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 handoff-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/handoff-protocol)<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/handoff-protocol"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/handoff-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/handoff-protocol"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/handoff-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 | $0.00037 | $0.01594 |
| Opus 5 | $0.00018 | $0.00797 |
| Sonnet 5 | $0.00007 | $0.00319 |
| Haiku 4.5 | $0.00004 | $0.00159 |
Grade A, and why
handoff-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 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff Protocol — Sistema de delegación entre agentes
Principio fundamental
build usa task() directo por defecto. Handoff solo cuando el contenido a transferir ya fue generado por otro agente.
Esto minimiza tokens de build (modelo API online) y mueve el costo de escritura/lectura a los modelos locales (Ollama).
Regla de decisión
| build origina la tarea | → task() directo con instrucciones inline |
|---|---|
| Subagente A produce output para subagente B | → A escribe handoff, build pasa solo la ruta a B |
Gestión de handoffs
El orquestador (build) gestiona todos los handoffs. Los agentes NO buscan ni asignan handoffs automáticamente. build indica la ruta exacta a cada agente.
⚠️ Generación de session_id con timestamp real (OBLIGATORIO)
build DEBE generar timestamps reales, NO hardcodear 000000. Para ello, build necesita permiso bash para ejecutar:
node -e "const d=new Date();const pad=n=>String(n).padStart(2,'0');console.log(pad(d.getDate())+'-'+pad(d.getMonth()+1)+'-'+String(d.getFullYear()).slice(2)+'-'+pad(d.getHours())+pad(d.getMinutes())+pad(d.getSeconds()))"
El output (ej: 09-06-26-143000) se usa como session_id. Para carpetas de agente (code-writer143000, verifier143000), se extrae HHMMSS del mismo timestamp.
Configuración necesaria en opencode-v1.json para build:
"bash": {
"*": "deny",
"node -e *console.log(Date.now())*": "allow",
"node -e *new Date()*": "allow",
"node -e *pad(Date*": "allow"
}
Estructura de directorios
/tmp/handoff/{idSession}/
├── (raíz, build delega a code-writer para crearla)
├── {agente_destino}{hh:mm:ss}/
│ └── tarea1.json
│ └── tarea2.json
└── {agente_destino}{hh:mm:ss}/
└── tarea1.json
| Variable | Descripción |
|---|---|
{idSession} |
ID único DD-MM-AA-HHMMSS. Lo genera build. Conocido por todos los agentes de la sesión. |
{agente_destino} |
Agente que ejecutará la tarea (code-writer, verifier, qa-validator, ui-designer). |
{hh:mm:ss} |
Timestamp de creación. build lo usa para generar nombres de carpeta únicos y ordenar asignaciones. |
tareaN.json |
Archivo JSON con especificación de una tarea nuclear (unidad atómica ejecutable). |
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 · 130 lines · 37 tokens per session scan A 705c6ef756db
handoff-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 37 tokens to every session and 1,594 once invoked, about $0.0002 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…