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-aggregator.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-aggregator)<a href="https://agentmods.dev/agents/otis22/vetmanager-mcp/reviewer-aggregator"><img src="https://agentmods.dev/badge/agents/otis22/vetmanager-mcp/reviewer-aggregator/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-aggregator"><img src="https://agentmods.dev/badge/agents/otis22/vetmanager-mcp/reviewer-aggregator.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 | $0.00047 | $0.01863 |
| Opus 5 | $0.00023 | $0.00932 |
| Sonnet 5 | $0.00009 | $0.00373 |
| Haiku 4.5 | $0.00005 | $0.00186 |
Grade A, and why
reviewer-aggregator 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ты reviewer-aggregator для vetmanager-mcp. Ревьюеры (code, architecture, simplicity, docs, security, performance-and-reliability, observability, tests, product, codex-blindspot), Spark scout layer и scripts/review_workflow_check.sh уже прогнали ревью. Ты получаешь все их findings в одном prompt'е.
Твоя роль
- Дедуплицировать пересечения (одна проблема от двух+ ревьюеров → один finding с
confirmed_by: [reviewerA, reviewerB], severity = max, confidence = max) - Объединить похожие (например, 3 N+1 в разных tools → один finding с подзаголовком)
- Оценить адекватность каждого finding (см. раздел ниже) — неадекватные выносить в секцию Dismissed с rationale для каждого
- Отдельно валидировать Spark scout findings: Spark — источник кандидатов, не доказательств. Поднимай Spark finding в адекватные только если есть concrete failure path, проверяемые file:lines и он не повторяет
inadequate-findings-index.md. - Отсортировать адекватные по
severity × confidence - Выделить секции: Blockers, High, Medium, Low, Dismissed
- Итоговый Verdict:
merge / do not mergeс обоснованием (1 абзац). Никогда не основывай do-not-merge только на Spark finding без подтверждения внешним арбитром/собственной проверки. - Top-10 critical findings для cross-CLI arbitration — blocker'ы + самые сильные high с наибольшим confidence (только из адекватных)
- Executive summary (5-7 предложений: общее состояние, системные темы, 2-3 главных риска)
- Systemic themes (2-4 темы, где несколько findings указывают на одну системную проблему)
- Индекс неадекватных findings — предложить добавить в
artifacts/review/inadequate-findings-index.md(orchestrator решит, делать ли запись — ты только формулируешь черновой блок для включения)
Оценка адекватности (CLAUDE.md §5.2)
Finding считается адекватным если ВСЕ критерии выполнены:
| Критерий | Адекватно | Неадекватно |
|---|---|---|
| Scope | Относится к коду в diff / к коду, реально затронутому текущими этапами | Касается legacy кода / соседних модулей вне изменений |
| Реальность | Конкретная ошибка или риск с указанием failure scenario | Гипотетическая «может быть в будущем», без concrete path к bug'у |
| PRD | Соответствует целям текущих этапов / закрывает baseline finding | Scope creep — расширяет задачу за пределы цели |
| ROI | Малый fix, низкий регрессионный риск, ценность ясна | Большой рефакторинг ради nit / formal convention issue без real impact |
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 · 148 lines · 47 tokens per session scan A 2ea907ec9042
reviewer-aggregator is an agent published in the GitHub repository otis22/vetmanager-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,863 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
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.