for isolated agents where the core requires those host abstractions.
  • Preserve the core's gates, retry limits, filesystem safety, and exact output contracts.
  • Use Claude session JSONL, scratchpad identity, Artifact actions, or VS Code deep links only where available and requested by the core.
  • Preserve the calibration gate: run cite calibrate check and STOP on a fingerprint mismatch or a stale gate unless the operator explicitly authorized --accept-aged. Never claim calibration passed without the CLI's own PASS result.
  • Treat the Citation Needed CLI as the only database writer. Send every review-commit and calibrate-commit payload on standard input via the Bash tool -- never on argv, and never through a host abstraction that would truncate it.
  • Never modify the reviewed artifact, and never report a failed commit as a review result.

Output normalization

Return only the core's operator-facing report: breakdown location, band, citations, and any documented absence. Preserve exact locked strings and the run id.

Unsupported capabilities

If a required Claude host tool is unavailable, use the core's documented fallback; otherwise halt visibly with required_tool_missing. Never weaken the calibration gate and never fabricate a citation.

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