starred/bug-hunt
1
0
Fork 0
mirror of https://github.com/danpeg/bug-hunt.git synced 2026-04-26 14:05:52 +03:00
Code Issues 1 Projects Releases Packages Wiki Activity
Adversarial bug hunting skill for Claude Code. 3 isolated agents (Hunter, Skeptic, Referee) find and verify real bugs.
16 commits 2 branches 0 tags 84 KiB
Find a file
Exact
Dan Peguine 5614e19e2b
 Merge pull request #4 from bheemreddy-samsara/docs/add-branch-diff-mode-to-readme
2026-03-05 20:31:46 +00:00
.github docs: add contributor infrastructure 2026-03-05 16:20:44 +00:00
prompts feat: add adversarial bug hunting skill for Claude Code 2026-03-05 10:08:38 +00:00
.gitignore docs: add contributor infrastructure 2026-03-05 16:20:44 +00:00
CHANGELOG.md docs: add changelog tracking project history 2026-03-05 18:40:01 +00:00
CODE_OF_CONDUCT.md docs: add contributor infrastructure 2026-03-05 16:20:44 +00:00
CONTRIBUTING.md docs: add contributor infrastructure 2026-03-05 16:20:44 +00:00
LICENSE feat: add adversarial bug hunting skill for Claude Code 2026-03-05 10:08:38 +00:00
README.md docs: Add branch diff mode to README usage section 2026-03-05 12:44:45 -06:00
SKILL.md feat: add branch diff mode for targeted bug hunting 2026-03-05 10:18:50 -06:00

README.md

image

/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:

  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

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

Claude Code auto-discovers skills in ~/.claude/skills/.

Usage

/bug-hunt                              # Scan entire project
/bug-hunt src/                         # Scan specific directory
/bug-hunt lib/auth.ts                  # Scan specific file
/bug-hunt -b feature-xyz              # Scan files changed in feature-xyz vs main
/bug-hunt -b feature-xyz --base dev   # Scan files changed in feature-xyz vs dev

Branch diff mode (-b) scans only files changed in a branch compared to a base branch (defaults to main). It reads the full file contents — not just the diff — so bug detection quality is preserved.

Update

cd ~/.claude/skills/bug-hunt && git pull

Uninstall

rm -rf ~/.claude/skills/bug-hunt

How the scoring works

The scoring incentives are load-bearing — they exploit each agent's desire to maximize its score:

  • Hunter: +1/+5/+10 for low/medium/critical bugs. Motivates thoroughness.
  • Skeptic: Earns points for disproving false positives, but pays 2x penalty for wrongly dismissing real bugs. Creates calibrated caution.
  • Referee: Symmetric +1/-1 scoring with "ground truth" framing. Makes it precise rather than biased.

Attribution

Based on the adversarial bug hunting technique described by @systematicls in "How To Be A World-Class Agentic Engineer."

Brand by Kitt at Curious Endeavor

Contributing

Contributions welcome! See CONTRIBUTING.md for guidelines.

License

License: MIT

MIT