agentleFS
Sign inStart free
leodiegooleodiegoo/orq/AGENTS.md

orq

AGENTS.md2 starsChanged 42 days agoMITView on GitHub

This clone is orq's code and, by default, its state (ORQ_HOME), its plan (plan/) and its integration worktrees (.worktrees/), all gitignored. The README is the reference: Install, Projects, Where things live. Run this when the user asks to set orq up, or when orq is not on PATH in a session opened in this clone. A dispatched worker skips it. The live clone runs the hooks and the manager panel, so work happens in a worktree of your own (git…

  • 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

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:

    Run this when the user asks to set orq up, or when orq is not on PATH in a session opened in this clone.

    line 7
  2. Very specific:

    Check the tools: orca, git, gh, and a Python 3.12+ (python3 --version.

    line 9
  3. Very specific:

    Run python3 orq.py install from the clone and show its output.

    line 11
  4. Very specific:

    Add the user's projects as they name them: orq project add <path|url> --dry-run, show the orca.yaml and the ambientes it proposes, then run …

    line 13

≈ “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

orq

This clone is orq's code and, by default, its state (ORQ_HOME), its plan (plan/) and its integration worktrees (.worktrees/), all gitignored. The README is the reference: Install, Projects, Where things live.

First use

Run this when the user asks to set orq up, or when orq is not on PATH in a session opened in this clone. A dispatched worker skips it.

  1. Check the tools: orca, git, gh, and a Python 3.12+ (python3 --version; orq also finds Homebrew, mise, uv or python3.12). Optional: tasks-axi (backlog), lavish-axi (decision pages), engram, Bun (orq manager tui). Done when you have one line per tool: found with its version, or missing.
  2. List what is missing and ask the user before installing any of it. Install only what they approve.
  3. Run python3 orq.py install from the clone and show its output. Done when a second run prints no linked:, added or repointed line. When it names Codex hooks to trust, tell the user to review them once in /hooks.
  4. Turn this session into the coordinator: orq start --objective "<what the user is working on>". It needs an Orca terminal; outside one, tell the user to reopen the harness in an Orca terminal inside this clone.
  5. Add the user's projects as they name them: orq project add <path|url> --dry-run, show the orca.yaml and the ambientes it proposes, then run it without --dry-run once the user agrees.

Changing orq

The live clone runs the hooks and the manager panel, so work happens in a worktree of your own (git worktree add -b <type>/<description> .worktrees/<ticket> origin/main) and the live main moves only through scripts/integrar.py. Done when orq test --affected and python3 test_noite_replay.py are green in that worktree; the integrator runs the night replay and the full suite.

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