agentmods.dev

project-starter-template-es-ai: Skill for Claude Code

.claude/skills/new-spec/SKILL.md

new-spec is a skill for Claude Code from brayandiazc/project-starter-template-es-ai. It costs 90 tokens per session (921 once invoked), scanned A, original, MIT.

A workflow for starting a lightweight change specification from a project template.

In plain words
What is it for?
Use it to start a feature or change proposal and record its problem, goals, exclusions, and approach.
Why use it?
It gives a planned change a consistent folder, title, status, date, and document structure before implementation begins.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool.

This is brayandiazc/project-starter-template-es-ai's own configuration. It tells Claude Code how to work on project-starter-template-es-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything project-starter-template-es-ai configures →

not rated 15repo changed 3d ago A scan 90 tokens original MIT
View source ↗ brayandiazc/project-starter-template-es-ai
Reuse

Borrowing it

Nothing to install: this file belongs to brayandiazc/project-starter-template-es-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/brayandiazc/project-starter-template-es-ai/main/.claude/skills/new-spec/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/brayandiazc/project-starter-template-es-ai

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 new-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/brayandiazc/project-starter-template-es-ai/new-spec/github.svg)](https://agentmods.dev/skills/brayandiazc/project-starter-template-es-ai/new-spec)
Your own site
<a href="https://agentmods.dev/skills/brayandiazc/project-starter-template-es-ai/new-spec"><img src="https://agentmods.dev/badge/skills/brayandiazc/project-starter-template-es-ai/new-spec/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.

agentmods 80×15 button for new-spec

Your own site · 80×15
<a href="https://agentmods.dev/skills/brayandiazc/project-starter-template-es-ai/new-spec"><img src="https://agentmods.dev/badge/skills/brayandiazc/project-starter-template-es-ai/new-spec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 921 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00090 $0.00921
Opus 5 $0.00045 $0.00461
Sonnet 5 $0.00018 $0.00184
Haiku 4.5 $0.00009 $0.00092

Measured 3d ago against content hash 41ddefd24f43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

new-spec 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/skills/new-spec/SKILL.md · 49 lines

What it actually says

Crea una nueva especificación de cambio cuyo nombre está en $ARGUMENTS.

  1. Lee specs/README.md para conocer el flujo de trabajo de las especificaciones, la convención de nombres de carpeta y qué espera cada sección de la plantilla. Sigue ese documento si difiere de los pasos siguientes.
  2. Convierte $ARGUMENTS en <change-name> con formato slug (minúsculas, separado por guiones).
  3. Calcula NNNN: el mayor prefijo numérico de 4 dígitos existente en specs/ y specs/archive/ (si existe), más uno; si no hay ninguna, 0001.
  4. Copia todo el directorio specs/_template/ a specs/NNNN-<change-name>/ (conserva cada archivo de la plantilla).
  5. En los archivos copiados, completa los metadatos obvios:
    • El título del cambio (la forma legible de $ARGUMENTS)
    • Estado: Borrador
    • Fecha: la fecha de hoy (YYYY-MM-DD)
    • Deja problem, goals, non-goals y approach como indicaciones para la persona autora.
  6. Rellena «Evidencia» antes que el objetivo: quién pagaría y qué lo respalda, si ya existe, y qué experimento se hizo. Mira primero docs/product/roadmap.md — puede que la respuesta ya esté. En una fix/* o de tooling, escribe «No aplica: corrección»: la sección existe para decidir qué construir, no para dar teatro a lo que ya está roto.
  7. Ata la spec al roadmap. Lee docs/product/roadmap.md y rellena el campo Ítem de roadmap de proposal.md con la versión y el ítem literal que esta spec completa. Si hay varios candidatos, pregunta con AskUserQuestion en vez de elegir por tu cuenta. Si no existe ningún ítem que encaje, dilo: o se añade al roadmap ahora, o el cambio debería contrastarse antes contra el roadmap (¿entra en esta versión?, ¿qué sale a cambio?). Anota también la spec junto al ítem en el roadmap ((specs/NNNN-<slug>/)).
  8. Si specs/README.md mantiene un índice de especificaciones, añade una entrada para la nueva especificación.
  9. Informa la ruta del directorio creado y enumera los archivos que la persona autora aún debe completar.

Ejemplo: /new-spec rediseño del checkout → specs/0007-checkout-redesign/ (si la última especificación era la 0006).

Rama ↔ spec: la rama que implemente esta spec debe llamarse feat/<change-name> (o fix/<change-name>) — mismo slug. El hook spec-guardrails.sh bloquea editar código en ramas feat/*/fix/* cuya spec no exista, así que crea la spec ANTES de crear la rama de implementación (o desde la rama, antes de tocar código). El hook también bloquea mientras proposal.md, design.md o tasks.md conserven líneas de la plantilla sin rellenar: deja los archivos completos (o borra las secciones que no apliquen) antes de implementar.

NO empieces a implementar el cambio, y NO elimines ni sobrescribas una carpeta de especificación existente — si ya existe alguna specs/*-<change-name>/ (con cualquier prefijo NNNN-; el nombre sin prefijo no va a existir nunca), detente y pregunta.

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 Changed · +21 lines 41ddefd24f43
  2. 10d ago First seen · 28 lines · 90 tokens per session scan A 02632201d957

Subscribe to this mod's changes

new-spec is a skill published in the GitHub repository brayandiazc/project-starter-template-es-ai (15 stars, last pushed 4d ago), licensed MIT. It adds 90 tokens to every session and 921 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 2026-09-01.

Claude CodePlanningagentsagents-mdaiplantillaproyectos
Related

Other skills, from other repositories

cloudron-app-packaging

Official Cloudron app packaging skill - Dockerfile patterns, manifest, addons, build methods.

marcusquinn/aidevops · 23 tokens

cloudron-app-publishing

Distribute Cloudron apps via CloudronVersions.json version catalogs.

marcusquinn/aidevops · 18 tokens

image-mosaic

Tiled image mosaic, photo mosaic, image mosaic, collage wallpaper, image grid background, and mozaic asset pipeline from approved real source imagery.

marcusquinn/aidevops · 33 tokens

proxmox-full

Complete Proxmox VE hypervisor management via REST API - VMs, containers, snapshots, backups, storage.

marcusquinn/aidevops · 27 tokens

cloudflare-platform-skill

Cloudflare platform development guidance — patterns, gotchas, decision trees, SDK usage for Workers, Pages, KV, D1, R2, AI, Durable Objects, and 60+ products. Use when building or developing ON the Cloudflare platform. For managing Cloudflare resources (DNS, WAF, DDoS, R2 buckets, Workers deployments), use the…

marcusquinn/aidevops · 89 tokens

chromium-debug-use

Attach to a user's already-open Chromium-family browser for live inspection and light interaction after explicit local approval.

marcusquinn/aidevops · 24 tokens