agentleFS
Sign inStart free
opum-aiopum-ai/proof-skills/CLAUDE.md

proof-skills

CLAUDE.md27 starsChanged 49 days agoMITView on GitHub

This project uses Quest CLI 0.9.0 for tracker operations. Run quest manifest --json to discover the supported command contract. Use quest instructions --json for the current versioned protocol. For Backlog tracker cutover, run quest migration backlog preview --source <project> --json, review its digest and mappings, then apply it with quest migration backlog apply --source <project> --digest <digest> --actor <id> --actor-kind human --json. Quest writes require an explicit actor declaration; do not edit Quest-authored records directly. CI should run quest agents…

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    When working on documentation, drive it through lore (not a plain editor) so Story <-> Task coupling, managed blocks, and cross-links stay …

    line 9
  2. Very specific:

    Just-in-time detail: run lore instructions for the canonical agent loop, then lore instructions <topic> (linking, sync, check, validation, …

    line 13

≈ “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
<!-- quest:agent-instructions:begin -->

Quest agent instructions

This project uses Quest CLI 0.9.0 for tracker operations. Run quest manifest --json to discover the supported command contract. Use quest instructions --json for the current versioned protocol. For Backlog tracker cutover, run quest migration backlog preview --source <project> --json, review its digest and mappings, then apply it with quest migration backlog apply --source <project> --digest <digest> --actor <id> --actor-kind human --json. Quest writes require an explicit actor declaration; do not edit Quest-authored records directly. CI should run quest agents --check --require-installed --target claude: current instructions, and a version-only difference (only the pinned Quest CLI version number is stale) both exit 0; missing, drifted, or malformed managed instructions exit 6. Quest does not retry write conflicts automatically; callers should read the latest task state and perform their own bounded retry when a command returns conflict/exit 5.

<!-- quest:agent-instructions:end --><!-- lore:agents:begin -->

This repo uses lore — an OKF-native documentation CLI — for the docs bundle under docs/. When working on documentation, drive it through lore (not a plain editor) so Story <-> Task coupling, managed blocks, and cross-links stay coherent.

  • Skill: .claude/skills/lore/SKILL.md — how to drive lore.
  • Just-in-time detail: run lore instructions for the canonical agent loop, then lore instructions <topic> (linking, sync, check, validation, workspace).
<!-- lore:agents:end -->

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