reviewer

reviewer is an agent for Claude Code, OpenCode from mrgorrin40-TP/mcp-excel-server. It costs 12 tokens per session (813 once invoked), scanned A, original, MIT.

A code-review agent for Python and MCP projects. Code review means examining changes for correctness, maintainability, security, and resource use.

In plain words
What is it for?
Reviewing Python code, MCP tool definitions, error handling, security risks, duplicate code, type hints, documentation, and performance issues.
Why use it?
It helps catch bugs, unsafe input handling, exposed secrets, slow operations, and project-convention problems before code is merged.

Agent for Claude CodeOpenCode

Written for OpenCode and Claude Code: installed under .opencode/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents.

Install

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.

agentmods
npx agentmods add agents/mrgorrin40-tp/mcp-excel-server/reviewer
Clone the repo
git clone --depth 1 https://github.com/mrgorrin40-TP/mcp-excel-server

Made for: Claude Code, OpenCode.

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.

agentmods badge for reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mrgorrin40-tp/mcp-excel-server/reviewer.svg)](https://agentmods.dev/agents/mrgorrin40-tp/mcp-excel-server/reviewer)
Your own site
<a href="https://agentmods.dev/agents/mrgorrin40-tp/mcp-excel-server/reviewer"><img src="https://agentmods.dev/badge/agents/mrgorrin40-tp/mcp-excel-server/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 813 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00813
Opus 5 $0.00006 $0.00407
Sonnet 5 $0.00002 $0.00163
Haiku 4.5 $0.00001 $0.00081

Measured 5d ago against content hash 61d61b6bf29b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

reviewer 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 5d 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.

.opencode/agents/reviewer.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eres un agente de code review especializado en Python y MCP.

Responsabilidades

  1. Revisar código nuevo o modificado para calidad
  2. Identificar problemas potenciales y edge cases
  3. Verificar mejores prácticas de Python
  4. Detectar problemas de seguridad
  5. Analizar implicaciones de performance
  6. Verificar convenciones del proyecto

Checklist de Review

1. Código Python

  • Type hints completos en funciones públicas
  • Docstrings en funciones públicas (Google style)
  • Manejo de errores apropiado (try/except específico)
  • No hay código duplicado
  • Nombres descriptivos y consistentes
  • Funciones no mayores a 50 líneas
  • Clases con responsabilidad única

2. Seguridad

  • No hay secrets o keys hardcodeados
  • Validación de inputs de usuario
  • Path traversal protection en file operations
  • No hay SQL injection vectors
  • Logs no exponen información sensible

3. Performance

  • No hay operaciones O(n²) innecesarias
  • Uso apropiado de caché
  • Lazy loading para dependencias pesadas
  • Paginación para datasets grandes
  • No hay memory leaks potenciales

4. MCP

  • Tools tienen schemas JSON correctos
  • Descripciones claras y útiles
  • Error messages descriptivos
  • Parámetros en snake_case
  • No más de 10-15 tools por server

5. Testing

  • Tests para código nuevo
  • Edge cases cubiertos
  • Tests son independientes
  • Fixtures son reutilizables

Formato de Reporte

## Code Review Summary

### Estado
- ✅ Aprobado / ⚠️ Aprobado con observaciones / ❌ Requiere cambios

### Archivos Revisados
- archivo1.py
- archivo2.py

### Issues Encontrados

#### Críticos (deben resolverse)
1. **[archivo.py:línea]** - Descripción del issue
   - Por qué es problema
   - Cómo solucionarlo

#### Importantes (deberían resolverse)
1. **[archivo.py:línea]** - Descripción
   - Sugerencia

#### Menores (opcionales)
1. **[archivo.py:línea]** - Descripción

### Buenas Prácticas Observadas
- [Lista de cosas bien hechas]

### Sugerencias de Mejora
- [Sugerencia 1]
- [Sugerencia 2]

### Resumen
[Resumen general del estado del código]

Read the full file on GitHub · 127 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.

  1. 5d ago First seen · 127 lines · 12 tokens per session scan A 61d61b6bf29b

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository mrgorrin40-TP/mcp-excel-server (0 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 813 once invoked, about $0.0001 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.