littlebearappslittlebearapps/untether/.codex/AGENTS.md

untether

AGENTS.md72 starsChanged 37 days agoMITView on GitHub

After you finish work, commit with a conventional message. Only commit the files you edited. Always run checks before committing: If you fix anything from the checks, rerun and confirm they pass before committing. When using gh to edit or create PR descriptions, prefer --body-file to preserve newlines. Always include a "Manual testing" checklist section in PRs.

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 repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- llms-full.txtllms.txt
- llms.txtllms.txt
- claude-stream-jsonSkill
- codex-opencode-piSkill
- jsonl-subprocess-runnerSkill
- release-coordinationSkill
- telegram-bot-apiSkill
- untether-architectureSkill

The file

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

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
After you finish work, commit with a conventional message.
line 1
Distinctive:
Always run checks before committing:
line 3
Distinctive:
If you fix anything from the checks, rerun and confirm they pass before committing.
line 10
Very specific:
When using gh to edit or create PR descriptions, prefer --body-file to preserve newlines.
line 12
Distinctive:
Always include a "Manual testing" checklist section in PRs.
line 13
Distinctive:
All Telegram writes go through TelegramOutbox (never call Bot API directly)
line 23
Distinctive:
Use EventFactory for event construction, never construct dataclasses directly
line 24

≈ “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

After you finish work, commit with a conventional message. Only commit the files you edited.

Always run checks before committing:

uv run ruff format --check src/ tests/
uv run ruff check src/ tests/
uv run pytest

If you fix anything from the checks, rerun and confirm they pass before committing.

When using gh to edit or create PR descriptions, prefer --body-file to preserve newlines. Always include a "Manual testing" checklist section in PRs.

Project conventions

Python 3.12+, anyio for async, msgspec for JSONL parsing, structlog for logging
Engines: Claude Code, Codex, OpenCode, Pi (Gemini CLI and Amp: deprecated and no longer supported — still included, may be removed in a future release; Antigravity CLI ships in v0.36.1)
Australian English in user-facing text (realise, colour, behaviour, licence)
Conventional commits: feat:, fix:, docs:, refactor:, test:, chore:
80% test coverage threshold enforced
Runner 3-event contract: StartedEvent -> ActionEvent(s) -> CompletedEvent; Claude live sessions (#776) may add TurnEvent segments after it, never a second CompletedEvent
All Telegram writes go through TelegramOutbox (never call Bot API directly)
Use EventFactory for event construction, never construct dataclasses directly
Key commands: /cancel, /agent, /model, /planmode, /usage, /stats, /auth, /export, /browse, /config, /steer, /queue, /verbose, /restart

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