agentleFS
Sign inStart free
fabianbothfabianboth/autonomous-review-loop/CLAUDE.md

autonomous-review-loop

CLAUDE.md2 starsChanged 9 months agoMITView on GitHub

Autonomous Review Loop - pairs your review bot with your coding agent to automate the review-fix-push cycle. When using Edit tools on Windows, you MUST use backslashes (\) in file paths, NOT forward slashes (/). Always verify code changes:

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

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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. Distinctive:

    Never suppress type/lint errors - fix them (rare exceptions only)

    line 37
  2. Distinctive:

    Avoid creating barrel exports via init files, always directly import instead

    line 38
  3. Distinctive:

    Always verify code changes:

    line 42
  4. Very specific:

    Verify changes with uv run ruff check

    line 45
  5. Very specific:

    Verify type checking with uv run pyright

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.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
CLAUDE.md

CLAUDE.md

Autonomous Review Loop - pairs your review bot with your coding agent to automate the review-fix-push cycle.

CRITICAL: File Editing on Windows

When using Edit tools on Windows, you MUST use backslashes (\) in file paths, NOT forward slashes (/).

Project Structure

  • src/reviewloop_cli/ — CLI package (typer-based), entry point in cli.py
  • src/reviewloop_cli/templates/ — Bundled template files (bash scripts, SKILL.md) — single source of truth for reviewloop init
  • specs/ — Feature specifications (speckit-managed)

Tech Stack

  • Python: 3.12+ with uv (CLI package + project tooling)
  • Bash: 4.0+ for review loop scripts (bundled in src/reviewloop_cli/templates/)
  • CLI Framework: typer, readchar (interactive selection)
  • Linting/Formatting: ruff
  • Type Checking: pyright (strict mode)

Commands

uv run ruff check
uv run ruff format
uv run pyright

Code Style

  • Self-explaining modular code: comment-free where possible (only comments when genuinely helpful)
  • Bash scripts use strict mode (set -euo pipefail)
  • Python 3.12+, line length 120, double quotes
  • Strict type hints (pyright strict mode) - all methods must be typed
  • Never suppress type/lint errors - fix them (rare exceptions only)
  • Avoid creating barrel exports via init files, always directly import instead

Change Verification

Always verify code changes:

  • Format code with uv run ruff format
  • Verify changes with uv run ruff check
  • Verify type checking with uv run pyright

Download now (ZIP)

  • In this repositoryOne other file it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

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