agentleFS
Sign inStart free
nicuknicuk/claude-md-memory-architecture/AGENTS.md

claude-md-memory-architecture

AGENTS.md0 starsChanged 46 days agoMITView on GitHub

This repo is a Claude Code plugin: skills/memory-architecture/SKILL.md is the skill, skills/memory-architecture/scripts/audit_memory.py its script. It's public, and one of three Cairn plugins whose shared principles and evidence are in nicuk/cairn-principles. Each rule names what enforces it, or says that nothing does. The audit warns on a rule here that does neither. Everything in .github/workflows/self-test.yml runs on every push. - Every check the script gains gets a planted defect in --self-test. The self-test reads the check names from the script itself,…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repositoryOne other file it gives its agents.

The file

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

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

  • 3

    Very specific

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

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

    The skill's frontmatter must parse as strict YAML: Never put : inside the description.

    line 24
  2. Very specific:

    README ## sections are shared across the family: don't add, rename or reorder one here alone.

    line 29
  3. Very specific:

    Nothing private goes in this repo: no client or product names, no private codebases, no absolute paths from anyone's machine.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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
AGENTS.md

Cairn Memory: rules for agents working here

This repo is a Claude Code plugin: skills/memory-architecture/SKILL.md is the skill, skills/memory-architecture/scripts/audit_memory.py its script. It's public, and one of three Cairn plugins whose shared principles and evidence are in nicuk/cairn-principles.

Each rule names what enforces it, or says that nothing does. The audit warns on a rule here that does neither. Everything in .github/workflows/self-test.yml runs on every push.

Rules

  • Every check the script gains gets a planted defect in --self-test. The self-test reads the check names from the script itself, so a check without one fails it. Enforced by skills/memory-architecture/scripts/audit_memory.py.
  • The script stays read-only and can't reach the network. Enforced by .github/scripts/check_privacy.py, which reads the code: no networking import in any form, no program but read-only git, file writes only in --draft-index and the self-test. That PRIVACY.md still describes this is not enforced: re-read it whenever either changes.
  • The skill's frontmatter must parse as strict YAML. Never put : inside the description. Enforced by .github/scripts/check_frontmatter.py, because claude plugin validate doesn't.
  • Numbers the docs state about the repo come from their source. Enforced by .github/scripts/check_claims.py: the check count in the README, the plugin description and the demo, the eval results, and the fixture's expected output.
  • README ## sections are shared across the family: don't add, rename or reorder one here alone. Enforced by the daily drift check in nicuk/cairn-principles, and before a push by .githooks/run_ci_locally.py when that repo is cloned alongside this one.
  • Every release raises version in .claude-plugin/plugin.json, with an entry in CHANGELOG.md and a git tag. Version and changelog are enforced by .github/scripts/check_claims.py. The tag is not enforced: tag vX.Y.Z when the release merges.
  • Nothing private goes in this repo: no client or product names, no private codebases, no absolute paths from anyone's machine. Absolute paths are enforced by .github/scripts/check_claims.py. Names and private code are not enforced: check before committing.
  • Hooks and agents for working on this repo go in .claude/, never in a root hooks/ or agents/ folder. The plugin ships from the repo root, so those folders would run in every installer's sessions. Enforced by .github/scripts/check_claims.py.

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