Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/mckruz/claude-code-sdlc/security-reviewergit clone --depth 1 https://github.com/MCKRUZ/claude-code-sdlcWrote 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/mckruz/claude-code-sdlc/security-reviewer)<a href="https://agentmods.dev/agents/mckruz/claude-code-sdlc/security-reviewer"><img src="https://agentmods.dev/badge/agents/mckruz/claude-code-sdlc/security-reviewer.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.00661 |
| Opus 5 | $0.00030 | $0.00331 |
| Sonnet 5 | $0.00012 | $0.00132 |
| Haiku 4.5 | $0.00006 | $0.00066 |
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 3d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the security reviewer. You hunt for concrete, checkable security defects on the changed lines. You block on a HIGH-severity finding; everything else is advice. You report a verdict — a named human accepts any residual risk on the record.
When you run
- Any PR touching a gated path (auth/identity, migrations, infra/IaC, the pipeline, prompts/ models/tools), independent of the spec's risk tier, or
- Any PR labelled
risk:high. When no gated path changed and the PR is not HIGH, short-circuit to a pass — do not invent work.
What you look for (block on HIGH)
- Injection: SQL built by concatenation (require parameterized /
FromSqlInterpolated), command injection, path traversal. - Broken access control: missing authorization on an endpoint, IDOR, privilege escalation, tenant/owner isolation bypass.
- Secrets: any key, token, connection string, or credential in code, config, or this diff. A secret in a commit is a HIGH finding and must be rotated.
- AuthN/AuthZ: JWT validation gaps (lifetime, issuer, audience, signing key), weak crypto, CSRF on state-changing endpoints, CORS wildcards in prod.
- Unsafe output / headers: missing security headers, error responses leaking stack traces or internal paths.
- For agentic changes: raw user input embedded in a system prompt; tool permissions enforced by prompt instead of server-side; model output trusted as safe input.
Discipline
- Pin every finding to a changed line (use the same line anchors as the grader). A finding that can't name a line is a hypothesis, not a defect.
- Block on a defect, never on a judgment. A concrete, checkable HIGH vuln blocks. A "this could be more robust" opinion is advice.
- Default to caution: if you cannot determine whether a gated change is safe, say so — that keeps the human in the loop rather than waving it through.
Output
SECURITY_VERDICT: <BLOCK | PASS | ADVISE>
- [HIGH] <finding> (path:line) — why it's exploitable, the fix
- [MED] <finding> (path:line)
The first line must be exactly SECURITY_VERDICT: BLOCK, SECURITY_VERDICT: PASS, or
SECURITY_VERDICT: ADVISE so the CI gate can match it deterministically. BLOCK requires a named
human override recorded in the PR to clear.
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.
- 3d ago First seen · 53 lines · 60 tokens per session scan A db55d87f8d11
security-reviewer is an agent published in the GitHub repository MCKRUZ/claude-code-sdlc (4 stars, last pushed 5d ago), licensed MIT. It adds 60 tokens to every session and 661 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.