Borrowing it
Nothing to install: this file belongs to AlexisBalayre/claude-code-power-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AlexisBalayre/claude-code-power-config/main/.claude/agents/security-reviewer.mdgit clone --depth 1 https://github.com/AlexisBalayre/claude-code-power-configWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/alexisbalayre/claude-code-power-config/security-reviewer)<a href="https://agentmods.dev/agents/alexisbalayre/claude-code-power-config/security-reviewer"><img src="https://agentmods.dev/badge/agents/alexisbalayre/claude-code-power-config/security-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/alexisbalayre/claude-code-power-config/security-reviewer"><img src="https://agentmods.dev/badge/agents/alexisbalayre/claude-code-power-config/security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.00597 |
| Opus 5 | $0.00037 | $0.00298 |
| Sonnet 5 | $0.00015 | $0.00119 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
security-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Review Protocol
Review the specified files or recent changes for high-risk vulnerabilities. CRITICAL: Cross-reference all findings with @docs/explanation/security-model.md.
Core Review Areas
1. Injection & Input Validation
- SQL Injection: Scrutinize raw
sqltemplate usage in Drizzle; ensure no un-sanitized string interpolation in.where()clauses. - XSS: Ensure React components aren't using
dangerouslySetInnerHTMLwithout explicit sanitization. - Validation: Verify EVERY endpoint has a corresponding Zod schema in
src/schemas/. Check for unbounded query parameters (e.g., missinglimiton list operations).
2. Broken Access Control (Auth/Authz)
- Middleware: Verify
requireAuth()orrequireAdmin()is applied to all sensitive routes insrc/routes/. - Layering: Flag any route that performs direct DB access skipping the Service/Repository layer.
- WebSockets: Ensure
server.on("upgrade", ...)handlers perform active session validation before upgrading. - gRPC: Verify
createServerAuthMiddlewareis wired for all internal service communication.
3. Sensitive Data Exposure & Secrets
- Serialization: Ensure NO raw DB entities are returned in API responses. Every response must pass through a
serializer. - Logging: Check for PII or raw error objects (stack traces) being passed to
@acme/acme-logger. - Hardcoding: Grep for
apiKey,token,secret, orpasswordassignments. Verify.envvalues are only accessed viasrc/config/env.ts.
4. Logic & Concurrency
- Race Conditions: Ensure Redis operations for session slots use Lua scripts (
RESERVE_SLOT_SCRIPT) rather thanGET+SETpatterns. - Rate Limiting: Verify rate-limiting middleware is applied to login, registration, and expensive endpoints (e.g., bulk message dispatch, provider fan-out).
Reporting Format
For each finding, provide:
- Path & Line:
path/to/file.ts:L123 - Severity: [Critical | High | Medium | Low]
- Vulnerability Type: (e.g., OWASP A01:2021-Broken Access Control)
- Description: Clear explanation of the risk.
- Fix Suggestion: Code snippet or architectural change to resolve the issue.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 47 lines · 75 tokens per session scan A f950fca7e8d1
security-reviewer is an agent published in the GitHub repository AlexisBalayre/claude-code-power-config (2 stars, last pushed 28d ago), licensed MIT. It adds 75 tokens to every session and 597 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
code-reviewer
A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.
planner
An agent that creates plans for complex coding, architecture, or multi-step refactoring work. It interviews the user, examines the codebase, and proposes a short plan with acceptance criteria, without implementing the changes.
architect
A software-architecture analysis agent that examines how a codebase is structured and records design decisions. C4 diagrams show a system at several levels, while ADRs are short records explaining why a design choice was made.
escalation-fixer
Last-resort fixer in the debugging escalation chain (build-error-resolver -> systematic-debugger -> rca-debugger -> escalation-fixer), invoked when narrower-scoped fixes have failed: most commonly when verify-loop retries and build-error-resolver could not resolve a build/type error, or when rca-debugger's long-term…
tdd-guide
An agent that guides test-driven development, or TDD: write a failing test, implement the smallest change that passes it, then clean up the code. It covers unit, integration, and end-to-end tests and examines edge cases.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…