Team Reviewer — Security agent for Claude Code
Adversarial code review and verification.
How to install Team Reviewer
Installs to ~/.claude/agents/ccancellieri-mcp-skill-hub-team-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ccancellieri/mcp-skill-hub/HEAD/agents/team-reviewer.md -o ~/.claude/agents/ccancellieri-mcp-skill-hub-team-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Team Reviewer does
name: team-reviewer description: Adversarial code review and verification. Operates with a single lens per invocation (security, correctness, performance, or tests) passed in the prompt. Default posture is refute-by-default — actively tries to disprove that the change is correct. Reports only high-confidence findings with file:line and severity. Use after an implementation to stress-test it before merge. Examples — user: "Review the ingestion fix (PR #1857) through the correctness l
Alternatives in Security
- Aspm Correlator — Application Security Posture Management persona 548 ★
- Audit Verifier — Adversarially verifies one candidate finding from /bug-audit — tries to REFUTE it by reading the code and, whe 335 ★
- Security Verifier — You write and execute PoC tests to PROVE bugs exist 215 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Worker Review
Reviews an existing PR. Runs /review (plus /cso if security-adjacent); /codex review is opt-in (OFF by default
Finding Skeptic
Read-only adversarial verifier for audit findings. Given one finding and one skeptic lens, actively tries to r
Principle Auditor P3
Audit a target artifact through P3 (Hormozi Lens) ONLY. Member of an audit- team launched by /audit --team. Re
Yellow Lion
Quality and defense specialist (Yellow Lion). Writes tests, runs verification, reviews for security and correc
Cook Refute
jeff refute pass. Adversarially test exactly one blocking review, verification, or audit finding before it tri
Debate Prosecutor
L0.97 Adversarial Verification — reads diff + spec + test results, constructs the strongest-case argument that
Related Skills
Code Audit
Adversarial code review tree. Wraps /cc-tree:tree with the code-audit preset preselected — finds security / pe
Dotnet Review
Multi-agent .NET code review - up to five reviewers in parallel (correctness, performance, security/observabil
Job Hunt
A job and contract search you run as a loop: an AI-assistant skill plus a dependency-free local dashboard. Gui