Topic
Security
Codebase audit preparation and repository-grounded threat modeling.
5 skills · 5 with a full profile. Subareas: Security review · Code review.
Agent
5 skills
Security review
- 01audit-context-buildingReads a codebase function by function, records what each one assumes and depends on, and writes the results to files instead of filling up the conversation — built for pre-audit codebase understanding.Claude CodeCursor— portableVendor Trail of Bits trailofbits/skills
- 02security-threat-modelProduces a repository-grounded threat model — trust boundaries, assets, attacker capabilities, abuse paths, mitigations — written to a markdown file. Roughly half its description is negative triggers.CodexOfficial OpenAI openai/skills
- 03thermosRuns two parallel Cursor subagents — a deep correctness/security audit and a strict maintainability rubric — and synthesizes both into one prioritized branch review.CursorOfficial Cursor cursor/plugins
Code review
- 01Cursor's built-in review skills/review, /review-bugbot, and /review-security ship with Cursor by default — general review, automated bug-hunting review, and a security-focused review, with nothing to install.CursorOfficial Cursor Cursor — Agent Skills (official docs)
- 02parallel-code-reviewRuns four read-only subagents in parallel — security, performance, correctness, readability — and merges the results into one prioritized review.CursorCommunity spencerpauly spencerpauly/awesome-cursor-skills
Not sure which?
Describe the outcome instead.
AgentSkills Doctor takes a goal in plain language and an agent, and recommends a small stack from this site’s inspected skills — no browsing required.