Reviewer Security Max — Security agent for Claude Code
Security reviewer for one change set, max effort — used when the classifier flags touches_auth.
How to install Reviewer Security Max
Installs to ~/.claude/agents/blazej-bryla-ai-coding-setup-reviewer-security-max.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/blazej-bryla/ai-coding-setup/HEAD/agents/reviewer-security-max.md -o ~/.claude/agents/blazej-bryla-ai-coding-setup-reviewer-security-max.md Restart Claude Code, or start a new session, for it to be picked up.
What Reviewer Security Max does
name: reviewer-security-max description: Security reviewer for one change set, max effort — used when the classifier flags touches_auth. Spawned by deep-review (and its Reuse callers /work, /implement, /bugfix); not for general use. model: opus effort: max disallowedTools: NotebookEdit
Read `~/.agents/skills/deep-review/prompts/security.md` and follow it exactly — it is your full instructions. The context block it refers to is the prompt you were spawned with. Do not change code in the
Alternatives in Security
- Security Hardening — Implement comprehensive security hardening with defense-in-depth strategy through coordinated multi 31.9k ★
- General Technical Project Lead — Use this agent proactively when you need principal-level technical leadership for complex projects, performanc 248 ★
- Electron Ipc Engineer — Use this agent for any change that touches Electron IPC — adding/removing channels, modifying main.ts ↔ preloa 204 ★
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
Claudehut Security Auditor
Spring-security review of the diff — authn/authz, filter chain, injection, secrets, deserialization, data expo
Sub Agent Security Reviewer
Security gate for the inner loop (G5). Use ONLY when the change touches auth, external input boundaries, SQL/O
Hipaa Reviewer
Read-only reviewer that checks code against HIPAA Security Rule technical safeguards (access control, audit lo
St Worker Xhigh
Strikethroo task-execution worker at the XHIGH reasoning-effort tier. Reserved for the hardest, highest-risk t
Executor Opus Xhigh
Ticket executor for tickets where judgment is the work — money, capacity, stored enums, migrations with a corr
Related Skills
Claude Code Config Dir Patcher VSCode
This VS Code extension lets you run multiple Claude Code accounts by patching Anthropic's anthropic.claude-cod
Diff Audit
PR / commit-scoped differential audit — audits only changed functions (plus 1-hop callers), flags removed secu
Scope Creep Detector
Reads a PRD, spec, or project brief line by line and flags every sentence that will cause scope creep. Identif