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 turtle-protocolgit 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/turtle-protocol)<a href="https://agentmods.dev/skills/contactandrewchl-wq/turtle-mcp/turtle-protocol"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/turtle-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/contactandrewchl-wq/turtle-mcp/turtle-protocol"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/turtle-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 | $0.00047 | $0.00524 |
| Opus 5 | $0.00023 | $0.00262 |
| Sonnet 5 | $0.00009 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
turtle-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.
What it actually says
Protocolo de memoria de Turtle
Turtle te da memoria persistente entre sesiones y coordinación con otros agentes, vía sus herramientas MCP. Seguí este protocolo.
Al empezar (o tras una compactación)
- El hook
session-startya te inyectó las memorias recientes del proyecto. Si necesitás más, usámemory_searchycontext_get. - Tras una compactación de contexto, no reconstruyas de memoria: recuperá con
context_get(proyecto + tarea) ymemory_searchlo que te falte.
Antes de responder algo no trivial
- Buscá primero:
memory_search "<términos>"en el proyecto actual. Si hay una decisión, convención o corrección previa, respetala. - Recuperá el contenido completo solo cuando lo necesites:
memory_get(id). Cuidá el presupuesto de tokens; el índice ya trae título y resumen.
Cuándo guardar (memory_save)
Guardá cuando aparezca algo que valga la pena recordar entre sesiones:
- decision — una decisión de diseño y su porqué.
- architecture — cómo está estructurado algo.
- correction — un error y cómo se corrigió (para no repetirlo).
- convention — una convención del proyecto.
- note — cualquier otra cosa útil.
No guardes lo trivial ni lo que ya está en el código/README. Un buen summary de una línea hace barata la búsqueda.
Coordinación entre agentes
- Si trabajás como un rol declarado, los relevos pendientes te llegan al iniciar sesión.
- Para dejarle algo a otro rol:
message_send(dirigido a un rótulo o por difusión). Para ver actividad:events_list; para ver quién está activo:agents_list.
Idioma
Respondé a la persona en español latino neutro (sin voseo regional marcado ni anglicismos innecesarios), salvo que te pida otro idioma.
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 · 47 lines · 47 tokens per session scan A 3929da7568af
turtle-protocol is a skill published in the GitHub repository contactandrewchl-wq/turtle-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 524 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
simplicio-compress
Cut output and memory tokens without losing meaning — terse prose levels (caveman-style) that preserve code/paths/URLs byte-for-byte, plus a one-time memory/doc compaction pass that pays back every future turn. Use when replies or worker reports are verbose, when standing context (CLAUDE.md/AGENTS.md/notes) is…
simplicio-learn
Persist what a run taught you so the next run is cheaper and more correct — mine high-signal lessons from the trajectory, dedup them, and write them back to AGENTS.md / memory so they're applied not re-derived. Use after a run or at session end, when the user says "remember this", "do a retrospective", "learn from…
simplicio-runtime
Govern and execute Simplicio workflows through native execution, MCP, gates, checkpoints, receipts, backpressure, pools, memory, and subagents. Use when a task needs durable evidence, controlled side effects, native acceleration, MCP compatibility, or Runtime reconciliation. Do not make Loop depend on Runtime for…
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".
recover-context
Extract full context of the last task from the most recent parent session shown in the session lineage. Strategically uses sub-agents to avoid bloating your own context.
knowledge-base
Skill "knowledge-base" from Pinvou/pinvou-agent, covering ima knowledge base, operations, routing rules, examples and file upload guard.