Santa Reviewer — Security agent for Claude Code
Use this agent for the Santa Method — an adversarial BREAKER + SIMPLIFIER + VERIFIER review that hunts REAL correctness/data-loss/security/concurrency bugs in a diff, then self-verifies each finding t.
How to install Santa Reviewer
Installs to ~/.claude/agents/ajayirkal23-agentic-mercy-10x-santa-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/AjayIrkal23/agentic-mercy-10x/HEAD/agents/santa-reviewer.md -o ~/.claude/agents/ajayirkal23-agentic-mercy-10x-santa-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What Santa Reviewer does
name: santa-reviewer description: "Use this agent for the Santa Method — an adversarial BREAKER + SIMPLIFIER + VERIFIER review that hunts REAL correctness/data-loss/security/concurrency bugs in a diff, then self-verifies each finding to kill false positives before reporting. It is the code-review specialist of the workflow: dispatch it after any non-trivial code change (it satisfies stop-gate Gate 4 / Santa), or on demand via /santa-review. It reports CONFIRMED must-fix findings (file:line +
Alternatives in Security
- Audit Verifier — Adversarially verifies one candidate finding from /bug-audit — tries to REFUTE it by reading the code and, whe 335 ★
- Threat Intel — PYA specialist spawned by the /pya orchestrator 240 ★
- Security Verifier — You write and execute PoC tests to PROVE bugs exist 215 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Fleet Review Deep
Frontier reviewer for very hard reviews. Use only when the user names it, when the change crosses a security o
Tier Opus
Subagent for a tier/opus issue — unclear root cause, cross-cutting refactors, concurrency/data-loss/security r
Delforge QA Breaker
Use for adversarial QA — actively trying to break an application to find bugs, edge cases, and security gaps i
AI Code Security Auditor
Security reviewer for AI-generated and vibe-coded apps — hunts the hardcoded secrets, broken row-level securit
Security AI Generated Code Auditor
Security reviewer for AI-generated and vibe-coded apps — hunts the hardcoded secrets, broken row-level securit
Plan Challenger
Adversarial plan review before implementation. Attacks plans across 5 dimensions (Assumptions, Missing Cases,
Related Skills
Kernel Ladder
Agent harness that writes and verifies GPU kernels. Claude proposes Triton kernels; a fixed verifier gates cor
Cmd Judge
Adversarial verifier for the PROVE phase: treats a finished-work report as untrusted claims, re-runs every ver
Page Implement
Per-page implementation pipeline. Executes a locked code plan, runs post-execution parallel critique (code-rev