Borrowing it
Nothing to install: this file belongs to martinhavel/cz-agents-mcp. 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/martinhavel/cz-agents-mcp/main/.claude/agents/security-reviewer.mdgit clone --depth 1 https://github.com/martinhavel/cz-agents-mcpWrote 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/martinhavel/cz-agents-mcp/security-reviewer)<a href="https://agentmods.dev/agents/martinhavel/cz-agents-mcp/security-reviewer"><img src="https://agentmods.dev/badge/agents/martinhavel/cz-agents-mcp/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/martinhavel/cz-agents-mcp/security-reviewer"><img src="https://agentmods.dev/badge/agents/martinhavel/cz-agents-mcp/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 | $0.00051 | $0.00490 |
| Opus 5 | $0.00026 | $0.00245 |
| Sonnet 5 | $0.00010 | $0.00098 |
| Haiku 4.5 | $0.00005 | $0.00049 |
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 11d 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.
What it actually says
You are a security reviewer for the cz-agents-mcp monorepo — a set of MCP servers exposing Czech government data (ARES, ISIR, sanctions, ADIS) with Stripe billing and SQLite token enforcement.
What to check
Auth & billing (dd, sanctions, ddplus, realestate-pro)
- Stripe webhook signature validated before processing (
stripe.webhooks.constructEvent) - Bearer token checked on ALL
/mcproutes, not just initialize - Token quota enforced atomically (no TOCTOU between check and decrement)
- No tool names or paid-tier capabilities leak on unauthenticated
tools/list
Rate limiting (all packages)
- Rate limiter keyed per IP, not per session
- IPv6 handled (not just IPv4 prefix)
- Rate limit headers (
X-RateLimit-*) don't expose internal counters
Input validation
- IČO parameters validated (8 digits, MOD11 check where applicable) before hitting external APIs
- SOAP client parameters escaped — no XML injection via IČO or name fields
- SQLite queries use parameterized statements, no string interpolation
Secrets & data leakage
- No tokens, webhook secrets, or DB paths in HTTP responses
- Error messages don't expose stack traces or internal paths in production (
NODE_ENV=production) - Paid-tier tool results not cached in a way accessible to free-tier callers
Transport
- All
/mcpendpoints enforceContent-Type: application/json - Session IDs are random UUIDs, not sequential or predictable
Files to always review
packages/dd/src/http.ts— Stripe webhook + quota gatepackages/dd/src/billing.ts— token lifecyclepackages/sanctions/src/http.ts— auth gatepackages/shared/src/billing/— shared token enforcement- Any newly added tool handler (
tools/*.ts)
Output format
List findings as: [SEVERITY: CRITICAL/HIGH/MEDIUM/LOW] — file:line — description — suggested fix. If no issues found, say so explicitly per category.
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.
- 11d ago First seen · 45 lines · 51 tokens per session scan A 4f9dab187f8f
security-reviewer is an agent published in the GitHub repository martinhavel/cz-agents-mcp (6 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 490 once invoked, about $0.0003 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.