Borrowing it
Nothing to install: this file belongs to otis22/vetmanager-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/otis22/vetmanager-mcp/main/.claude/commands/super-review.mdgit clone --depth 1 https://github.com/otis22/vetmanager-mcpWrote 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/commands/otis22/vetmanager-mcp/super-review)<a href="https://agentmods.dev/commands/otis22/vetmanager-mcp/super-review"><img src="https://agentmods.dev/badge/commands/otis22/vetmanager-mcp/super-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/commands/otis22/vetmanager-mcp/super-review"><img src="https://agentmods.dev/badge/commands/otis22/vetmanager-mcp/super-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 | $0.00042 | $0.04567 |
| Opus 5 | $0.00021 | $0.02284 |
| Sonnet 5 | $0.00008 | $0.00913 |
| Haiku 4.5 | $0.00004 | $0.00457 |
Grade A, and why
super-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 9d 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 — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Super-review: многоплановое ревью проекта
Ты — оркестратор ревью. Выполняй по шагам.
Модельная матрица
Используй универсальную схему: дешёвые/быстрые модели повышают полноту поиска, сильные модели принимают решения.
| Слой | Codex/GPT | Claude | Назначение |
|---|---|---|---|
| Scout/prepass | gpt-5.3-codex-spark |
Haiku/Sonnet light | Массовые кандидаты findings, chunk review, edge cases, docs/tests drift, snippet collection |
| Code/docs/tests | gpt-5.4-mini или gpt-5.3-codex-spark |
Sonnet | Локальное качество, тестовые пробелы, verified docs drift |
| Observability | gpt-5.4 |
Sonnet | Логи, метрики, трассировка, пригодность для дебага |
| Perf/reliability | gpt-5.4 или gpt-5.5 |
Opus или strong Sonnet | Hot paths, retry/timeout, partial failure, async pitfalls |
| Security | gpt-5.5 |
Opus | Auth/token/SSRF/SQLi/secrets findings |
| Architecture | gpt-5.5 |
Opus | Границы модулей, coupling, long-term design |
| Product/PRD | gpt-5.5 |
Opus | Acceptance criteria, UX для LLM-клиента, breaking changes |
| Aggregator/verdict | gpt-5.5 |
Opus | Dedup, adequacy, severity, финальный verdict |
| Arbitration/challenge | gpt-5.5 |
Opus | Проверка Top-10 и спорных findings |
Правило: gpt-5.3-codex-spark findings — untrusted leads. Они идут в aggregator только как кандидаты с source: spark-scout; финальный verdict, severity и do-not-merge решение не отдавай Spark.
Cross-CLI arbitration
Финальная arbitration всегда идёт через другую модельную семью, чем основной orchestrator:
- Если super-review запущен в Claude Code: внешний арбитр — Codex CLI (
codex exec) наgpt-5.5, fallbackgpt-5.4. - Если super-review запущен в Codex: внешний арбитр — Claude CLI (
claude -p) наopus, fallbacksonnet.
Определи runtime по доступному окружению/контексту. Если сомневаешься:
.claude/commands/super-review.mdвнутри Claude Code → считаем runtime=claude.- Codex skill / Codex CLI / текущий агент Codex → считаем runtime=
codex.
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.
- 9d ago First seen · 333 lines · 42 tokens per session scan A 01266b770e37
super-review is a command published in the GitHub repository otis22/vetmanager-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 4,567 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other commands, from other repositories
simplicity-review
Review the current diff (or the files I name) against the MoE Sovereign Complexity Decision Ladder.
review
Perform a comprehensive code review with actionable feedback.
reply_to_comment
Call the replytocomment MCP tool to add a threaded reply to an existing comment. Read the comment id and the reply text from $ARGUMENTS. Use this to respond to my feedback, or as the author/defender role in a review thread before I resolve it. If no id is given, ask me which comment to reply to.
conformance
Assess architecture conformance — ADR decision implementation, cross-decision consistency, design-principles alignment, architecture drift, technical debt, and custom constraint rules.
show_diff
Call the showdiff MCP tool to show me a side-by-side visual diff (it returns an image in the chat). If I passed a checkpoint sha in $ARGUMENTS, diff that checkpoint; otherwise show my current uncommitted changes.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.