AAWEA.ORG

Manual start

↓

1

Detect edited files

Identify which source files were edited in the last turn.
2

Run related tests

Run the smallest relevant test subset for edited files. Fix failures before continuing.

> npm test -- --findRelatedTests

↓

✓

Exit condition: tests_pass

Related tests pass after each edit batch

> npm test -- --findRelatedTests

📦 Install Files

These files are included when you download the loop.

📄 .cursor/hooks.json

{
  "version": 1,
  "hooks": {
    "afterFileEdit": [
      {
        "type": "prompt",
        "prompt": "Post-Edit Test Guard: run related tests for the files just edited. If tests fail, fix them before continuing other work."
      }
    ]
  }
}

📄 .claude/settings.json

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Write|Edit",
        "hooks": [
          {
            "type": "prompt",
            "prompt": "Post-Edit Test Guard: run related tests for the files just edited. If tests fail, fix them before continuing other work."
          }
        ]
      }
    ]
  }
}

📄 .cursor/loops/post-edit-test-guard/README.md

# Post-Edit Test Guard

Uses the `afterFileEdit` hook (Cursor) and `PostToolUse` hook (Claude Code) to run related tests after edits.

## Pair with
Copy the kickoff prompt from loops! to align agent behavior with the hook.

📊 Flow Diagram

flowchart TD Start(["Event start"]) Start --> S0 S0("Detect edited files") S1("Run related tests") S0 --> S1 Exit{"Related tests pass after each edit batch"} S1 --> Exit Exit -- "No" --> S0 Exit -- "Yes" --> Done(["Success"]) style Exit fill:#fffbeb,stroke:#f59e0b,stroke-width:2px,color:#92400e style Done fill:#ecfdf5,stroke:#10b981,stroke-width:2px,color:#065f46

Kickoff prompt

Install and run the "Post-Edit Test Guard" loop.

Goal: after each batch of file edits, related tests must pass before continuing.
Between iterations run: npm test -- --findRelatedTests <edited files>
Exit when: related tests exit 0.

Step 1: After edits, run related tests. If they fail, fix before making more changes.

Anti-gaming rules

Rules the agent must follow so it cannot cheat the exit condition.

Do not modify the check command or exit criteria to force success
Do not skip, disable, or bypass checks to pass the exit condition
If stuck after several iterations, stop and report blockers instead of gaming metrics