agentleFS
lucamartinslucamartins/ouroboros/.claude/CLAUDE.md

ouroboros

CLAUDE.md2 starsChanged 8 days agoMITView on GitHub

Claude Code plugin that learns from sessions on its own (memories + skills) with a local dashboard. The full design is in DESIGN.md; read it before changing behavior, and update it when a decision changes.

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:

    Must work on Windows, macOS and Linux: hooks use exec form (node <script> <args>), never shell-specific syntax.

    line 7
  2. Very specific:

    Never write plugin state under ${CLAUDE_PLUGIN_ROOT} (it changes on update).

    line 8

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 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

Ouroboros

Claude Code plugin that learns from sessions on its own (memories + skills) with a local dashboard. The full design is in DESIGN.md; read it before changing behavior, and update it when a decision changes.

  • Every file in this repository is in English — code, comments, docs, skills, commit messages and dashboard UI, whatever language the conversation is in.
  • Runtime: Node ≥ 22.13, zero dependencies (node:sqlite, node:http). No npm install, no build step. Tests: npm test (never a bare node --test: it runs the fixtures too and hangs).
  • Must work on Windows, macOS and Linux: hooks use exec form (node <script> <args>), never shell-specific syntax.
  • Never write plugin state under ${CLAUDE_PLUGIN_ROOT} (it changes on update); use ${CLAUDE_PLUGIN_DATA} or ~/.ouroboros/.
  • Plugin names must not start with claude-; validate with claude plugin validate --strict.
  • Every user-visible change (fix or feature) ships its release in the same PR: bump version in .claude-plugin/plugin.json, the Status: vX.Y.Z line at the top of DESIGN.md, and add a CHANGELOG.md entry (a minor gets its own ## X.Y.0 — <date> section; a patch is a - X.Y.Z: … bullet under its minor's section).

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.