Home › Prompts › Community › Test-Driven Bug Hunting With Reproduction Agents

Test-Driven Bug Hunting With Reproduction Agents

Any chat AI Agents & automation Community (CC0)

Community prompt, not a RuleStack original. Contributed by ilkerulusoy to prompts.chat (f/prompts.chat), file prompts.csv, released under CC0 1.0. Shown exactly as written; we filtered it for quality and safety but did not write or test it. Imported 2026-10-16 from commit 0abaca9.

Note: Review and test before use. Provided as is, without warranty. See Terms.

Prompt

Download

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.

How to use

Paste it into ChatGPT, Claude, Gemini, Grok or any other chat AI.
Replace the variables in ${…}, {…} or […] with your own details first.
Check the output before you rely on it.

More: all agents & automation prompts · all community prompts · prompt library

Related prompts

Design an automation workflow (n8n/Zapier/Make)

Turn a manual process into a step-by-step automation design with triggers, nodes, error handling and an LLM step prompt.

Any chat AIAgents & automation

ChatGPT agent: multi-step web task with checkpoints

A brief for ChatGPT's agent to research, compare and compile results on the web, pausing before any purchase or submission.

ChatGPTAgents & automation

Agentic coding task brief for Claude Code

A task brief for Claude Code that defines the goal, constraints, verification and stopping point so the agent works autonomously but safely.

ClaudeAgents & automation

Gemini automation across Gmail, Docs and Calendar

A request that has Gemini gather info from email and docs and produce a draft plan, without sending anything.

GeminiAgents & automation

Grok tool-using research agent prompt

A system prompt for a Grok agent that plans, searches, verifies and writes a cited brief, with a cap on tool calls.

GrokAgents & automation

Agent Organization Expert

Agent Organization Expert: --- name: agent-organization-expert description: Multi-agent orchestration skill for team assembly, task decomposition…

Any chat AIAgents & automationCommunity (CC0)

Get new rules weekly

One email a week: fresh rule files, agent tips, and what's changing in Cursor, Claude Code and Copilot. Free, unsubscribe anytime.

Opens the Rulestack Newsletter on beehiiv in a new tab. Or subscribe directly on beehiiv.