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 superreviewgit 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/superreview)<a href="https://agentmods.dev/skills/kochetkov-ma/claude-brewcode/superreview"><img src="https://agentmods.dev/badge/skills/kochetkov-ma/claude-brewcode/superreview/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/superreview"><img src="https://agentmods.dev/badge/skills/kochetkov-ma/claude-brewcode/superreview.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 | $0.00035 | $0.00427 |
| Opus 5.5 | $0.00014 | $0.00171 |
| Sonnet 5.5 | $0.00007 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
superreview 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
Superreview
Use the native Codex review workflow in references/review-contract.md. This skill authorizes review and report artifacts only: never edit reviewed code, instructions, agents, skills, or configuration, including this skill itself. Suggest corrections separately.
Resolve the requested scope before work. Explicit paths, exclusions, revisions, and user narrowing win. Default to staged + unstaged + untracked changes; with a clean tree review the last two commits, falling back to one or the root commit. QUICK is the default; requests for depth, completeness, pre-merge, or release review select EXTENDED. Depth changes effort, never scope or mutation authority. Announce the concrete scope, depth, baseline, checks, and expected report in English.
Read applicable AGENTS.md instructions and their referenced rules explicitly; .codex/rules/ and paths: metadata do not load rules automatically. Reuse project check commands and live native reviewer roles. Parse agent TOML as TOML, not YAML; availability comes from the current runtime. Do not create agents or require an intent-guard role.
Review in order: simplification/reuse assessment, correctness/safety, then maintainability/clarity. Simplification is a report pass, not permission to run a mutating simplify workflow. At both depths compare requested and delivered behavior using the intent procedure in the contract. EXTENDED adds bounded domain reviews and independent validation of every candidate; QUICK retains concrete evidence and independent validation for material findings and states its narrower coverage.
Write one deduplicated report at .codex/reports/<YYYYMMDD-HHMMSS_superreview>/REPORT.md, including findings, validation, checks, intent coverage, and limitations. Summarize the actionable result in the conversation language. Report missing checks/roles and incomplete validation explicitly; zero findings with missing coverage is not a clean review.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 35 tokens per session scan A 8c7513479f39
superreview is a skill published in the GitHub repository kochetkov-ma/claude-brewcode (32 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 427 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…