agentleFS
Sign inStart free
hidai25hidai25/eval-view/docs/AGENTS.md

eval-view

AGENTS.md140 starsChanged 11 months agoApache-2.0View on GitHub

  • Reads credentials
  • 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 repository6 other files it gives its agents.

The file

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

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

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

    Run example flow: make run-example (initializes .evalview/ then runs sample case if present).

    line 13
  2. Distinctive:

    Keep public CLI/API stable.

    line 19
  3. Very specific:

    Run locally with pytest or evalview run --pattern "<case>.yaml" --verbose.

    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

Repository Guidelines

Project Structure & Module Organization

  • evalview/: Python package and CLI (cli.py). Modules: adapters/ (framework integrations), core/ (types, loader, pricing), evaluators/ (cost, latency, output, sequence), reporters/ (console, JSON).
  • tests/: Pytest assets and YAML scenarios under tests/test-cases/*.yaml.
  • docs/: Reference docs (adapters, database, backend setup). examples/: Example YAML and backend notes.
  • Root tooling: Makefile, pyproject.toml, uv.lock, optional Node workspace (package.json).

Build, Test, and Development Commands

  • Install: make install (editable) or make dev-install (adds dev deps).
  • Quality: make format (black), make lint (ruff), make typecheck (mypy), make check (all).
  • Tests: make test (pytest -v) or make test-cov (coverage HTML + terminal).
  • Run example flow: make run-example (initializes .evalview/ then runs sample case if present).
  • CLI test runner: evalview run [--pattern "*.yaml"] [--verbose].

Coding Style & Naming Conventions

  • Python 3.9+. Formatting via black (line length 100); lint with ruff; strict typing with mypy.
  • Indentation: 4 spaces. Naming: modules/files snake_case.py, classes PascalCase, functions/vars snake_case.
  • Keep public CLI/API stable; extend via new adapters/evaluators under existing folders.

Testing Guidelines

  • Framework: pytest. Place Python tests under tests/. Name files test_*.py.
  • Scenario tests: add YAML cases to tests/test-cases/ (see existing examples). Prefer precise expected.output.contains and realistic thresholds (max_cost, max_latency).
  • Run locally with pytest or evalview run --pattern "<case>.yaml" --verbose.

Commit & Pull Request Guidelines

  • Commits: imperative, concise, and scoped (e.g., "Add LangGraph adapter config"). Group related changes; include rationale when behavior changes.
  • PRs: clear description, linked issues, reproduction/testing steps, CLI output or screenshots when useful. Update docs/tests as needed.
  • Checks: ensure make check and make test pass; avoid committing secrets or .env.local.

Security & Configuration Tips

  • Secrets: store in .env.local (gitignored). Common: OPENAI_API_KEY, service endpoints.
  • Local config: .evalview/config.yaml controls defaults for runs. Avoid hard‑coding credentials in tests or examples.

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