Test-Driven Bug Hunting With Reproduction Agents
Enter a bug report to have it write a failing mock-based test first, form hypotheses about the cause, then run sub-agent fixes for the top hypotheses through to a merge recommendation.
| Category | Development › Coding |
|---|---|
| Tags | AnalyzingReviewingDeveloperCode |
Bug report: ${bug}. Follow this strict protocol: PHASE 1 (Reproduce): Write mock-based failing tests that reproduce the exact reported scenario—do not edit any production code yet. Show me the failing test output. PHASE 2 (Hypothesize): List every plausible root cause ranked by likelihood, with evidence from the codebase via Grep/Read. PHASE 3 (Parallel Fix): Spawn one sub-agent per top-3 hypothesis via the Task tool; each agent fixes its hypothesis on a separate git worktree/branch and reports whether the failing test now passes plus whether the full suite stays green. PHASE 4 (Synthesize): Recommend which fix to merge and why, then commit. Refuse to skip phases.What this prompt does
Useful for a strict development workflow that starts bug fixing from reproduction tests. It requires failing output before production edits, evidence via Grep/Read, and separate worktrees for candidate fixes.
More in this category
| E COMMERCE WEBSITE | |
| Plataforma Escopo Bugbouty Cyber Hunter Lab | |
| Voice Cloning Assistant | |
| 2046 Puzzle Game Challenge | |
| 21st.dev component prompt |
Test-Driven Bug Hunting With Reproduction Agents