AAWEA.ORG

Manual start

↓

1

Run smoke checklist

Execute the staging smoke script or manual checklist (login, critical path, webhooks).

> npm run smoke:staging
2

Fix failures

If smoke fails, trace logs, fix the smallest issue, and redeploy or hotfix as appropriate.
3

Confirm green

Re-run smoke until all checklist items pass.

> npm run smoke:staging

↓

✓

Exit condition: ci_green

Staging smoke checklist passes

> npm run smoke:staging

📊 Flow Diagram

flowchart TD Start(["Manual start"]) Start --> S0 S0("Run smoke checklist") S1("Fix failures") S0 --> S1 S2("Confirm green") S1 --> S2 Exit{"Staging smoke checklist passes"} 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 "Staging Smoke Test" in your agent

Prompt only

Deeplinks and "Open in Cursor" only paste the kickoff prompt. They do not install hook files — your agent cannot tell whether files are on disk until you add them yourself.

Two separate pieces

Kickoff prompt — tells the agent the goal, check command, exit condition, and how to self-pace.

Kickoff prompt

Start the "Staging Smoke Test" loop.

Goal: staging smoke checklist passes
Max iterations: 6
Between iterations run: npm run smoke:staging
Exit when: smoke command exits 0

Step 1: Run the staging smoke checklist. Fix the first failing item, then repeat.

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