pentest-agents-bug-bounty-framework — Claude Code skill: setup
A bug bounty testing setup for autonomous vulnerability discovery. It coordinates 50 specialized agents, connects findings into exploit chains, and tracks targets in a local brain.
npx skills add reason-machines/security-skills --skill pentest-agents-bug-bounty-framework -a claude-codeWhat pentest-agents-bug-bounty-framework does
This framework turns your coding assistant into an automated security hunter. It deploys 50 agents divided between coordinators (such as chain-builder or hunt-orchestrator) and specialized testers targeting SQLi, XSS, SSRF, or IDOR. The built-in brain tracks target endpoints persistently and combines isolated vulnerabilities into end-to-end exploit flows.
The tool ships with 26 slash commands, 19 CLI utilities, and 2 dedicated MCP servers. One server connects directly to platforms like HackerOne, Bugcrowd, and Intigriti to pull target scope and submit writeups. The other server looks up exploitation techniques across past bug reports using FAISS vector search, an SQLite database, or bundled payloads.
Platform integrations depend on explicit API credentials such as HACKERONE_TOKEN, and workspace scaffolding requires Python with uv. Running platform sync without these environment keys will immediately fail.
What it helps with
- Chain isolated findings into A→B multi-stage exploits
- Sync program scope directly from HackerOne or Bugcrowd
- Evaluate bugs against the 7-Question Gate checklist
- Search past writeup databases for vulnerability techniques
Example prompts for the agent
- Pull target scope with
/sync hackerone teslaand examine the attack surface - Validate the latest issue using
/validateand build a chain via/chain - Start an automated vulnerability loop for the target domain:
/autopilot tesla.com
How to install pentest-agents-bug-bounty-framework
1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill pentest-agents-bug-bounty-framework -a claude-code2Manually: put the files in place
~/.claude/skills/pentest-agents-bug-bounty-framework/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pentest-agents-bug-bounty-framework/
1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill pentest-agents-bug-bounty-framework -a codex2Manually: put the files in place
.agents/skills/pentest-agents-bug-bounty-framework/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill pentest-agents-bug-bounty-framework -a cursor2Manually: put the files in place
.cursor/skills/pentest-agents-bug-bounty-framework/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/security-skills pentest-agents-bug-bounty-framework2Manually: put the files in place
.github/skills/pentest-agents-bug-bounty-framework/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill pentest-agents-bug-bounty-framework -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/security-skills --path skills/pentest-agents-bug-bounty-frameworkManually: put the files in place
.devin/skills/pentest-agents-bug-bounty-framework/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill pentest-agents-bug-bounty-framework -a opencodeClaude.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 pentest-agents-bug-bounty-framework
How do I install pentest-agents-bug-bounty-framework in Claude Code?
Run npx skills add reason-machines/security-skills --skill pentest-agents-bug-bounty-framework -a claude-code. The skill file will be placed in ~/.claude/skills/pentest-agents-bug-bounty-framework/SKILL.md.
What does pentest-agents-bug-bounty-framework do?
It automates bug bounty workflows by orchestrating 50 specialized testing agents, organizing endpoint discoveries, and assembling multi-step exploit chains.
What are the search modes for the writeup server?
The writeup MCP server supports three modes: FAISS semantic search using embeddings, keyword matching via SQLite, and fallback search across local payload files.