security-review plugins

by river-review maintainers

Turn review into an organizational judgment asset. Review Judgment as Code for AI-assisted development, delivered as a capability pack for Codex: your team's review criteria as versioned, repo-owned skills (a Skill Registry), driven by a review agent that runs perspective-based reviewer roles (code, security, performance, architecture, testing, adversarial) and verifies findings against the diff so humans keep the high-risk judgment.

by Wildcat Labs

Evidence-preserving budgets for engineering prose.

by river-review maintainers

Turn review into an organizational judgment asset. Review Judgment as Code for AI-assisted development, delivered as a capability pack for Codex: your team's review criteria as versioned, repo-owned skills (a Skill Registry), driven by a review agent that runs perspective-based reviewer roles (code, security, performance, architecture, testing, adversarial) and verifies findings against the diff so humans keep the high-risk judgment.

by NecturaLabs

Five Agent Skills for coding agents: instruction-file maintenance, independent code review, security review, test engineering, and project documentation.

by David Dunnock

Deep test, analyze, and audit Claude skills. Use this skill whenever the user wants to test a skill's behavior, analyze how it uses the Claude API, inspect inputs/outputs from scripts, or run security and code review audits against skill scripts. Trigger on: "test my skill", "analyze this skill", "audit skill scripts", "review skill for security issues", "what does this skill actually do when it runs", "inspect API calls from skill", "run a skill through its paces", "check my skill for bugs or vulnerabilities". Also trigger when the user shows you a SKILL.md and asks you to evaluate, critique, or stress-test it.

by AgentReview

AgentAutoReview — AI 앱 보안 리뷰 워크플로 스킬 7종 + 리모트 MCP(aar-mcp). /aar_review(적용 시나리오 전수 실증) · /aar_update(주간 SaaS 추적, 트리·보고서 델타 갱신) · /aar_fix(대화에서 배운 걸 규범에 반영) · /aar_explain(리뷰 결과를 큰그림·적은글씨 HTML 아티팩트로) · /aar_menu(원천 트리 항목 하나만 조사해 그 노드에 보고서를 붙임) · /aar_menutoy(SaaS 웹 메뉴를 크롤러 코드로 재현·git 이력, 주간) · /aar_sensing(Agent Auto Sensing 랭킹 세션을 가져와 리뷰하고 카드마다 완료 표시, 매주). 리뷰 발행 직전 독립 검증 서브에이전트 aar-reviewer(대상 드리프트·tier 귀속 정직성·커버리지·증거 게이트)와 대전제 감사 aar-compounder. 스킬은 한 트리(skills/)에서만 관리하고 MCP `skill('get', …)` 로 원문을 받아 쓴다. 도구는 서버측 자동 업데이트.