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 WhiteMuush/Your-Claude-DevOps --skill metrics-setupgit clone --depth 1 https://github.com/WhiteMuush/Your-Claude-DevOpsWrote 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/whitemuush/your-claude-devops/metrics-setup)<a href="https://agentmods.dev/skills/whitemuush/your-claude-devops/metrics-setup"><img src="https://agentmods.dev/badge/skills/whitemuush/your-claude-devops/metrics-setup/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/whitemuush/your-claude-devops/metrics-setup"><img src="https://agentmods.dev/badge/skills/whitemuush/your-claude-devops/metrics-setup.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 | $0.00128 | $0.02059 |
| Opus 5.5 | $0.00051 | $0.00824 |
| Sonnet 5.5 | $0.00026 | $0.00412 |
| Haiku 4.5 | $0.00013 | $0.00206 |
Grade A, and why
metrics-setup 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 26d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 26d ago First seen · 133 lines · 128 tokens per session scan A da0df6a16ac2
metrics-setup is a skill published in the GitHub repository WhiteMuush/Your-Claude-DevOps (2 stars, last pushed 17d ago), with no licence file. It adds 128 tokens to every session and 2,059 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-22.
Other skills, from other repositories
crear-spec-sdd
Convierte una idea de feature en un spec.md completo, listo para SDD (Spec-Driven Development). Sigue el estándar de GitHub Spec Kit: historias priorizadas con criterios de aceptación en Gherkin, requisitos funcionales, entidades, criterios de éxito medibles y suposiciones. Céntrate en el QUÉ y el PORQUÉ, nunca en el…
mapa-de-historias-usuario
Crea un mapa de historias de usuario (user story mapping, de Jeff Patton) que despliega la columna vertebral de actividades, sus pasos y tareas, y traza las líneas de release para separar el MVP de lo que viene después. Úsala cuando arranques un producto o una funcionalidad grande, quieras construir entendimiento…
cuando-usar-ia-metodo-e2ad
Ayuda a decidir qué tareas, procesos o problemas merecen llevarse a la IA (y cuáles no) con el método propio E2AD de Javier Garzás (Eliminar, Agilizar, Automatizar y, solo con lo que quede, Delegar), que trata la IA como el último recurso, no el primero, y lo respalda con los principios de estrategia de IA de…
arbol-oportunidad-solucion
Construye un Árbol de Oportunidad-Solución (OST) para estructurar el descubrimiento de producto — conecta un resultado deseado con oportunidades del cliente, soluciones candidatas y experimentos para validarlas. Basado en Continuous Discovery Habits de Teresa Torres. Úsala cuando estructures el discovery, quieras…
crear-historias-de-usuario
Aterriza UNA única historia de usuario en su definición completa y lista para que un equipo de desarrollo la pueda coger en un sprint. Produce un documento markdown con story statement, contexto, criterios de aceptación en formato Gherkin (happy path + edge cases + errores), Definition of Ready, Definition of Done…
crear-lean-canvas
Guía paso a paso, en modo conversación, para construir un Lean Canvas (el modelo de negocio de Ash Maurya) rellenando sus 9 bloques uno a uno — problema, segmento de clientes, propuesta de valor única, solución, canales, ingresos, costes, métricas clave y ventaja injusta. Hace una pregunta cada vez, ofrece ejemplos…