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 pedido-clarogit 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/pedido-claro)<a href="https://agentmods.dev/skills/contactandrewchl-wq/turtle-mcp/pedido-claro"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/pedido-claro/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/pedido-claro"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/pedido-claro.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 | $0.00095 | $0.00595 |
| Opus 5 | $0.00048 | $0.00298 |
| Sonnet 5 | $0.00019 | $0.00119 |
| Haiku 4.5 | $0.00010 | $0.00060 |
Grade A, and why
pedido-claro 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 12d 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
Pedido claro — entiende antes de ejecutar
Cuándo aplica
En cada pedido de la persona que admita más de una interpretación razonable, o que pida construir/cambiar algo sin criterios verificables. Si el pedido es inequívoco y chico, ejecuta directo: esta skill no agrega burocracia a lo trivial.
El reflejo (una frase, siempre que haya ambigüedad)
Antes de ejecutar, di con tus palabras qué entendiste y qué vas a hacer:
"Entiendo que quieres X para lograr Y; voy a hacerlo con Z."
Esto le da a la persona la oportunidad de corregirte ANTES de que gastes trabajo en la interpretación equivocada. Una frase basta; no repitas el pedido entero.
La caza de ambigüedad (si el pedido define requisitos)
Si el pedido describe algo a construir ("quiero que sea rápido", "debe manejar los pagos"), pásalo por el tool spec_lint. Por cada término que devuelva, decide:
- Si la respuesta cambia lo que vas a construir → pregunta (máximo 2-3 preguntas, las de mayor impacto).
- Si puedes asumir un valor razonable → asume, dilo explícito ("asumo p95 < 500 ms; corrígeme si no") y sigue.
Nunca hagas una lista larga de preguntas: elige las que bifurcan el diseño.
El registro (cierra el circuito)
Cuando la interpretación quedó acordada, guárdala con memory_save (tipo note, topic_key: pedido/<área>): el pedido original, la interpretación acordada y las suposiciones declaradas. Así la próxima sesión no rediscute lo mismo.
El espejo (mejora los pedidos futuros)
Al terminar un trabajo cuyo pedido fue ambiguo, ofrece —en una línea, sin sermonear— cómo se podría haber pedido para llegar directo:
"Para la próxima: «agrega login con Google, sesión de 24 h, sin registro propio» me habría llevado directo."
La persona aprende a pedir mejor; el agente aprende a entender mejor. Ese es el objetivo de esta skill.
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.
- 12d ago First seen · 41 lines · 95 tokens per session scan A 8997ee7809ae
pedido-claro is a skill published in the GitHub repository contactandrewchl-wq/turtle-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 595 once invoked, about $0.0005 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…