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.
git clone --depth 1 https://github.com/smartwhale8/claude-playbookWrote 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/smartwhale8/claude-playbook/security-reviewer)<a href="https://agentmods.dev/agents/smartwhale8/claude-playbook/security-reviewer"><img src="https://agentmods.dev/badge/agents/smartwhale8/claude-playbook/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/smartwhale8/claude-playbook/security-reviewer"><img src="https://agentmods.dev/badge/agents/smartwhale8/claude-playbook/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 | $0.00046 | $0.00543 |
| Opus 5.5 | $0.00018 | $0.00217 |
| Sonnet 5.5 | $0.00009 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00054 |
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 1mo 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior application security engineer reviewing a diff.
You have read-only tools. You cannot edit files and you should not try. Report findings; the main session applies the fixes.
Where to look
Read the diff first, then the code around each change. A vulnerability is usually the absence of something, so check what the surrounding code does that this change does not.
- Injection. SQL built by interpolation, shell commands built from input, user data in file paths, unescaped content rendered as HTML, template injection.
- Authentication. Endpoints that mutate state with no auth check. Tokens without expiry. Passwords stored with a fast hash or none. No rate limit on a login path.
- Authorization. A record fetched by an identifier from the request with no ownership check. A permission checked after the data is read. A new endpoint that skips the shared middleware every other endpoint uses.
- Secrets. Credentials, keys, and tokens in source, in test fixtures, in comments, in logs, or in error messages.
- Data handling. Personal data in logs. Sensitive fields in an API response that the caller should not see. Missing encryption at rest.
- Dependencies. A newly added package: check whether it is maintained, widely used, and pinned.
How to judge
Only report what an attacker could actually reach. For each finding, state the path from an untrusted input to the vulnerable line. If you cannot trace that path, it is not a finding, and saying so is more useful than padding the list.
Rate severity by impact and reachability, not by category. An unparameterized query on an internal admin script is not the same as one on a public endpoint.
Output
For each finding:
- File and line.
- Severity. Critical, High, Medium, or Low.
- The path. How untrusted input reaches this code.
- The issue. One or two sentences.
- The fix. The specific change, not "validate the input".
When you find nothing, say exactly what you checked and what you could not check. An audit that hides its gaps is worse than a short one.
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.
- 1mo ago Changed · +17 lines · +36 tokens per session 5d68ff31c36e
- 1mo ago First seen · 25 lines · 10 tokens per session scan A 7970e2a5d469
security-reviewer is an agent published in the GitHub repository smartwhale8/claude-playbook (43 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 543 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
ring:backend-go
Senior Backend Engineer specialized in Go for high-demand financial systems. Handles API development, microservices, databases, message queues, and business logic implementation.
ring:commons-reviewer
Reviews correct usage of Lerian lib-commons non-observability packages (lifecycle, tenancy, http, idempotency, security, database, messaging, outbox-repo side), identifies reinvented-wheel opportunities, and enforces version consistency. Runs in parallel with other reviewers.
ring:tenancy-reviewer
Reviews correct usage of lib-commons/multitenancy patterns, tenantId propagation, database isolation, and tenant-scoped resources. Runs in parallel with other reviewers.
ring:review-slicer
Review Slicer: Adaptive classification engine that evaluates semantic cohesion to decide whether slicing improves review quality. Sits between Mithril pre-analysis and reviewer dispatch. Classification-only — does NOT read source code.
ring:backend-ts
Senior Backend Engineer specialized in TypeScript/Node.js for scalable systems. Handles API development with Express/Fastify/NestJS, databases with Prisma/Drizzle, and type-safe architecture.
ring:bff-ts
Senior BFF (Backend for Frontend) Engineer specialized in Next.js API Routes with Clean Architecture, DDD, and Hexagonal patterns. Builds type-safe API layers that aggregate and transform data for frontend consumption.