doctor

doctor is a command for Claude Code from polmarza/project-template. It costs 0 tokens per session (830 once invoked), scanned A, original, MIT.

A diagnostic command that checks the project's documentation, feature records, tests, and development environment, then reports what is missing or broken. It only suggests fixes and does not apply them.

In plain words
What is it for?
Use it when first entering a project, investigating unexplained failures, checking required documentation, verifying feature coverage, or reviewing promised tests.
Why use it?
It gives you a clear health report before a long coding session or when something fails unexpectedly.

Command for Claude Code

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 commands/polmarza/project-template/doctor
Clone the repo
git clone --depth 1 https://github.com/polmarza/project-template

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.

agentmods badge for doctor

README.md
[![agentmods](https://agentmods.dev/badge/commands/polmarza/project-template/doctor.svg)](https://agentmods.dev/commands/polmarza/project-template/doctor)
Your own site
<a href="https://agentmods.dev/commands/polmarza/project-template/doctor"><img src="https://agentmods.dev/badge/commands/polmarza/project-template/doctor.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 830 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 $0.00000 $0.00830
Opus 5 $0.00000 $0.00415
Sonnet 5 $0.00000 $0.00166
Haiku 4.5 $0.00000 $0.00083

Measured 3d ago against content hash 49ee1a29754b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doctor 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 3d 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/commands/doctor.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Revisa el estado del proyecto y del entorno, y da un parte de qué está bien, qué falta y cómo arreglarlo. Solo diagnostica: no arregla nada por su cuenta. Al terminar, propón las correcciones y deja que el usuario decida cuáles aplicar.

Ejecútalo cuando alguien entra al proyecto por primera vez, cuando algo falla sin motivo aparente o antes de una sesión larga, para no descubrir a mitad que faltaba media configuración.

Qué comprobar

1. Documentación

  • ¿Existen todos los archivos que CLAUDE.md marca como obligatorios para este proyecto? (La obligatoriedad depende del tamaño: mira la tabla "Qué documentación necesita cada proyecto".)
  • ¿Alguno está vacío — solo comentarios <!-- -->, sin contenido real?
  • ¿Sigue existiendo .template/? Entonces la inicialización quedó a medias.

2. Fichas de feature

Ejecuta la verificación de cobertura y reporta su salida tal cual:

node scripts/verificar-cobertura.mjs

Comprueba las tablas contra docs/prd.md: filas sin validación declarada, excepciones que no explican nada, identificadores inexistentes y tests prometidos que no existen en fichas Verificada. Sus FALLO son FALLO aquí; sus ATENCIÓN son ATENCIÓN.

Añade a mano lo que el script no mira, porque requiere criterio:

  • Fichas en En construcción: son trabajo a medias. Di cuáles y desde cuándo.
  • Tests declarados que existen pero están vacíos o sin aserciones reales. El script solo comprueba que el archivo esté ahí; si te cruzas con uno hueco, es un FALLO aunque la verificación pase.

3. Entorno

  • Versión de Node y de pnpm frente a lo que declare CLAUDE.md. Si no coinciden, dilo: la mayoría de fallos raros de instalación son esto.
  • ¿Están las dependencias instaladas (node_modules/)? ¿El lockfile está al día respecto a package.json?
  • Variables: compara los nombres de .env.example con los que hay definidos en el entorno o en .env.local. Reporta solo los nombres que faltan. Nunca imprimas un valor, ni completo ni parcial, ni siquiera para confirmar que es correcto.

Read the full file on GitHub · 73 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. 3d ago First seen · 73 lines · 0 tokens per session scan A 49ee1a29754b

Subscribe to this mod's changes

doctor is a command published in the GitHub repository polmarza/project-template (79 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 830 tokens. 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 2026-08-30.