by danpeg · Claude Skill · ★ 101
/bug-hunt Adversarial bug finding skill for Claude Code. Uses 3 isolated AI agents to find and verify real bugs with high fidelity. How it works Inspired by @systematicls's article) on exploiting LLM sycophancy for better code review: Hunter - Scans your code and reports every possible bug (biased to over-report) Skeptic - Tries to disprove each bug (biased to dismiss false positives) 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.
| Stars | 101 |
| Forks | 9 |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 66.9212615750295/100 |
| Open Issues | 1 |
| Last Updated | 2026-03-05 |
| Created | 2026-03-05 |
| Platforms | claude-code |
| Est. Tokens | ~3k |
Explore other popular claude skill tools:
bug-hunt is Adversarial bug hunting skill for Claude Code. 3 isolated agents (Hunter, Skeptic, Referee) find and verify real bugs.. It is categorized as a Claude Skill with 101 GitHub stars.
You can find installation instructions and usage details in the bug-hunt GitHub repository at github.com/danpeg/bug-hunt. The project has 101 stars and 9 forks, indicating an active community.
bug-hunt is released under the MIT license, making it free to use and modify according to the license terms.