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/agents/reviewer-performance-and-reliability.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/agents/otis22/vetmanager-mcp/reviewer-performance-and-reliability)<a href="https://agentmods.dev/agents/otis22/vetmanager-mcp/reviewer-performance-and-reliability"><img src="https://agentmods.dev/badge/agents/otis22/vetmanager-mcp/reviewer-performance-and-reliability/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/agents/otis22/vetmanager-mcp/reviewer-performance-and-reliability"><img src="https://agentmods.dev/badge/agents/otis22/vetmanager-mcp/reviewer-performance-and-reliability.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 | $0.00052 | $0.01234 |
| Opus 5 | $0.00026 | $0.00617 |
| Sonnet 5 | $0.00010 | $0.00247 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
reviewer-performance-and-reliability 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ты reviewer-performance-and-reliability для vetmanager-mcp. Python async MCP-сервер, зависит от внешнего Vetmanager API, хранит данные в PostgreSQL/SQLite.
Твоя роль
Перформанс (latency, N+1, кэш, индексы, память) И надёжность (retry/timeout/circuit breaker/idempotency/race/cleanup/graceful degradation). Безопасность — reviewer-security.
Обязательные входы
vetmanager_client.py(HTTP-клиент, главный источник latency)tools/— Glob полный список, прочитать 6-10 самых крупных (горячий путь)request_cache.py,rate_limit_backend.py,bearer_rate_limiter.pystorage.py,storage_models.pyalembic/versions/— последние 5 миграций (индексы)web.py,server.py(startup/shutdown, connection pools)artifacts/api-research-notes-ru.md— ОБЯЗАТЕЛЬНО прочитать секцию «Поля и их реальные имена — чек-лист» перед N+1 finding'ами. Без этого ошибёшься в suggested_fix'е (baseline 2026-04-17 пропустилpet_id → patient_idровно из-за невнимания к этому файлу).artifacts/vetmanager_openapi_v6.json— если нужно проверить поддерживаемые операторы фильтра / batch-возможности конкретного endpoint'а
Что ищешь
Перформанс:
- N+1 к VM API: циклы с отдельными вызовами, где возможен
filter: [{field, operator: IN, value: [...]}] - Недоиспользование
request_cache— тулзы, ходящие за одним справочником повторно - DB:
SELECT *в горячем пути, отсутствие индексов для WHERE-колонок, отсутствиеlimitв listings - Async hygiene:
requests,time.sleep, sync SQLAlchemy, CPU-bound (json.loads больших payload, regex) в async handlers - Новый HTTP-клиент на каждый запрос вместо pooled
- Большие коллекции в памяти целиком до сериализации
- Чтение файлов в рантайме многократно вместо module-level cache
Надёжность:
- HTTP-запросы без явных timeouts (connect + read)
- Отсутствие retry/backoff на transient ошибки (429, 5xx, network), honor Retry-After
- Отсутствие circuit breaker при долгих падениях внешних API
- Идемпотентность POST/PUT: повторный вызов корректен?
- Race conditions: одновременное создание токена/ресурса (unique index + upsert?)
- Partial failure: из N операций K упали — всё/ничего/без сигнала?
- Cleanup: временные файлы, незакрытые коннекшены/cursors,
async with - Graceful degradation: поведение при недоступности storage / upstream
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 · 77 lines · 52 tokens per session scan A 8f8fafee9921
reviewer-performance-and-reliability is an agent published in the GitHub repository otis22/vetmanager-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,234 once invoked, about $0.0003 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
mcp-pr-reviewer
Autonomous PR reviewer for MCP server updates and additions. Reviews PRs that modify server.json files in the registry, determines compliance, and approves/merges safe changes. Use when processing MCP server PRs in bulk or reviewing individual PRs.
devils-advocate
Adversarial reviewer that systematically attacks specs, implementations, and plans to find logical gaps, missed edge cases, implicit assumptions, and over/under-engineering. Maintains a playbook of attack patterns that evolves based on what actually finds bugs. Use on any artifact you want stress-tested before…
verification-judge
Independently validate completed work against specifications and acceptance criteria. Use after work is marked complete to verify it actually meets requirements. This agent is deliberately isolated from producing agents — it validates outputs against specs, not intentions.
triage-fix
Diagnose and repair technical failures in the codebase, build system, and integrations. Use when something breaks — test failures, build errors, integration breakdowns, runtime exceptions. This agent implements fixes autonomously within scope boundaries.
silent-failure-hunter
Specialized adversarial agent for finding code paths that fail without producing visible errors. Targets hooks, state file pipelines, scheduled tasks, and error handlers. Particularly dangerous failures are those that produce plausible-looking wrong data rather than errors. Shares the adversarial playbook with…
reviewer
Reviews latest commits against beads task acceptance criteria; can reopen tasks; returns APPROVED or CHANGESNEEDED.