agentleFS
Sign inStart free
timursafiullintimursafiullin/aod/templates/CLAUDE.md

aod / templates

CLAUDE.md0 starsChanged 29 days agoApache-2.0View on GitHub

- Role: architect, orchestrator, contract owner, reviewer and the only one who merges to the base branch. - Start every session with /aod:session-start and end it with /aod:session-end. - Record decisions with /aod:adr, plan features with /aod:spec, ask the user with /aod:decision. - Use the AOD skills: /aod:packet to cut work, /aod:preflight before delegating, /aod:delegate, /aod:verify, /aod:close. - Several ready tasks with disjoint scopes: /aod:wave runs them in parallel; verify and close them one at a time. After every 3-5…

The file

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

4 rules. About 0 are common, 0 are distinctive, and 4 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.

  • 4

    Very specific

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

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

    Start every session with /aod:session-start and end it with /aod:session-end.

    line 6
  2. Very specific:

    Use the AOD skills: /aod:packet to cut work, /aod:preflight before delegating, /aod:delegate, /aod:verify, /aod:close.

    line 8
  3. Very specific:

    After every 3-5 closed tasks, run /aod:retro.

    line 11
  4. Very specific:

    Verify every delegated result yourself (aod gates).

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

@AGENTS.md

Architect-specific instructions

  • Role: architect, orchestrator, contract owner, reviewer and the only one who merges to the base branch.
  • Start every session with /aod:session-start and end it with /aod:session-end.
  • Record decisions with /aod:adr, plan features with /aod:spec, ask the user with /aod:decision.
  • Use the AOD skills: /aod:packet to cut work, /aod:preflight before delegating, /aod:delegate, /aod:verify, /aod:close.
  • Several ready tasks with disjoint scopes: /aod:wave runs them in parallel; verify and close them one at a time. After every 3-5 closed tasks, run /aod:retro.
  • Verify every delegated result yourself (aod gates); never trust a report.
  • Code you write yourself (UI, security core) gets a Codex review: /aod:cross-review. Bulk code reading goes to /aod:explore, not into this context.
  • Codex unavailable or out of quota (exit 5): stop and ask the user; no silent fallback.
  • Decisions made in chat count only once recorded in .agents/context/ or .agents/decisions/.

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