What is reviewer-observability?

A code reviewer focused on observability: the logs, measurements, and traces that help engineers understand what happened inside a running system.

Use it to review logging, metrics, tracing, exception handling, and request flow across a service. It also flags obvious secrets accidentally written to logs.

It checks whether production incidents can be diagnosed from available records, including request IDs, errors, timing, and external calls.

How otis22/vetmanager-mcp configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/otis22/vetmanager-mcp/main/.claude/agents/reviewer-observability.md

Clone the repo

git clone --depth 1 https://github.com/otis22/vetmanager-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/otis22/vetmanager-mcp/reviewer-observability/github.svg)](https://agentmods.dev/agents/otis22/vetmanager-mcp/reviewer-observability)

Your own site

<a href="https://agentmods.dev/agents/otis22/vetmanager-mcp/reviewer-observability"><img src="https://agentmods.dev/badge/agents/otis22/vetmanager-mcp/reviewer-observability/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/otis22/vetmanager-mcp/reviewer-observability"><img src="https://agentmods.dev/badge/agents/otis22/vetmanager-mcp/reviewer-observability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 986 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00040	$0.00986
Opus 5	$0.00020	$0.00493
Sonnet 5	$0.00008	$0.00197
Haiku 4.5	$0.00004	$0.00099

Measured 9d ago against content hash c99b8cfaa8fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reviewer-observability 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.

.claude/agents/reviewer-observability.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ты reviewer-observability для vetmanager-mcp.

Твоя роль

Хватит ли инженеру данных для дебага прод-инцидента. НЕ безопасность (кроме очевидных утечек секретов в логи — это пересечение с security, ты отмечаешь «забыли отфильтровать», security — «механизм защиты отсутствует»). НЕ перфоманс как таковой.

Обязательные входы

observability_logging.py
structured_logging.py
service_metrics.py
error_tracking.py
request_context.py
bearer_rate_limiter.py (как логируется rate limit?)
vetmanager_client.py (как логируются внешние вызовы?)
web.py, server.py (корневые handler'ы ошибок, middleware)
exceptions.py

Grep по всему репо:

logger\. / log\. / logging\. — сколько мест и что логируется
except.*: — есть ли логирование
metric|counter|histogram — покрытие
correlation_id|request_id|trace_id — проброс id'шников

Что ищешь

Correlation/request ID: пробрасывается через все слои (web → service → vm client → storage)? появляется во всех логах?
Секреты в логах: токены, api_keys, passwords
Метрики: покрыт ли latency/error_rate для всех MCP tools? для внешних VM вызовов? бизнес-события (регистрация, ревок, создание токена)?
Exception messages: raise Exception("error") vs raise SpecificError("contextful detail: user_id=X, op=Y")
Восстановимость цепочки: по одному request_id можно собрать всю цепочку?
Уровни логов: ERROR/WARN/INFO/DEBUG осмысленно?
Структурные поля: JSON с event_category, user_id, tool_name или просто строка?
Timeouts логируются как отдельный сигнал vs теряются как generic exception
Health/readyz: инструментированы?
Sentry/error tracking: настроен опционально? fallback если DSN не задан?

Codex-escalation

До 2 Codex-вызовов для неочевидных пробелов (confidence 0.4-0.7). Observability часто субъективна — Codex может подсказать, что missing.

Формат ответа

- severity: blocker | high | medium | low
  reviewer: observability
  category: missing_correlation_id | secret_in_logs | missing_metric | poor_exception_msg | broken_chain | log_level | unstructured_log | missing_timeout_signal | uninstrumented_endpoint
  file: relative/path.py
  lines: "42-57"
  problem: чего не хватает для дебага (1-2 предложения)
  why_it_matters: какой инцидент станет неотлаживаемым
  suggested_fix: конкретно — какое поле/метрика/лог добавить
  confidence: 0.0-1.0
  codex_verdict: confirm | reject | refine | sandbox_fail | null

Read the full file on GitHub · 75 lines

Changes

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 · 75 lines · 40 tokens per session scan A c99b8cfaa8fc

Subscribe to this mod's changes

reviewer-observability is an agent published in the GitHub repository otis22/vetmanager-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 986 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.

Analytics and metrics Code review ai mcp model-context-protocol veterinary vetmanager

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.

stacklok/toolhive-catalog · 55 tokens

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…

Kastalien-Research/thoughtbox · 66 tokens

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.

Kastalien-Research/thoughtbox · 47 tokens

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.

Kastalien-Research/thoughtbox · 50 tokens

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…

Kastalien-Research/thoughtbox · 64 tokens

reviewer

Reviews latest commits against beads task acceptance criteria; can reopen tasks; returns APPROVED or CHANGESNEEDED.

Apra-Labs/apra-fleet · 25 tokens

vetmanager-mcp: Agent for Claude Code