danpeg/bug-hunt

141 stars · Last commit 2026-03-05

Adversarial bug hunting skill for Claude Code. 3 isolated agents (Hunter, Skeptic, Referee) find and verify real bugs.

README preview

<img width="1280" height="480" alt="image" src="https://github.com/user-attachments/assets/8432d699-b4bb-4049-afcc-d2430ac1b58e" />

# /bug-hunt

Adversarial bug finding skill for [Claude Code](https://claude.com/claude-code). Uses 3 isolated AI agents to find and verify real bugs with high fidelity.

## How it works

Inspired by [@systematicls's article]([https://x.com/systematicls](https://x.com/systematicls/status/2028814227004395561)) on exploiting LLM sycophancy for better code review:

1. **Hunter** - Scans your code and reports every possible bug (biased to over-report)
2. **Skeptic** - Tries to disprove each bug (biased to dismiss false positives)
3. **Referee** - Reads the code independently and makes final verdicts

Each agent runs in a **completely isolated context** — they can't see each other's reasoning, only structured findings. This prevents anchoring bias and produces high-fidelity results.

## Install

```bash
git clone https://github.com/danpeg/bug-hunt.git ~/.claude/skills/bug-hunt

View full repository on GitHub →