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 superreview-setupgit 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-setup)<a href="https://agentmods.dev/skills/kochetkov-ma/claude-brewcode/superreview-setup"><img src="https://agentmods.dev/badge/skills/kochetkov-ma/claude-brewcode/superreview-setup/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-setup"><img src="https://agentmods.dev/badge/skills/kochetkov-ma/claude-brewcode/superreview-setup.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 | $0.00056 | $0.12302 |
| Opus 5.5 | $0.00022 | $0.04921 |
| Sonnet 5.5 | $0.00011 | $0.02460 |
| Haiku 4.5 | $0.00006 | $0.01230 |
Grade D, and why
superreview-setup scanned grade D with 3 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
echo "reports: $({ find .codex/reports -maxdepth 1 -type d -name '*_superreview' 2>/dev/null || true; } | wc -l | tr -d ' ') dir(s) — deleted by 'purge', kept by 'uninstall'" Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
**Confirm before deleting.** `uninstall` and `purge` each `main-chat user gate` exactly once, listing the real paths (`find .codex/skills/superreview -type f | sort`) and, for `purge`, the number of review reports being Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
never pick a temp dir by glob (`rm -rf` on the newest `tmp.*`): it may belong to another run. How it starts
The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project-tailored review
Inspect repository instructions, architecture, tests, and recent changes, then create a focused Codex review skill in the user-selected project .codex/skills/ path. Encode evidence-based checks, severity guidance, and verification commands. Validate the generated skill and do not create Markdown agent definitions.
Complete native workflow
Follow every phase below. When a phase delegates work, use Codex collaboration with only task_name and message; treat each "Codex delegation brief" block as role and message content, not executable syntax. Required approval: main presents a concrete, reviewable proposal in chat and waits for an actual user reply before dependent action. Existing authorization for the same scope remains valid; do not ask again. Optional clarification: use request_user_input_async only if exposed, or request_user_input only if available in the current runtime/mode, for optional choices and never approval. Otherwise ask in main chat. Delegated agents return unresolved questions to main. Silence, elapsed time and tool errors are not approval. Resolve <skill-directory>, <plugin-root>, <project-root>, and <arguments> before running commands.
Super Review Generator (brewcode:superreview-setup)
A human-invoked generator: it analyzes the TARGET project, then writes a self-contained project-local review skill into it. It does not review code itself; the emitted skill does.
Output: <target>/.codex/skills/superreview/ (SKILL.md + references) plus the project agent
<target>/.codex/agents/intent-guard.toml. The emitted skill references (never restates) the project's
.codex/rules + convention files, is read-only, stack-generic (Java/Kotlin, Node/TS, Python, Go), with no plugin
dependency and no sibling-skill orchestration once generated.
Three things make or break the emitted skill:
- Domain experts — a review routed to generic agents finds generic issues; Phase 1.6 creates the missing ones before emitting.
- Scope discipline — every change measured against the sanctioned baseline (task + issue + recorded decisions): creep, blast radius, under-delivery, closeout. Phase 1.5 wires it to the target's tracker.
- The intent pass —
intent-guardanswers "was the DELIVERED thing the ASKED thing?" at both depths, and is the whole review atQUICK. Phase 1.6 + Phase 3 wire it to this project's real invariants.
What ships with it
16 files 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.
- agents/openai.yaml 244 B
- README.md 3.7 KB
- references/agent-prompt.md 13 KB
- references/go.md 3.4 KB
- references/intent-guard.md.template 15 KB
- references/intent-guard.toml.template 295 B
- references/java-kotlin.md 3.6 KB
- references/python.md 3.6 KB
- references/report-template.md 13 KB
- references/scope.md.template 15 KB
- references/SKILL.md.template 66 KB
- references/typescript-react.md 3.4 KB
- scripts/emit-intent-guard.sh 2.9 KB runs code
- scripts/generate.sh 52 KB runs code
- tests/run.sh 2.6 KB runs code
- tests/suite-emit-safety.mjs 18 KB runs code
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.
- today Changed d4a9b4b7f5c4
- yesterday Changed 4324f9d90f3d
- 2d ago Changed · -6 lines 036fea639c70
- 3d ago Changed · -148 lines a5ab3fbadc00
- 10d ago Changed 0b6029efdbf9
- 15d ago Changed · -2 lines df3ee5816d12
- 1mo ago Changed 6e57f01f5ae4
- 1mo ago First seen · 655 lines · 56 tokens per session scan D 6033f532b9f5
superreview-setup is a skill published in the GitHub repository kochetkov-ma/claude-brewcode (32 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 12,302 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it D with 3 findings (reads agent configuration directories, enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
claude-friends
Ask AIs from other families to review something before you commit to it. User-triggered, never automatic. Fires when the user signals uncertainty or asks for another perspective: 'ask a friend', 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test this', 'critique this', 'devil's…
la-chancla
Use only when the user explicitly requests a strict review of one named task, change, plan, release, or invariant. Never self-selected, never auto-loaded, never invoked by another skill or by the mexican-mom router. NOT a session-wide mode and NOT a warning counter.
frijoles-en-el-tupper
Use when writing or reviewing names — functions, variables, types, files, schemas, API fields, config keys — and the comments attached to them, to check that each label predicts what is actually inside. NOT for whether failure paths are handled; use pero-ponte-sueter.
pero-tu-primo
Use after a substantial implementation works and before claiming it is good, clean, idiomatic, or optimal. Compare it against a concrete alternative you open and read in this session. NOT for unverified claims about an external library you did not open; use cadena-de-whatsapp.
si-el-lo-hace-tu-tambien
Use before giving your own technical justification when it rests mainly on popularity, trend, convention, or what another codebase does rather than on the requirements at hand. Name the requirement and the trade-off instead. NOT when the user already chose the tool; use porque-yo-lo-digo.
generic-fullstack-code-reviewer
Review full-stack code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md compliance. Enforces TypeScript strict mode, input validation, GPU-accelerated animations, and design system consistency. Use when completing features, before commits, or reviewing pull requests.