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 cruzs85/opencode-multiagente-local-37-iterations --skill delegation-protocolgit clone --depth 1 https://github.com/cruzs85/opencode-multiagente-local-37-iterationsWrote 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/cruzs85/opencode-multiagente-local-37-iterations/delegation-protocol)<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/delegation-protocol"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/delegation-protocol/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/cruzs85/opencode-multiagente-local-37-iterations/delegation-protocol"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/delegation-protocol.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 | $0.00053 | $0.01282 |
| Opus 5 | $0.00026 | $0.00641 |
| Sonnet 5 | $0.00011 | $0.00256 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
delegation-protocol 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 10d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegation Protocol — Instrucciones claras para code-writer
Objetivo
Estructurar las tareas que el orquestador delega a code-writer para evitar que code-writer confunda contenido del archivo con instrucciones de ejecución.
Regla de oro
** Separa siempre qué escribir de cómo ejecutarlo.**
Formato obligatorio
Usa estos marcadores para delimitar cada sección:
Para creación de archivos nuevos
=== CONTENIDO DEL ARCHIVO ===
[archivo: ruta/absoluta/al/archivo]
[tipo: TypeScript | HTML | SCSS | JSON | Markdown]
[Comportamiento esperado: descripción de lo que debe hacer]
[Estructura completa: propiedades, métodos con tipos, lógica]
=== INSTRUCCIONES ===
[Método: bash heredoc (cat > ruta << 'EOF')]
[Skills a cargar: json-safe-edit]
[Pasos específicos para la ejecución]
Para modificación de archivos existentes (code .ts, .html, .scss)
Sigue el formato de partial-edit-protocol como base, y además:
=== FRAGMENTO A CAMBIAR ===
[archivo: ruta/absoluta/al/archivo]
[Contexto antes/después con líneas de referencia]
[Líneas exactas a modificar]
=== INSTRUCCIONES ===
[Método: edit]
[Resto del archivo debe mantenerse intacto]
[Skills a cargar si aplica]
Para modificar JSON (especialmente opencode.json)
** NO uses === CONTENIDO DEL ARCHIVO ===.** Las modificaciones de propiedades JSON no escriben un archivo completo, solo cambian una propiedad. Usa solo === INSTRUCCIONES === con el comando exacto.
En lugar de incluir el valor largo en el comando (riesgo de colisión de comillas entre bash y JavaScript), escribe el valor en un archivo temporal primero:
Paso 1 — Preparar el valor:
=== INSTRUCCIONES (paso 1) ===
[Método: bash heredoc]
[Escribe el nuevo valor del prompt en /tmp/nuevo_valor.txt:]
cat > /tmp/nuevo_valor.txt << 'EOF'
Aquí el texto del prompt con "comillas" y 'simples'
EOF
[Carga json-safe-edit antes de continuar]
Paso 2 — Aplicar la modificación:
=== INSTRUCCIONES (paso 2) ===
[Método: node -e programático leyendo desde /tmp/]
[Comando:]
node -e "
const fs = require('fs');
const ruta = 'opencode.json';
const nuevoValor = fs.readFileSync('/tmp/nuevo_valor.txt', 'utf8');
const doc = JSON.parse(fs.readFileSync(ruta, 'utf8'));
doc.agent.X.prompt = nuevoValor;
fs.writeFileSync(ruta, JSON.stringify(doc, null, 2) + '\n');
console.log('✅ JSON actualizado');
"
[Validar JSON post-edición]
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.
- 10d ago First seen · 119 lines · 53 tokens per session scan A 17d229c84f1a
delegation-protocol is a skill published in the GitHub repository cruzs85/opencode-multiagente-local-37-iterations (5 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,282 once invoked, about $0.0003 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…