Test-Driven Bug Hunting With Reproduction Agents

This prompt guides users through a structured process of identifying, reproducing, and fixing bugs in software. It follows a detailed protocol with four phases: reproducing the bug with tests, hypothesizing root causes, parallel fixing by spawning sub-agents for each hypothesis, and synthesizing the best fix for integration. Ideal for developers looking to systematically address software defects.

@ilker

22 days agoJuly 11, 2026 at 01:25 PM

coding

Content

Variables

bug

Bug report: . 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.

Test-Driven Bug Hunting With Reproduction Agents

Content

Comments (0)