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.
npx skills add j4rk0r/claude-skills --skill lint-drupal-modulegit clone --depth 1 https://github.com/j4rk0r/claude-skillsWrote 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/skills/j4rk0r/claude-skills/lint-drupal-module)<a href="https://agentmods.dev/skills/j4rk0r/claude-skills/lint-drupal-module"><img src="https://agentmods.dev/badge/skills/j4rk0r/claude-skills/lint-drupal-module/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/skills/j4rk0r/claude-skills/lint-drupal-module"><img src="https://agentmods.dev/badge/skills/j4rk0r/claude-skills/lint-drupal-module.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 | $0.00225 | $0.04947 |
| Opus 5 | $0.00112 | $0.02474 |
| Sonnet 5 | $0.00045 | $0.00989 |
| Haiku 4.5 | $0.00022 | $0.00495 |
Grade A, and why
lint-drupal-module 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 10d 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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lint Review — Módulo Drupal 11
Primera línea del informe generado: "Español confirmado."
Para qué sirve
Combina 4 fuentes de análisis (PHPStan, PHPCS, agente drupal-qa, agente drupal-security) en una sola invocación paralelizada, y consolida los hallazgos en un informe accionable. A mano son ~12 pasos y ~30 minutos; con la skill, lo que tarda la fuente más lenta (~2-5 min en completo, ~30s-1min en diff).
Fast path
1. Identificar módulo (nombre/ruta del usuario, o Glob si no especifica)
2. Detectar modo: completo (default) | diff (si dice "diff", "rápido", "vs develop")
3. Detectar entorno: ddev describe → ejecutar via "ddev exec"
4. Verificar herramientas (vendor/bin/phpstan, vendor/bin/phpcs); instalar si faltan PREGUNTANDO
5. Verificar agentes drupal-qa y drupal-security disponibles (si no, ver "Recovery")
6. Leer references/prompts-agentes.md (necesario para el paso 7)
7. Ejecutar las 4 fuentes EN PARALELO en el mismo mensaje:
a) Agent drupal-qa — prompt literal de references/prompts-agentes.md
b) Agent drupal-security — prompt literal de references/prompts-agentes.md
c) PHPStan level 5 vía Bash (ver "Ejecución en paralelo")
d) PHPCS Drupal,DrupalPractice vía Bash
8. Leer references/plantilla-informe.md y consolidar las 4 salidas en un informe markdown
9. Detectar IDE → escribir en <carpeta-IDE>/Lint reviews/<nombre-modo-rama>.md
10. Resumir top bloqueantes en chat; preguntar "arregla todo" / "solo crítico" / "déjalo así"
Si cualquier paso falla, detente y consulta references/edge-cases.md. No improvises.
Referencias bajo demanda
Tres archivos en references/, cargados solo cuando los necesitas (progressive disclosure):
| Archivo | Cuándo cargarlo | Por qué |
|---|---|---|
references/prompts-agentes.md |
Antes del paso 7 (invocar agentes) | Contiene los prompts literales para drupal-qa y drupal-security. Son largos a propósito — sin brief explícito los agentes devuelven reviews superficiales. Cópialos literales, solo sustituye <ruta-absoluta>, <modo>, <lista-archivos>. |
references/plantilla-informe.md |
Antes del paso 8 (redactar informe) | Plantilla fija. La consistencia entre informes de distintos módulos es lo que hace que el equipo los lea rápido. |
references/edge-cases.md |
Cuando algo falle | Síntoma → causa → solución para los problemas más comunes (DDEV, PHPStan, services.yml, OAuth, modo diff). |
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 257 lines · 225 tokens per session scan A c2cabe26b612
lint-drupal-module is a skill published in the GitHub repository j4rk0r/claude-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 225 tokens to every session and 4,947 once invoked, about $0.0011 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 skills, from other repositories
la-chancla
Use only when the user explicitly requests a strict review of one named task, change, plan, release, or invariant. Never self-selected, never auto-loaded, never invoked by another skill or by the mexican-mom router. NOT a session-wide mode and NOT a warning counter.
frijoles-en-el-tupper
Use when writing or reviewing names — functions, variables, types, files, schemas, API fields, config keys — and the comments attached to them, to check that each label predicts what is actually inside. NOT for whether failure paths are handled; use pero-ponte-sueter.
pero-tu-primo
Use after a substantial implementation works and before claiming it is good, clean, idiomatic, or optimal. Compare it against a concrete alternative you open and read in this session. NOT for unverified claims about an external library you did not open; use cadena-de-whatsapp.
si-el-lo-hace-tu-tambien
Use before giving your own technical justification when it rests mainly on popularity, trend, convention, or what another codebase does rather than on the requirements at hand. Name the requirement and the trade-off instead. NOT when the user already chose the tool; use porque-yo-lo-digo.
shipkit-review-shipping
Review changes across 12 quality dimensions and report findings. Use after a chunk of work or before commit.
shipkit-prompt-audit
Audit LLM prompt pipeline architecture — decomposition, parallelization, chain integrity, schema validation, fallback paths. Finds structural issues no linter catches.