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 glosario-vivogit 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/glosario-vivo)<a href="https://agentmods.dev/skills/contactandrewchl-wq/turtle-mcp/glosario-vivo"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/glosario-vivo/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/glosario-vivo"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/glosario-vivo.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 | $0.00088 | $0.00593 |
| Opus 5 | $0.00044 | $0.00296 |
| Sonnet 5 | $0.00018 | $0.00119 |
| Haiku 4.5 | $0.00009 | $0.00059 |
Grade A, and why
glosario-vivo 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
Glosario vivo — las mismas palabras, el mismo significado
El problema que resuelve
En un proyecto largo, la persona y el agente desarrollan un vocabulario propio ("el bus", "la malla", "el consejo", "perfil"). Sin registro, cada sesión nueva reinterpreta esos términos desde cero, y dos sesiones pueden entender cosas distintas por la misma palabra. El glosario convierte ese vocabulario en memoria consultable.
Cuándo guardar un término
- La persona usa un término propio del proyecto que no es obvio por el código.
- Un término genérico tiene un significado específico aquí (p. ej. "spawn" = proceso del SO, NO sub-agente).
- Hubo un malentendido por una palabra: la señal más fuerte de que falta la entrada.
Cómo guardarlo
Una memoria por término, evolutiva (se actualiza, no se duplica):
memory_save(
tipo: "convention",
topic_key: "glosario/<término-en-minúsculas>",
titulo: "Glosario: <término>",
contenido: "<término> = <definición en una o dos frases>. Ejemplo: <uso real>. NO confundir con: <el malentendido que motivó la entrada>."
)
Cómo consultarlo
- Al arrancar una tarea que toca un área con vocabulario propio:
memory_search("glosario <área o término>"). - Ante la duda de qué quiso decir la persona con una palabra: busca el término en el glosario ANTES de preguntar; pregunta solo si no está.
- Si la persona usa el término de forma incompatible con la entrada, muéstrale la definición guardada y pregunta cuál vale: puede que el significado haya evolucionado — actualiza la entrada con el mismo
topic_key(el historial queda enmemory_history).
Regla de oro
Una palabra con entrada en el glosario se usa SIEMPRE con ese significado, en la salida a la persona y en las memorias nuevas. Si el significado cambió, se cambia la entrada, no el uso.
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 · 42 lines · 88 tokens per session scan A 3076a38d55f3
glosario-vivo is a skill published in the GitHub repository contactandrewchl-wq/turtle-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 593 once invoked, about $0.0004 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
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-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-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-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…
knowledge-base
Skill "knowledge-base" from Pinvou/pinvou-agent, covering ima knowledge base, operations, routing rules, examples and file upload guard.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.