AAWEA.ORG
AAWEA.ORG
AAWEA.ORG
Testing Manual trigger πŸ‘‘ Official πŸ›‘ Hardened

Independent Verifier Pass

When implementation claims done, a separate verifier pass runs build, lint, and tests with no access to the implementer's rationale.

πŸ‘ 1,243 views πŸ“₯ 1,717 installs πŸ‘€ by loops!
Download loop
Share Now
Manual start
↓
  1. 1
    Run verifier checks

    As an independent verifier, run build, lint, and tests. Do not assume the prior pass was correct.

    > npm run build && npm run lint && npm test
  2. 2
    Report gaps

    List every failing check with file paths and error excerpts. No self-reporting β€” only command output counts.

  3. 3
    Fix or hand back

    If failures exist, fix them or produce a concise failure report for the implementer to continue.

↓
βœ“
Exit condition: tests_pass

Build, lint, and tests all pass under independent verification

> npm run build && npm run lint && npm test
πŸ“Š Flow Diagram
flowchart TD Start(["Manual start"]) Start --> S0 S0("Run verifier checks") S1("Report gaps") S0 --> S1 S2("Fix or hand back") S1 --> S2 Exit{"Build, lint, and tests all pass under independent verification"} S2 --> 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
Run "Independent Verifier Pass" in your agent
Prompt only
Deeplinks and "Open in Cursor" only paste the kickoff prompt. They do not install hook files β€” your agent cannot tell whether files are on disk until you add them yourself.
Two separate pieces
  • Kickoff prompt β€” tells the agent the goal, check command, exit condition, and how to self-pace.
Kickoff prompt
Start the "Independent Verifier Pass" loop.

Goal: build, lint, and tests pass under independent verification
Max iterations: 8
Between iterations run: npm run build && npm run lint && npm test
Exit when: all verifier commands exit 0

Step 1: Run build, lint, and tests as a verifier. Trust only command output, not prior claims.

Self-pace this loop. After each iteration, run the check command, read the output, and only continue if the exit condition is not met. Stop when the exit condition passes or max iterations is reached. Give a short status update each pass.
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