agentleFS
lutzseverinolutzseverino/repo-canon/AGENTS.md

repo-canon

AGENTS.md1 starsChanged yesterdayMITView on GitHub

Before changing this repository, read CONTRIBUTING.md. Read docs/agents/project.md, when present, for repository-specific constraints. For setup and validation commands, read docs/development/README.md. Deliver every change as one pull request: implement, then review in a separate agent when configured, as CONTRIBUTING.md directs. Before handing work to another agent, subagent or session, check whether an installed skill covers it. This includes implementation workers delegating ticket subwork without invoking orchestrate or triage, and heavy reads. When covered, invoke that skill using the session's supported invocation…

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

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

4 rules. About 0 are common, 1 is distinctive, and 3 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.

  • 3

    Very specific

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

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

    Before changing this repository, read CONTRIBUTING.md.

    line 3
  2. Very specific:

    Read docs/agents/project.md, when present, for repository-specific constraints.

    line 4
  3. Very specific:

    Before handing work to another agent, subagent or session, check whether an installed skill covers it.

    line 13
  4. Distinctive:

    When covered, invoke that skill using the session's supported invocation mechanism, followed by task context.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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

Agent guidance

Before changing this repository, read CONTRIBUTING.md. Read docs/agents/project.md, when present, for repository-specific constraints.

For setup and validation commands, read docs/development/README.md.

Deliver every change as one pull request: implement, then review in a separate agent when configured, as CONTRIBUTING.md directs.

Agent skills

Before handing work to another agent, subagent or session, check whether an installed skill covers it. This includes implementation workers delegating ticket subwork without invoking orchestrate or triage, and heavy reads. When covered, invoke that skill using the session's supported invocation mechanism, followed by task context. When no installed skill covers the work, pass task context only.

Task context includes issue links, evidence, recorded decisions, scope, workspace and plan references, report-back destinations and task-specific delivery obligations. Keep procedure and question format with the invoked skill.

Where session naming is supported, name sessions you launch or own for their operation and target. Otherwise, continue without naming. Keep naming metadata outside the skill invocation and task context.

Issue tracker

Issues, specifications, and tickets live in GitHub Issues, worked with the gh CLI. See docs/agents/issue-tracker.md.

Triage labels

The canonical triage roles map to Repo Canon's state: labels. See docs/agents/triage-labels.md.

Domain docs

Single-context by default: a root GLOSSARY.md and docs/adr/; a root GLOSSARY-MAP.md makes it multi-context. See docs/agents/domain.md.

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.