agentleFS
Sign inStart free
gfrancodevgfrancodev/canon/AGENTS.md

canon

AGENTS.md1 starsChanged 52 days agoMITView on GitHub

Before architecture work in a repository that already has .canon/manifest.yaml, delegate to canon-architect (agents/canon-architect.md). Do not call individual Canon skills directly for structural changes. Core workflow: Language and ecosystem are inferred from repository evidence (detect). Never ask the user for a language flag. Do not introduce new module boundaries, dependencies, or abstractions without checking project decisions first. When creating or editing a file, follow the kind in .canon/conventions.yaml whose match fits that file. Copy its shape, how, the naming table,…

  • 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 repository7 other files it gives its agents.

The file

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

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

  • 4

    Very specific

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

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

    Before architecture work in a repository that already has .canon/manifest.yaml, delegate to canon-architect (agents/canon-architect.md).

    line 3
  2. Very specific:

    Treat explicit .canon/ project decisions as authority over generic patterns.

    line 8
  3. Very specific:

    Use /canon create when no architecture contract exists yet.

    line 9
  4. Very specific:

    Run deterministic architecture review after edits (after-edit).

    line 10
  5. Distinctive:

    Do not introduce new module boundaries, dependencies, or abstractions without checking project decisions first.

    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

Canon agent instructions

Before architecture work in a repository that already has .canon/manifest.yaml, delegate to canon-architect (agents/canon-architect.md). Do not call individual Canon skills directly for structural changes.

Core workflow:

  1. Load architecture context before planning (before-plan hook or hook --event before-plan).
  2. Treat explicit .canon/ project decisions as authority over generic patterns.
  3. Use /canon create when no architecture contract exists yet.
  4. Run deterministic architecture review after edits (after-edit).
  5. Record build and test evidence before finishing (before-finish).

Language and ecosystem are inferred from repository evidence (detect). Never ask the user for a language flag.

Do not introduce new module boundaries, dependencies, or abstractions without checking project decisions first.

When creating or editing a file, follow the kind in .canon/conventions.yaml whose match fits that file. Copy its shape, how, the naming table, and an example already in the repo. A use case is only one kind. The same obligation applies to ports, entities, adapters, controllers, and any kind the project identified. Ask before replacing that pattern (sync-conventions --confirm). New violations fail review. Findings already in .canon/baseline.json stay as accepted debt.

Portable hook integration details live in adapters/AGENTS.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.

Check your setup, free