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 ingjaviergomezm/el-camello --skill master-orchestratorgit clone --depth 1 https://github.com/ingjaviergomezm/el-camelloWrote 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/ingjaviergomezm/el-camello/master-orchestrator)<a href="https://agentmods.dev/skills/ingjaviergomezm/el-camello/master-orchestrator"><img src="https://agentmods.dev/badge/skills/ingjaviergomezm/el-camello/master-orchestrator/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/ingjaviergomezm/el-camello/master-orchestrator"><img src="https://agentmods.dev/badge/skills/ingjaviergomezm/el-camello/master-orchestrator.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 | $0.00090 | $0.00849 |
| Opus 5 | $0.00045 | $0.00425 |
| Sonnet 5 | $0.00018 | $0.00170 |
| Haiku 4.5 | $0.00009 | $0.00085 |
Grade A, and why
master-orchestrator 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 11d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Master Orchestrator (El Director de Proyectos)
Siempre que el usuario solicite un proyecto complejo que requiera múltiples recursos, formatos o habilidades, DEBES invocar estrictamente este flujo antes de escribir una sola línea de código.
El objetivo principal es evitar soluciones "genéricas de un solo clic" y fomentar la co-creación profunda con el usuario.
Reglas de Oro
- Pausa y Piensa: Nunca inicies la programación de herramientas complejas (DOCX, PPTX, React) de golpe.
- Co-Trabajo Interactivo: El usuario es perfeccionista. Debe aprobar el flujo, los textos base y cada entregable individual.
- Respeta las Fases de cada Skill: Si usas
doc-coauthoring, ejecuta sus fases de entrevista. Si usaspptx, ejecuta su QA visual. Sin atajos. - Brand First: Antes de generar cualquier documento visual, busca si existe alguna skill
brand-*en el directorio de skills (~/.gemini/antigravity/skills/). Si existe, aplícala como contexto obligatorio de identidad. Los Brand Books siempre tienen prioridad sobre los temas genéricos detheme-factory.
Detección de Complejidad
Antes de iniciar el flujo completo, evalúa la complejidad del proyecto:
- Tarea Simple (1 skill, 1 formato → ej. "resume esta reunión"): Ejecutar la skill directamente. No necesitas Discovery ni planificación.
- Tarea Media (2-3 skills → ej. "hazme un documento de marca"): Discovery breve + Ejecución con checkpoint al final.
- Tarea Compleja (4+ skills, múltiples formatos → ej. "crea un pitch con manual, presentación y web"): Flujo completo de 5 fases obligatorio.
Pasos del Flujo (para Tareas Medias y Complejas)
1. Fase de Diagnóstico (Discovery)
Pregunta al usuario:
- ¿Cuál es el objetivo final?
- ¿Quién es la audiencia objetivo?
- ¿Existen materiales previos (Brand Books, borradores, identidad visual)?
2. Selección del Escuadrón (Stack Selection)
Consulta el Registro de Capacidades en references/capabilities-registry.md dentro de esta skill.
Presenta al usuario qué especialistas se usarán y por qué.
What ships with it
1 file 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.
- 11d ago First seen · 59 lines · 90 tokens per session scan A ed613a2c8221
master-orchestrator is a skill published in the GitHub repository ingjaviergomezm/el-camello (2 stars, last pushed 4mo ago), licensed MIT. It adds 90 tokens to every session and 849 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
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
pr-review-triage
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
issue-triage
Scan open issues and discussions, deduplicate, prioritize, and propose labels. Provides a clean actionable queue.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.