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 contactandrewchl-wq/turtle-mcp --skill agent-orchestrationgit clone --depth 1 https://github.com/contactandrewchl-wq/turtle-mcpWrote 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/contactandrewchl-wq/turtle-mcp/agent-orchestration)<a href="https://agentmods.dev/skills/contactandrewchl-wq/turtle-mcp/agent-orchestration"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/agent-orchestration/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/contactandrewchl-wq/turtle-mcp/agent-orchestration"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/agent-orchestration.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 | $0.00043 | $0.02615 |
| Opus 5 | $0.00022 | $0.01307 |
| Sonnet 5 | $0.00009 | $0.00523 |
| Haiku 4.5 | $0.00004 | $0.00262 |
Grade A, and why
agent-orchestration 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orquestación de agentes (sobre el bus de Turtle)
Coordinar varias personas/agentes que trabajan hacia una misma meta, secuenciando, relevando y desbloqueando el trabajo a través del bus asíncrono de Turtle, sin pisarse y dejando rastro observable.
Cuándo usar
Cuando dos o más personas (rótulos distintos) avanzan sobre una misma meta y hace falta:
- ordenar quién hace qué y en qué momento (secuenciar),
- pasar trabajo de una persona a otra sin perder contexto (relevar),
- destrabar a alguien que espera un insumo (desbloquear),
- evitar que dos personas toquen el mismo módulo a la vez (no pisarse).
Si una sola persona resuelve la meta de punta a punta, no necesitas orquestación: trabaja directo.
Límite de alcance (leer primero)
Turtle NO lanza, spawnea, mata ni controla procesos. El SRS (sección 1.2) lo fija sin ambigüedad: "TURTLE no es un orquestador que lance o controle agentes; la comunicación entre agentes es asíncrona y mediada por la base de datos, no un canal de baja latencia."
Por lo tanto, en Turtle orquestar = secuenciar y relevar trabajo por el bus. Quien ejecuta cada agente es el usuario o el runtime de cada cliente, nunca Turtle.
Está prohibido en esta skill:
- proponer spawnear, lanzar, reiniciar o matar procesos o agentes,
- asumir un canal síncrono de baja latencia entre agentes,
- diseñar cualquier "control" sobre el ciclo de vida de otro agente.
Todo lo que sigue se apoya solo en mensajes asíncronos persistidos en la base.
Matiz ratificado: delegar en un sub-agente del CLI ≠ spawnear un proceso
La prohibición de arriba es sobre procesos del SO que Turtle cree o controle. Es distinto de delegar en un sub-agente nativo del CLI (p. ej. la herramienta Task de Claude Code): a ese sub-agente lo lanza el runtime del cliente, no Turtle, y Turtle no gobierna su ciclo de vida. El dueño lo ratificó: "spawn" = proceso del SO controlado por Turtle (prohibido) ≠ sub-agente Task del CLI (permitido).
Entonces, en clientes multi-agente (Claude Code), orquestar suma una segunda vía además del bus: delegar trabajo y revisión en sub-agentes Task. Sigue valiendo la regla dura —Turtle no lanza ni mata procesos; la coordinación entre personas sigue siendo asíncrona y por el bus—. En CLIs de una sola sesión (Codex, OpenCode) no hay sub-agentes: el patrón degrada a un guion secuencial dentro de la misma sesión.
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 · 126 lines · 43 tokens per session scan A d23c26f46fb8
agent-orchestration is a skill published in the GitHub repository contactandrewchl-wq/turtle-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 2,615 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
gno
Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…
engram-memory
Give the agent durable, local memory with engram — recall past decisions before answering, and persist new decisions, preferences and facts as they happen. Use when work spans sessions or the user says "remember".
simplicio-loop
Unified public entrypoint for Simplicio's body-of-work orchestration: core + loop in one command. Use when the user types /simplicio-loop, says "ralph loop", "keep iterating until done", "finish all open issues", or asks to drain a queue of work autonomously. Runtime-agnostic: binds a real stop-hook where the host…
simplicio-nest-gate
N-Nest protocol — multi-level gate-corrected agent tree. PRIME depth verification, BH port.port.port addressing, per-level confabulation catch.
simplicio-orient
Terminal-first execution — answer facts with the shell, never with the LLM. Use whenever a step needs a fact about the filesystem, git, processes, or system resources, or runs a build/test/lint/diff whose output would flood context. Substitutes deterministic shell/CLI calls for native LLM operations and clamps their…
simplicio-autoresearch
Evolutionary optimize-by-metric loop — mutate a target, evaluate against fixed criteria, KEEP if the score improves (commit) or REVERT if it doesn't (git checkout), repeat, plateau-break after N stagnated runs. Adapts Karpathy's autoresearch pattern (and the ECC autoresearch-agent) with mandatory yool guardrails (§11…