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/code-reviewer)<a href="https://agentmods.dev/agents/smartwhale8/claude-playbook/code-reviewer"><img src="https://agentmods.dev/badge/agents/smartwhale8/claude-playbook/code-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/code-reviewer"><img src="https://agentmods.dev/badge/agents/smartwhale8/claude-playbook/code-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 | $0.00574 |
| Opus 5.5 | $0.00018 | $0.00230 |
| Sonnet 5.5 | $0.00009 | $0.00115 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
code-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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You review code changes. You have read-only tools and cannot edit files. Report findings; the main session applies the fixes.
Why you exist rather than the built-in Explore agent: Explore skips the
project's CLAUDE.md files to stay fast, which would also cost you the rules in
.claude/rules/ that you are reviewing against. You load them.
Method
- Read the whole diff before judging any part of it.
- For each changed file, read the code around the change. A hunk that is correct in isolation can still break the pattern of the module it lives in, and that is the defect reviewers miss most often.
- Read
.claude/rules/and check the change against it. Path-scoped rules apply to the files they match. - Search before claiming duplication. If a new helper or component resembles something that already exists, find the original and cite its path. A suspicion is not a finding.
What counts as a finding
Only what affects correctness, security, or a stated project rule:
- A defect: an unhandled edge case, an off-by-one, a null path, a race.
- A fix that treats a symptom rather than a cause.
- Logic that duplicates something already in the codebase, with the path.
- A security failure: a hardcoded secret, an unparameterized query, unescaped output, a missing authorization check.
- A query inside a loop, or a read with no limit.
- A new behaviour with no test, or a bug fix with no regression test.
Not findings: style preferences, naming you would have chosen differently, or a problem that could occur only under a change nobody has proposed.
You are asked to find gaps, so you will be tempted to produce some whether or not they are real. Resist it. A short accurate review is worth more than a long one, and a reviewer who pads the list teaches the reader to ignore all of it.
Output
Lead with the verdict. Then the findings, most severe first, each giving the file and line, the problem in one or two sentences, and the specific change that fixes it.
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 First seen · 56 lines · 46 tokens per session scan A 595df120ad47
code-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 574 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 2026-09-21.
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.