A skill-building workflow for creating reusable instructions that guide an AI coding agent through a task. It offers a quick interview for simple skills and a more complete design process for advanced ones.

Use it to create a new skill, decide what should activate it, define how it should behave, and organize scripts or reference files for more involved skills.

It turns a vague idea into a defined skill with clear inputs, outputs, triggers, rules, and optional supporting files. This reduces the work of designing and packaging agent instructions by hand.

skill-forge — Skill for Claude Code and Codex by ingjaviergomezm

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.

Any agent

npx skills add ingjaviergomezm/el-camello --skill skill-forge

Clone the repo

git clone --depth 1 https://github.com/ingjaviergomezm/el-camello

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ingjaviergomezm/el-camello/skill-forge/github.svg)](https://agentmods.dev/skills/ingjaviergomezm/el-camello/skill-forge)

Your own site

<a href="https://agentmods.dev/skills/ingjaviergomezm/el-camello/skill-forge"><img src="https://agentmods.dev/badge/skills/ingjaviergomezm/el-camello/skill-forge/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ingjaviergomezm/el-camello/skill-forge"><img src="https://agentmods.dev/badge/skills/ingjaviergomezm/el-camello/skill-forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,051 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.

Model	Per session	Once invoked
Fable 5.1	$0.00093	$0.01051
Opus 5	$0.00046	$0.00526
Sonnet 5	$0.00019	$0.00210
Haiku 4.5	$0.00009	$0.00105

Measured 9d ago against content hash 474a41734498, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

skill-forge 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 9d 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.

skills/skill-forge/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Forge: La Fragua de Habilidades

Combina la entrevista humana amigable con la ingeniería técnica profesional en un solo flujo.

Paso 0: Selección de Modo

Al activarse, pregunta al usuario:

"¿Necesitas una skill rápida (entrevista ligera, resultado inmediato) o una skill avanzada (arquitectura completa con scripts, archivos de referencia y empaquetado profesional)?"

Si el usuario no está seguro, usa Modo Rápido por defecto. Siempre podrá escalar después.

Modo Rápido

Fase 1: Entrevista Interactiva

Regla de oro: Haz solo 1-2 preguntas por turno. No abrumes al usuario.

Objetivo Principal: ¿Qué problema específico resuelve esta skill?
Contexto (RAG): ¿Tienes archivos de ejemplo que pueda leer? (Si da rutas, léelos antes de continuar).
Disparadores: ¿Qué frases deberían activar esta skill? (para el description del frontmatter YAML).
Entradas y Salidas: ¿Qué recibe el agente y qué formato de respuesta esperas?
Reglas o Casos Borde: ¿Alguna directriz especial de formato, tono u otras condiciones?
Ubicación: ¿Global (~/.gemini/antigravity/skills/) o específica del Workspace (.agent/skills/)?

Fase 2: Diseño del SKILL.md

Estándar obligatorio:

Frontmatter YAML (---): name (minúsculas con guiones) + description (cuándo activarse, palabras clave).
Rol y Propósito: Quién es el agente y cómo se comporta.
Instrucciones paso a paso con manejo de excepciones.
Estructura de Salida en formato Markdown claro.

Fase 3: Creación Automática

No pidas al usuario que cree nada manualmente:

Crea la carpeta y subcarpetas (references/, scripts/, assets/) según necesidad.
Escribe el SKILL.md directamente con la herramienta de creación de archivos.
Confirma al usuario que la skill está lista para invocarse.

Fase 4: Oferta de Escalamiento

Al finalizar, pregunta:

"¿Deseas escalar esta skill al Modo Avanzado para añadir scripts reutilizables, archivos de referencia y empaquetado profesional?"

Read the full file on GitHub · 88 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.

9d ago First seen · 88 lines · 93 tokens per session scan A 474a41734498

Subscribe to this mod's changes

skill-forge is a skill published in the GitHub repository ingjaviergomezm/el-camello (2 stars, last pushed 4mo ago), licensed MIT. It adds 93 tokens to every session and 1,051 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.

Building agents agentic-ai ia

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

mochi-remind

Handle due reminders — notify the user with natural language and mark them done.

kirodotdev/KiroCrew · 20 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens