What does the action do on a pull request?

Scores the pull request and its target branch, then posts one comment with how the overall score, each check and each agent's score changed. Later pushes update that comment.

Is it an AI code reviewer?

No. It calls no model and reviews no code. It checks the files agents rely on, like AGENTS.md, tests and CI config.

Why is AGENTS_BADGE_TOKEN required?

It's an on switch, not a password. Any value turns the comment on; unset, the action does nothing, so template repos can ship the workflow without it running in every copy.

Does it contact this website?

No. The scorer and weights are bundled into the action, so it works even if this site is down.

Does it work on private repos?

Yes. Scoring runs on the CI machine and your code is never sent anywhere. The comment uses the workflow's own GITHUB_TOKEN.

How do I pin a version?

@v0 follows the latest 0.x release; an exact tag such as @v0.1.0 stays on one version.

Agent Friendly Action: score every pull request

Comments on every pull request with how it changes your score for each agent, for example “this PR drops your Claude Code score by 4.1 points because it removed CI config”. It runs in your CI, and one secret turns it on.

Check the score on every pull request

Add this file. Each pull request gets one comment on how the score changed and why.

# .github/workflows/agent-friendly.yml
name: Agent-friendly score diff

on:
  pull_request:
    branches: [main]

permissions:
  contents: read
  pull-requests: write

jobs:
  score-diff:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v7
        with:
          fetch-depth: 0
      - uses: hsnice16/agent-friendly-action@v0
        with:
          agents-badge-token: ${{ secrets.AGENTS_BADGE_TOKEN }}

Add AGENTS_BADGE_TOKEN to the repo's secrets to turn the comment on. Without it, the action does nothing.

Set the AGENTS_BADGE_TOKEN secret

The action runs only when AGENTS_BADGE_TOKEN is set:

In your repo, open Settings → Secrets and variables → Actions.
Click New repository secret.
Name: AGENTS_BADGE_TOKEN. Value: any text, for example enabled. The value isn't read.
Click Add secret. The action runs on your next pull request.

GitHub's guide: docs.github.com — using secrets .

How it works

actions/checkout with fetch-depth: 0 gives the action the pull request and its target branch's history.
It scores both with the same weights, fetching the target commit if it is missing.
It posts or updates one comment, marked with .

FAQ

What does the action do on a pull request?
Scores the pull request and its target branch, then posts one comment with how the overall score, each check and each agent's score changed. Later pushes update that comment.
Is it an AI code reviewer?
No. It calls no model and reviews no code. It checks the files agents rely on, like AGENTS.md, tests and CI config.
Why is AGENTS_BADGE_TOKEN required?
It's an on switch, not a password. Any value turns the comment on; unset, the action does nothing, so template repos can ship the workflow without it running in every copy.
Does it contact this website?
No. The scorer and weights are bundled into the action, so it works even if this site is down.
Does it work on private repos?
Yes. Scoring runs on the CI machine and your code is never sent anywhere. The comment uses the workflow's own GITHUB_TOKEN.
How do I pin a version?
@v0 follows the latest 0.x release; an exact tag such as @v0.1.0 stays on one version.

Source

github.com/hsnice16/agent-friendly-action — MIT-licensed. Listed on the GitHub Marketplace under Code Quality / Continuous Integration.