Phase 2 of the pentest pipeline — map the live attack surface from the pre-recon baseline. Invoked by pentest-orchestrator.
How this skill is triggered — by the user, by Claude, or both
Slash command
/shannon-for-claude-code:reconThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Combine `01-pre-recon.md` with light live probing of `url` (only after the
Combine 01-pre-recon.md with light live probing of url (only after the
orchestrator's authorization gate passed).
02-recon.md — narrative of endpoints, parameters, auth/session flows,
roles, and which pre-recon leads were confirmed reachable.attack-surface.json:{
"endpoints": [
{ "method": "POST", "path": "/login", "params": ["email","password"],
"auth": "none", "notes": "" }
],
"authFlows": [],
"roles": []
}
Keep live requests minimal and non-destructive (GET/OPTIONS, no payloads).
Write both files into pentest-workspace/<run-id>/.
Provides a checklist for code reviews covering functionality, security, performance, maintainability, tests, and quality. Use for pull requests, audits, team standards, and developer training.
npx claudepluginhub gamblerix2/shannonforclaudecode