AgentConfigScore

AgentConfigScore

English | 简体中文 | 繁體中文

Codecov for AI coding-agent instructions.

  Stop pull requests from quietly making AGENTS.md, CLAUDE.md, Cursor, Copilot and Gemini instructions worse.

AgentConfigScore is a deterministic regression gate for coding-agent configuration. It compares a change with its baseline and answers one CI-friendly question:
Did this change make our agent instructions worse?

It is regression-first rather than perfection-first: an existing repository can start at 72/100 and adopt the gate immediately. A pull request that stays at 72 can pass; one that drops to 65 can fail.

A 100 means no active deterministic rule matched—not that the instructions are semantically perfect. AgentConfigScore is a focused linter, not an AI judge. See the public score contract and known blind spots.

See the complete visual tour for setup, regression, and history demos.

Get running

New here? The user guide covers setup, pass/fail behavior,
exit codes and troubleshooting. The documentation index
separates everyday usage from research and benchmark material.

To test the latest stable pre-1.0 source directly from GitHub instead:

init safely creates:

- .agentconfigscore.json — version-controlled policy, suppressions, and editor schema annotation
- .github/workflows/agent-config-score.yml — pull-request regression gate

Review and commit those files. Pull requests are then checked automatically.

Validate the integration and run the same regression check locally before pushing:

diff auto-detects a safe local default-branch baseline when possible. You can still pass an explicit ref such as origin/main whenever you want full control.

Initialization is conservative: every target is preflighted before anything is written, conflicting files are never overwritten…