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 skills add kochetkov-ma/claude-brewcode --skill brewcode-reviewgit clone --depth 1 https://github.com/kochetkov-ma/claude-brewcodeWrote 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/skills/kochetkov-ma/claude-brewcode/brewcode-review)<a href="https://agentmods.dev/skills/kochetkov-ma/claude-brewcode/brewcode-review"><img src="https://agentmods.dev/badge/skills/kochetkov-ma/claude-brewcode/brewcode-review/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/skills/kochetkov-ma/claude-brewcode/brewcode-review"><img src="https://agentmods.dev/badge/skills/kochetkov-ma/claude-brewcode/brewcode-review.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 | $0.00031 | $0.00339 |
| Opus 5.5 | $0.00012 | $0.00136 |
| Sonnet 5.5 | $0.00006 | $0.00068 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
brewcode-review 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 13d 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
Brewcode review
Apply superreview and its review contract, keeping the user's explicit product/path/revision boundary. This adapter adds product checks; it does not duplicate the review engine, apply fixes, or update review instructions.
Read live root/nested AGENTS.md, referenced rules, manifests, producer templates, compatibility generators, and existing validation/test entrypoints for the selected product. Treat Claude-facing source as a review subject/evidence when requested, never as the Codex runtime instruction contract.
Check relevant surfaces: hook event/schema and JSON output; ESM/async/error handling; shell interpreter/platform assumptions; skill metadata and usable procedures; native agent TOML versus product Markdown formats; placeholders and generated-versus-canonical lineage; compatibility/install/update preservation; pinned dependencies and actual release/version contracts. Derive requirements from current sources rather than stale fixed counts, plugin versions, role names, or copied flag tables.
Review producer-shaped data through the integrated consumer where feasible. Verify generated parity using existing non-mutating checks or an isolated workspace; never regenerate live files during review. Include ignored instruction targets when explicitly requested. Search existing reusable implementations before suggesting new abstractions.
Honor explicit quorum or critic requests as independent perspectives within available resources; evidence and counterexample validation decide findings, never majority voting. Report one validated product review with coverage, actual checks, unresolved findings, and scope limitations through superreview's report contract.
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.
- 13d ago First seen · 17 lines · 31 tokens per session scan A 2d51d6c9b8c7
brewcode-review is a skill published in the GitHub repository kochetkov-ma/claude-brewcode (32 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 339 once invoked, about $0.0001 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 2026-10-01.
Other skills, from other repositories
review
Code review with semantic diffs, expert routing, and auto-TaskCreate. Triggers on: code review, review changes, check code, review PR, security audit.
structural-search
Search code by AST structure using ast-grep. Find semantic patterns like function calls, imports, class definitions instead of text patterns. Triggers on: find all calls to X, search for pattern, refactor usages, find where function is used, structural search, ast-grep, sg.
rubber-ducky
Use when you've planned a non-trivial change and are about to implement it, finished a complex or multi-file piece of work, just wrote tests, or are stuck on repeated failures — and any time the user says "rubber duck this", "rubber ducky", "get a second opinion", "sanity-check my plan", "poke holes in this", "what am…
pr-sweep
Use when you want to sweep all open pull requests across all repos, triage their status, run code reviews on unreviewed PRs, merge what's ready, fix quick blockers, and produce a full status report. Trigger when the user says "check my PRs", "close out open PRs", "what's the status of my PRs", "sweep my PRs", "PR…
review
Use when user invokes /review to review code changes. Also triggers on "review my code", "check this PR", "look at my changes". Accepts a PR number (e.g. /review 123), a path filter (e.g. /review src/auth/), or no argument (reviews current branch vs base). Produces structured per-file review with severity labels…
open-pr
Use when wrapping up a development task and getting a PR ready — runs local tests, creates a PR (if one doesn't exist) with a structured description template, conducts a code review via the review skill, and checks CI status with quick fixes. Trigger when the user says they're done with a feature, want to open a PR…