agentleFS
ghvinashvilighvinashvili/specagent/AGENTS.md

specagent

AGENTS.md7 starsChanged 12 days agoApache-2.0View on GitHub

  • Reads credentials

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:

    Every change ships with tests in the package's tests/.

    line 19
  2. Distinctive:

    Never delete or weaken an existing test to make a change pass.

    line 20
  3. Very specific:

    Do not add network calls to new hosts without an entry in docs/quality/SECURITY.md.

    line 28
  4. Very specific:

    Use .github/PULL_REQUEST_TEMPLATE.md.

    line 32
  5. Very specific:

    Every new document gets one line in docs/llms.txt, or in its folder's README.md when docs/llms.txt links that README.

    line 33

≈ “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

AGENTS.md

Project overview

Python monorepo managed with uv (packages/*). packages/harness is the CLI that runs multi-session agent work; the other packages are the product. Nested AGENTS.md files in packages take precedence for files under them.

Setup and commands

  • uv sync — install the workspace
  • uv run pytest -q packages/<pkg> — tests of one package (uv run builds the environment of a fresh worktree on first use)
  • uv run ruff check . && uv run ruff format --check . — lint and format check
  • just validate — harness self-check (schemas, role types, skills, settings)

Code style

  • Python 3.12, type hints on public functions, ruff rules from the root pyproject.toml.
  • Small modules; one responsibility per file; no top-level side effects on import.

Testing

  • Every change ships with tests in the package's tests/.
  • Never delete or weaken an existing test to make a change pass; report it instead.
  • Tests that need a database run on the database engine production uses (PostgreSQL where production runs PostgreSQL, in a container or a local server), never SQLite or an in-memory stand-in to save time.
  • The tests of packages/harness read docs/roles/, which a role session cannot see: in a role session run the tests of the packages you work on. The gate runs the whole suite outside the session.

Security

  • Secrets come from the environment; commit only .env.example.
  • Do not add network calls to new hosts without an entry in docs/quality/SECURITY.md.

Commits and pull requests

  • Conventional Commits (feat, fix, docs, refactor, test, chore, ci, build, perf, style).
  • Use .github/PULL_REQUEST_TEMPLATE.md; link the spec or ADR the change implements.
  • Every new document gets one line in docs/llms.txt, or in its folder's README.md when docs/llms.txt links that README; a plan folder gets its line in docs/exec-plans/active/README.md (.claude/rules/docs.md).
  • A code change carries its pages under wiki/, docs/runbooks/ or docs/decisions/ in the same commit, or its task's entry in the planner's tasks.json says why not (docs: none — <reason>; ADR-0027).

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.