>_ BuildaPrompt
TEXT en

Test-Driven Bug Hunting With Reproduction Agents

Test-Driven Bug Hunting With Reproduction Agents — a ready-to-use text prompt with customizable fields (bug) for Development & Code. Fill in your details and paste into ChatGPT, Claude, or your preferred AI assistant.

How to use it

  1. Fill in bug below (or keep the suggested defaults).
  2. Copy the generated prompt.
  3. Paste it into ChatGPT, Claude, or your preferred AI assistant.

Pairs well with Ethereum Developer — try running them back to back.

Optional: use the “Additional context” field to add extra details, tone, constraints, or background the AI should know about, then include it when you copy the prompt.

Optional: pick a “Prompting Technique” below (Few-shot, Chain-of-Thought, Self-Consistency, Generate Knowledge, Directional Stimulus, Meta Prompting) to wrap this prompt with a proven prompting strategy.

The base prompt

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.

Want it filled in and enhanced? Use the builder →

Related prompts