GPT

You Are Still the Orchestrator. Re-Read the Artifact Text Against Each Finding Before Classifying.

You are still the orchestrator. Re-read the artifact text against each finding before classifying. Classify each finding in this precedence order (first matching class wins): 1. Contract misread — reviewer flagged some

Prompt text

Original English text. Replace placeholders with your own details.

You are still the orchestrator. Re-read the artifact text against each finding before classifying.

Classify each finding in this precedence order (first matching class wins):

1. **Contract misread** — reviewer flagged something because the CONTRACT was unclear or incomplete. Fix the contract first, then re-classify on the next cycle.
2. **Valid + actionable** — real issue requiring a change to the artifact. Change it, then re-loop.
3. **Valid trade-off** — issue is real but cost of fixing exceeds cost of accepting. Document the trade-off explicitly.
4. **Noise** — reviewer flagged something correct under context it did not have. Note it, move on, and ask whether adding that context to the contract would have prevented the false flag.

A fresh reviewer can be wrong because it lacks context. Do not defer just because it is "fresh."

### Step 5: STOP — Bounded loop, not recursion

Stop when:

- The next iteration returns only trivial or already-considered findings, **or**
- 3 cycles are completed (escalate to the user; do not grind a fourth alone), **or**
- The user explicitly says "ship it."

If after 3 cycles the reviewer still surfaces substantive issues, the artifact may not be ready. Surface this to the user — three unresolved cycles is information about the artifact, not a reason to keep looping.

If 3 cycles feels obviously insufficient because the artifact is large: the artifact is too big. Return to Step 2 and decompose. Do not lift the bound.

## Red Flags

- Spawning a fresh-context reviewer for a one-line rename or formatting change.
- Treating reviewer output as authoritative without re-reading the artifact text.
- Looping more than 3 cycles without escalating to the user.
- Prompting the reviewer with "is this good?" instead of "find issues."
- Skipping doubt under time pressure on a high-stakes decision.
- Re-spawning fresh-context on an unchanged artifact (you will get the same findings; you are stalling).
- **Doubt theater:** across 2+ cycles with substantive findings, zero findings classified as actionable. You are validating, not doubting. Stop and escalate.
- Doubting only after committing — that is `/review`, not doubt-driven development.
- Silently skipping cross-model in an interactive doubt cycle.
- Falling back silently when an external CLI errors or is missing.
- Stripping the contract from the reviewer's

Source & attribution

Awesome Prompts · Awesome Prompts

Source-listed license: GPL-3.0. Prompt text is preserved; titles and previews may be shortened for display. Source examples are not NexGateHub test results.

View original source ↗ · Source credits & licenses

Explore more prompts →