agentleFS
Sign inStart free
SprocketLabSprocketLab/slop-code-bench/AGENTS.md

slop-code-bench

AGENTS.md288 starsChanged 11 months agoMITView on GitHub

Note: Dashboard visualization features are partially documented via the viz diff command. See docs/commands/viz.md for details.

  • 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 31,774 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 repository8 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, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Use from __future__ import annotations, pathlib.Path, and type annotations for all functions.

    line 28
  2. Very specific:

    Test files use *_test.py or test_*.py under tests/.

    line 34
  3. Distinctive:

    No explicit coverage target.

    line 35
  4. Very specific:

    NEVER: run a problem's test with pytest.

    line 36
  5. Distinctive:

    Commit history favors short, capitalized summaries without scopes (e.g., “Canary Fix”).

    line 39

≈ “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

Repository Guidelines

Project Structure & Module Organization

  • src/slop_code/ holds the core library. Key areas: entrypoints/ (CLI), evaluation/, execution/, agent_runner/, metrics/, and dashboard/.
  • tests/ contains the pytest suite, generally mirroring src/ subpackages.
  • problems/ contains benchmark problems. Each problem has config.yaml, checkpoint_N.md (specs), and a tests/ directory with conftest.py, test_checkpoint_N.py files, and test data under tests/data/.
  • configs/ houses agent, model, prompt, environment, and run configs (e.g., configs/agents/, configs/models/).
  • docs/ provides guides for agents, evaluation, execution, and problem authoring; assets/ stores images; outputs/ stores run artifacts.

Note: Dashboard visualization features are partially documented via the viz diff command. See docs/commands/viz.md for details.

Build, Test, and Development Commands

uv sync                          # Install dependencies
uv run slop-code --help           # List CLI commands
uv run slop-code run ...          # Run an agent (see README for full example)
slop-code eval outputs/<run-dir>  # Evaluate a run directory
uv run slop-code tools run-case -s outputs/<snapshot> -p <problem> -c <n> -e configs/environments/docker-python3.12-uv.yaml
bash scripts/eval_checkpoint <problem name> <n>

uv run pytest -q                  # Run all tests
uv run pytest tests/path/to/test_file.py
uv run ruff check --fix .               # Lint

Coding Style & Naming Conventions

  • Python 3.12+, 4-space indentation, max line length 80 (ruff).
  • Use from __future__ import annotations, pathlib.Path, and type annotations for all functions.
  • Configuration should use Pydantic models; logging uses structlog.get_logger(__name__).
  • Imports are single-line (ruff isort settings); module names are snake_case, classes CapWords.

Testing Guidelines

  • Framework: pytest (see pyproject.toml).
  • Test files use *_test.py or test_*.py under tests/.
  • No explicit coverage target; add tests for new behavior and edge cases.
  • NEVER run a problem's test with pytest. ALWAYS use either: scripts/eval_checkpoint.sh, uv run slop-code --quiet eval-snapshot, or uv run slop-code --quiet tools run-case

Commit & Pull Request Guidelines

  • Commit history favors short, capitalized summaries without scopes (e.g., “Canary Fix”). Keep messages concise and descriptive.
  • For problem contributions, follow the PR template in docs/contributing-problems/checklist.md (overview, checkpoints, test counts).
  • For other PRs, include a clear description, link relevant issues, note tests run, and add screenshots for dashboard/UI changes.

Configuration & Credentials

  • API keys are provided via environment variables (see README). Do not commit secrets.
  • Environment/runtime settings live in configs/environments/ and configs/providers.yaml.

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