bounty-deep-hunt — Claude Code skill for bug hunting
The bounty-deep-hunt Claude Code skill pushes bug bounty work past routine checks and into less obvious vulnerability paths. It tracks tests until a finding is verified or the evidence-backed ledger is complete.
LicenseRef-Proprietary ★ 326 updated 2026-11-01
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill bounty-deep-hunt -a claude-codeWhat bounty-deep-hunt does
The skill guides an agent through hunting for less obvious flaws on a live target. It discourages ending with an empty result and instead directs attention to artifacts, connections between components, and fresh ways to test a surface.
A ledger tracks each test. The session ends with a working proof of concept or a complete record of tested and blocked items, each backed by evidence. A finding needs at least two successful reproductions. The skill activates during live-target bug bounty work or when a web-pentest run is about to stop without a result.
What it helps with
- continue a hunt after routine checks find nothing
- track untested areas of a target
- connect small findings into a larger attack path
- verify a vulnerability with a reproducible PoC
Example prompts for the agent
- Continue the bug bounty assessment of this live target and record each test.
- After the web pentest, explore other ways to test the same surfaces.
- Review the small findings and check whether they form a chain.
How to install bounty-deep-hunt
1Skills CLI (Vercel)
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill bounty-deep-hunt -a claude-code2Manually: put the files in place
~/.claude/skills/bounty-deep-hunt/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/bounty-deep-hunt/
1Skills CLI (Vercel)
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill bounty-deep-hunt -a codex2Manually: put the files in place
.agents/skills/bounty-deep-hunt/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill bounty-deep-hunt -a cursor2Manually: put the files in place
.cursor/skills/bounty-deep-hunt/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install mrhlaingbwardev/agentic-hacking-skills skills/bounty-deep-hunt2Manually: put the files in place
.github/skills/bounty-deep-hunt/SKILL.md1Skills CLI (Vercel)
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill bounty-deep-hunt -a gemini-cli2Platform CLI
gemini skills install https://github.com/mrhlaingbwardev/agentic-hacking-skills --path skills/bounty-deep-huntManually: put the files in place
.devin/skills/bounty-deep-hunt/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about bounty-deep-hunt
How do I install bounty-deep-hunt in Claude Code?
Run npx skills add mrhlaingbwardev/agentic-hacking-skills --skill bounty-deep-hunt -a claude-code. The skill file is placed at ~/.claude/skills/bounty-deep-hunt/SKILL.md.
What does bounty-deep-hunt do?
It helps an agent look beyond routine bug bounty checks and keep a record of tests instead of stopping at an empty result. It is triggered for live-target hunting or when a web-pentest run is about to end without findings.
What counts as a finished hunt?
The session must end with a working PoC or a complete ledger of tested and blocked items, with evidence for each. A finding must be reproduced at least twice.