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 agentmods add skills/facturascripts/fs-claude-plugin/skill-commitnpx skills add FacturaScripts/fs-claude-plugin --skill skill-commitgit clone --depth 1 https://github.com/FacturaScripts/fs-claude-pluginWhat 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 | $0.00092 | $0.01346 |
| Opus 5 | $0.00046 | $0.00673 |
| Sonnet 5 | $0.00018 | $0.00269 |
| Haiku 4.5 | $0.00009 | $0.00135 |
Grade A, and why
skill-commit 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 2d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commits en Git — Buenas Prácticas
El objetivo de un buen commit es que cualquier persona del equipo (o tú mismo dentro de 6 meses) pueda entender qué se cambió y por qué con solo leer el historial de git. Un commit bien hecho facilita las revisiones de código, simplifica los reverts y hace que el proyecto sea más mantenible.
Estructura del mensaje de commit
Usa el formato de Conventional Commits adaptado al español:
<tipo>(<ámbito>): <descripción breve>
<cuerpo opcional>
<pie opcional>
Ejemplo 1:
feat(facturas): añadir campo de descuento por pronto pago
Se añade un nuevo campo en el modelo de factura que permite
aplicar un porcentaje de descuento cuando el cliente paga
antes de la fecha de vencimiento.
Ejemplo 2:
fix(informes): corregir cálculo de IVA en informe trimestral
El IVA se estaba calculando sobre el total con descuento en
lugar de sobre la base imponible. Ahora se aplica correctamente.
Ejemplo 3 (simple):
docs(readme): actualizar instrucciones de instalación
Código de tarea en el commit
Cuando el usuario proporcione un código de tarea (por ejemplo, un número de issue o tarea del roadmap como 4543, #1234, TASK-567, etc.), este código debe incluirse en el título del commit, justo después del tipo (y ámbito si lo hay), antes de la descripción. Solo se incluye el código numérico o identificador, sin enlaces ni texto adicional.
Formato con código de tarea:
<tipo>: <código> <descripción breve>
Formato con código de tarea y ámbito:
<tipo>(<ámbito>): <código> <descripción breve>
Ejemplos con código de tarea:
feat: 4543 añadir filtro por fecha de pago en las listas de anticipos de clientes y proveedores
fix: 1287 corregir cálculo de IVA en informe trimestral
feat(facturas): 3201 añadir campo de descuento por pronto pago
Si el usuario no menciona ningún código de tarea, el commit se escribe sin él, siguiendo el formato estándar.
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.
- 2d ago First seen · 134 lines · 92 tokens per session scan A d681cb761ec6
skill-commit is a skill published in the GitHub repository FacturaScripts/fs-claude-plugin (8 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 1,346 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…