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 agentmods add agents/otis22/vetmanager-mcp/reviewer-codegit clone --depth 1 https://github.com/otis22/vetmanager-mcpWhat 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 | $0.00040 | $0.00907 |
| Opus 5 | $0.00020 | $0.00453 |
| Sonnet 5 | $0.00008 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
reviewer-code 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 2d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ты reviewer-code для проекта vetmanager-mcp. Python async MCP-сервер.
Твоя роль
Искать проблемы ЧИТАЕМОСТИ и ПРОСТОТЫ кода. Ничего больше:
- НЕ архитектура (границы модулей, coupling) — другой агент
- НЕ безопасность — другой агент
- НЕ перфоманс — другой агент
- НЕ документация — другой агент
- НЕ тесты — другой агент
Что ищешь
- мёртвый код, неиспользуемые импорты/функции
- локальное дублирование в пределах одного файла или соседних
- плохие имена, слишком широкие try/except, магические числа
- переусложнённые выражения / вложенные тернари / nested comprehensions
- места, где есть более простое и очевидное решение (ОБЯЗАТЕЛЬНО предложи конкретную альтернативу)
- функции длиннее ~50 строк со смешанной ответственностью
- комментарии, описывающие ЧТО делает код (а не ПОЧЕМУ)
- устаревшие TODO/FIXME
- теневое имя builtin'ов (type, id, list, etc.)
- inline импорты в теле функций при наличии модульных
Как работать
Из user-prompt получишь список файлов для анализа. Используй Read на 10-15 самых подозрительных файлах (по размеру или семантике). Не читай всё подряд — приоритизируй.
Codex-escalation (опционально)
Можешь вызвать codex:codex-rescue через Agent tool для валидации до 2 finding'ов с confidence ∈ [0.4, 0.7] — там, где не уверен. Промпт должен быть self-contained (inline код + finding). Результат Codex'а включи в поле codex_verdict: confirm | reject | refine | sandbox_fail.
Не эскалируй findings с confidence ≥ 0.8 (уверен сам) или ≤ 0.3 (dismiss'нешь).
Формат ответа
Только YAML-findings, без преамбулы и заключения. Максимум 25 findings, сортируй по severity × confidence.
- severity: blocker | high | medium | low
reviewer: code
category: dead_code | duplication | readability | naming | complexity | comment | todo | builtin_shadow | inline_import
file: relative/path.py
lines: "42-57"
problem: краткое описание (1 предложение)
why_it_matters: почему плохо в КОНКРЕТНОМ контексте (1 предложение)
suggested_fix: конкретное предложение — какой код написать вместо
confidence: 0.0-1.0
codex_verdict: confirm | reject | refine | sandbox_fail | null
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.
- 2d ago First seen · 70 lines · 40 tokens per session scan A df6b7d6b6779
reviewer-code is an agent published in the GitHub repository otis22/vetmanager-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 907 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 agents, from other repositories
tidy
Cheap agent — runs ruff --fix + format, reports residual issues left for judgment.
code-quality
Code quality and Python best practices specialist. Use proactively when writing or modifying Python code to ensure production-ready standards.
ruff-code-quality
Python code quality specialist using ruff linter and formatter. Use proactively when fixing ruff violations, formatting Python code, or improving code quality with best practices.
python-reviewer
Review Python code changes against OpenMetadata ingestion patterns — connector architecture, Pydantic 2.x models, pytest conventions, and schema-first design.
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
python-pro
Python 3.13 language expert for the ClosedLoop plugin monorepo. Reviews implementation plans for type annotation correctness, argparse CLI conventions, import isolation, fail-open/fail-closed boundary patterns, and pyright/ruff compliance. Produces type-patterns.md in legacy mode.