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 orchestrator-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/orchestrator-protocol)<a href="https://agentmods.dev/skills/cruzs85/opencode-multiagente-local-37-iterations/orchestrator-protocol"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/orchestrator-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/orchestrator-protocol"><img src="https://agentmods.dev/badge/skills/cruzs85/opencode-multiagente-local-37-iterations/orchestrator-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 | $0.00063 | $0.00751 |
| Opus 5.5 | $0.00025 | $0.00300 |
| Sonnet 5.5 | $0.00013 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
orchestrator-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 2mo 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator Protocol — Anti-contradicción
Objetivo
Evitar que el orquestador dé instrucciones a un subagente que contradigan las herramientas, métodos y reglas que ese subagente tiene configuradas en su prompt interno.
Regla de oro
No le exijas a un subagente usar herramientas distintas a las que su prompt le ordena.
Procedimiento obligatorio
Antes de enviar cualquier instrucción a un subagente, el orquestador DEBE:
Paso 1: Leer el prompt del subagente destino
Consultar opencode.json en la raíz del proyecto, sección agent.<nombre-del-agente>.prompt, para conocer:
- Qué herramientas tiene permitidas (
edit,bash, etc.) - Qué métodos de trabajo prefiere (ej:
bash + catpara archivos completos vseditpara cambios parciales) - Qué comandos específicos puede ejecutar (ej:
npm run build*pero no otros)
Paso 2: Alinear las instrucciones
Asegurarse de que las instrucciones que se van a dar usan EXACTAMENTE las herramientas y métodos que el subagente tiene configurados.
Paso 3: No forzar herramientas no autorizadas
Si el subagente tiene edit: deny (como qa-validator), no se le debe pedir que edite archivos. Si solo tiene permitido npm run build* y npm test*, no se le debe pedir que ejecute otros comandos.
Casos concretos
| Subagente | Tiene configurado | Qué NO pedirle |
|---|---|---|
code-writer |
bash + cat para archivos completos, edit para cambios parciales |
edit para archivos completos (debe usar cat) |
qa-validator |
Solo npm run build*, npm test*, npm run lint* |
Que ejecute npx, ls, cat, git |
package-manager |
npm install*, ng *, npx *, mkdir, cp, mv, rm, cat |
Que edite archivos de código (usa bash+cat para archivos completos) |
e2e-validator |
Solo npx playwright test* |
Que ejecute builds o instale paquetes |
unit-tester |
edit solo para *.spec.ts, bash solo npm test* |
Que modifique archivos de implementación |
decomposer |
Solo skill.* |
Que ejecute bash, edite archivos o use task |
explorer / researcher |
Solo skill.* y webfetch (researcher) |
Que ejecute bash o edite archivos |
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.
- 2mo ago First seen · 36 lines · 63 tokens per session scan A a811a7c9942d
orchestrator-protocol is a skill published in the GitHub repository cruzs85/opencode-multiagente-local-37-iterations (5 stars, last pushed 3mo ago), licensed MIT. It adds 63 tokens to every session and 751 once invoked, about $0.0003 per session on Opus 5.5. 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.
orchestrator-protocol compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| orchestrator-protocolcruzs85/opencode-multiagente-local-37-iterations | Skill | 5 | 3mo ago | MIT | A | 63 | OpenCode |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 3d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 6d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |