Not in the top 1,000 by GitHub stars
danpeg/bug-hunt
Adversarial bug hunting skill for Claude Code. 3 isolated agents (Hunter, Skeptic, Referee) find and verify real bugs.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
5614e19e2bb1 → 5614e19e2bb1
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5614e19e2bb1
No earlier version was observed for comparison.
146GitHub stars
0stars in 7 days
1skill in this repository
0commits in 30 days
Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- bug-hunt
/
How it works
bug-hunt
When your agent uses it
Run adversarial bug hunting on your codebase. Uses 3 isolated agents (Hunter, Skeptic, Referee) to find and verify real bugs with high fidelity. Invoke with /bug-hunt, /bug-hunt [path], or /bug-hunt -b <branch> [--base <base>].
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
946 tokensWhen the skill is activated
Reference documents
2,898 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Usage
- Target
- Execution Steps
Files
.github/ISSUE_TEMPLATE/bug_report.mddoc459 bytes.github/ISSUE_TEMPLATE/feature_request.mddoc369 bytes.github/PULL_REQUEST_TEMPLATE.mddoc237 bytes.gitignoreasset57 bytesCHANGELOG.mddoc440 bytesCODE_OF_CONDUCT.mddoc1,127 bytesCONTRIBUTING.mddoc1,174 bytesLICENSEasset1,068 bytesREADME.mddoc2,702 bytesSKILL.mdcore3,872 bytesprompts/hunter.mddoc1,738 bytesprompts/referee.mddoc2,147 bytesprompts/skeptic.mddoc1,838 bytes
Read SKILL.md
# Bug Hunt - Adversarial Bug Finding
Run a 3-agent adversarial bug hunt on your codebase. Each agent runs in isolation.
## 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
```
Skills included
- bug-hunt
Repository facts
- License
- MIT
- Created
- Mar 5, 2026
- Last pushed
- Mar 5, 2026
- Forks
- 12
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
- No broad tool permissions
- 1 dangerous shell commandin 1 file: README.md:46
- 10 network referencesin 3 files: README.md:1 CONTRIBUTING.md:16 CODE_OF_CONDUCT.md:29
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 1 reference to secretsin 1 file: .gitignore:5
- No requests to vote in Hot
Show all 12 signals by file
.gitignore
- Access to secretsline 5
[Credential-related source omitted]
CODE_OF_CONDUCT.md
- Network accessline 29
This Code of Conduct is adapted from the [Contributor Covenant](https://www.contributor-covenant.org/), version 2.1.
CONTRIBUTING.md
README.md
- Network accessline 1
<img width="1280" height="480" alt="image" src="https://github.com/user-attachments/assets/8432d699-b4bb-4049-afcc-d2430ac1b58e" /> - Network accessline 5
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. - Network accessline 9
Inspired by [@systematicls's article]([https://x.com/systematicls](https://x.com/systematicls/status/2028814227004395561)) on exploiting LLM sycophancy for better code review: - Network accessline 20
git clone https://github.com/danpeg/bug-hunt.git ~/.claude/skills/bug-hunt - Dangerous shell operationline 46
rm -rf ~/.claude/skills/bug-hunt - Network accessline 59
Based on the adversarial bug hunting technique described by [@systematicls](https://x.com/systematicls) in "How To Be A World-Class Agentic Engineer." - Network accessline 61
Brand by [Kitt](https://x.com/Kitt_Curious) at [Curious Endeavor](https://curiousendeavor.com/) - Network accessline 69
[](LICENSE)
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 11 facts
- Network access in prose of documentationCODE_OF_CONDUCT.md:29Low confidence
- Network access in code of documentationCONTRIBUTING.md:16Low confidence
- Network access in prose of documentationCONTRIBUTING.md:33Low confidence
- Network access in prose of documentationREADME.md:1Low confidence
- Network access in prose of documentationREADME.md:5Low confidence
- Network access in prose of documentationREADME.md:9Low confidence
- Network access in code of documentationREADME.md:20Low confidence
- Dangerous shell operation in code of documentationREADME.md:46Low confidence
- Network access in prose of documentationREADME.md:59Low confidence
- Network access in prose of documentationREADME.md:61Low confidence
- Network access in prose of documentationREADME.md:69Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Frontmatter field disable-model-invocation in SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
