agentleFS
vakovalskiivakovalskii/ontoship/AGENTS.md

ontoship

AGENTS.md125 starsChanged 5 months agoMITView on GitHub

The one entry point for every agent (Claude Code, Codex, Qwen Code, Cursor…): rules and a short map live here; CLAUDE.md only imports this file (@AGENTS.md). Start with docs/README.md; keep md as the source of truth, regenerate the index. OntoShip is a Claude Code marketplace (ontoship) shipping gitmark — an md+git knowledge base (FTS5 search, HTML graph, ontology linter) plus the spec-driven dev-flow built on top of it. destructive-guard (the PreToolUse safety hook) now lives in its own repo: github.com/vakovalskii/destructive-guard.

  • 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 31,542 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 repository4 other files it gives its agents.

The file

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

1 rule. About 0 are common, 1 is distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every folder's README.md is its index.

    line 37

≈ “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

OntoShip — entry point

The one entry point for every agent (Claude Code, Codex, Qwen Code, Cursor…): rules and a short map live here; CLAUDE.md only imports this file (@AGENTS.md). Start with docs/README.md; keep md as the source of truth, regenerate the index.

OntoShip is a Claude Code marketplace (ontoship) shipping gitmark — an md+git knowledge base (FTS5 search, HTML graph, ontology linter) plus the spec-driven dev-flow built on top of it.

destructive-guard (the PreToolUse safety hook) now lives in its own repo: github.com/vakovalskii/destructive-guard.

Where things live

.claude-plugin/        marketplace.json + plugin.json (the gitmark plugin manifest)
commands/              slash commands: /kb /kb-map /doc /onto-doc /ship
skills/
  kb-search/           the gitmark CLI engine (gitmark.py) + SKILL.md
  kb-curate/           rules for maintaining the KB as a typed ontology
  dev-flow/            the gated ship pipeline
docs/                  the knowledge base itself (this is the KB)

Start here

  • Knowledge base → docs/README.md — master index
  • The model → docs/ontology.md — how docs are typed & linked
  • How it fits together → docs/reference/architecture.md
  • Commands → docs/reference/commands.md

Principle

Markdown + git is the source of truth. Everything derived — the search index (.gitmark/index.db), the HTML graph — is regenerated, never committed as truth. Every folder's README.md is its index; never let a doc become an orphan.

Maintain

python3 skills/kb-search/gitmark.py index    # rebuild the index after editing docs
python3 skills/kb-search/gitmark.py lint     # check the ontology (broken links, orphans, frontmatter)
python3 skills/kb-search/gitmark.py map -o docs-map.html   # regenerate the graph

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.