agentleFS
Sign inStart free
sametbrrsametbrr/llm-wiki-manager/AGENTS.md

llm-wiki-manager

AGENTS.md72 starsChanged 11 days agoMITView on GitHub

Agent Skill + plugin (Claude Code and Codex) for a Karpathy-style LLM-managed markdown wiki.

  • 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 31,700 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 repository2 other files it gives its agents.

The file

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

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Update CHANGELOG.md and both READMEs (EN + TR mirror) with every version bump.

    line 14
  2. Distinctive:

    Never commit or push without explicit approval from the maintainer.

    line 15

≈ “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

llm-wiki-manager — agent guide

Agent Skill + plugin (Claude Code and Codex) for a Karpathy-style LLM-managed markdown wiki.

Layout

  • skills/llm-wiki-manager/SKILL.md: mode router. references/ holds one workflow per mode; assets/templates/ holds the page templates; scripts/ holds five stdlib-only Python scripts plus schema_file.py (AGENTS.md/CLAUDE.md detection).
  • .claude-plugin/plugin.json and .codex-plugin/plugin.json: keep version identical in both and in SKILL.md metadata.version.
  • tests/test_scripts.py: functional tests that run every script against temp wikis.

Rules

  • Scripts stay Python stdlib only, idempotent, and take --path <wiki-root>. Never hardcode CLAUDE.md; go through schema_file.resolve_schema_file.
  • A structural convention change bumps EXPECTED_SCHEMA_VERSION in migrate_wiki.py and adds a migration step.
  • Host-neutral wording; no ~/.claude/... paths in skill text.
  • Update CHANGELOG.md and both READMEs (EN + TR mirror) with every version bump.
  • Never commit or push without explicit approval from the maintainer.

Checks

  • python3 -m unittest discover -s tests
  • claude plugin validate .
  • Codex: install from a local marketplace in an isolated CODEX_HOME; llm-wiki-manager:llm-wiki-manager must appear in codex debug prompt-input.

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