App Harness

1. Create docs/spec.md from user request. Get user sign-off.
2. Pick ONE vertical slice.
3. Write docs/contract.md with:
   • What to build (user-visible outcome)
   • Files to change
   • Verification commands (exact, runnable)
   • Non-goals

Phase 2: Build → Evaluate loop (MANDATORY 5 rounds)

Every slice runs EXACTLY 5 rounds. No exceptions. No early exit.

For round N (1 through 5):

Step A — Launch Builder Agent:

Use the Agent tool with this prompt:

"You are a Builder. Read docs/contract.md and docs/eval-round-{N-1}.md (if exists).
Build or fix the code to satisfy the contract and address all eval feedback.
Do NOT evaluate your own work. Do NOT claim it works. Just write code.
When done, commit with message 'build: round N'."

Step B — Launch Evaluator Agent (SEPARATE agent, fresh context):

Use the Agent tool with this prompt:

"You are an Evaluator. You have NEVER seen the builder's reasoning.
Read docs/contract.md. Then verify the build:

1. Run scripts/verify.sh — report full output
2. Run the project test suite — report full output  
3. Execute each verification step from the contract LITERALLY
4. Try to break things: empty inputs, wrong types, rapid actions, missing auth, 
   mobile viewport, concurrent requests
5. Check rubrics/ for domain-specific quality gates

Write docs/eval-round-N.md with:
- PASS or FAIL for each verification step
- Exact error messages and reproduction steps for failures
- Red-team findings (issues not in contract but found by trying to break things)
- Overall verdict: PASS / FAIL

Be harsh. Your job is to find what's wrong, not confirm what's right.
Round 1-2: finding real bugs is expected.
Round 3-4: finding edge cases and polish issues.
Round 5: finding anything at all means the builder needs more work."

Step C — Record round in docs/contract.md verification log:

Round N: [PASS/FAIL] — [one-line summary of eval findings]

Repeat A→B→C for all 5 rounds.

Phase 3: After 5 rounds

4. Write docs/qa-report.md — final state of all verification steps
5. Update docs/handoff.md — what changed, what's next
6. Pick next slice → new contract → repeat Phase 2

Rules

Non-negotiable

• 5 rounds per slice. Always. Even if round 1 passes everything, the evaluator must dig deeper in rounds 2-5. No early exit.
• Builder and Evaluator are SEPARATE Agent calls. Never combine them. Never let the builder see the evaluator's reasoning process. They share files only.
• Evaluator must run commands. Code review alone is not evaluation. Run verify.sh, run tests, hit endpoints, load pages.
• Round 1 evaluator MUST find issues. If round 1 returns all-pass, the evaluator wasn't thorough enough. Relaunch with "dig deeper."

Escalation across rounds

What NOT to do

• Do NOT build and evaluate in the same agent call.
• Do NOT skip rounds. 5 means 5.
• Do NOT let the evaluator read the builder's chain-of-thought.
• Do NOT describe methodology. Launch agents, pass files, record results.