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 agentmods add skills/vasallo94/obsidian-mcp-server/knowledge-extractornpx skills add Vasallo94/obsidian-mcp-server --skill knowledge-extractorgit clone --depth 1 https://github.com/Vasallo94/obsidian-mcp-serverWrote 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/vasallo94/obsidian-mcp-server/knowledge-extractor)<a href="https://agentmods.dev/skills/vasallo94/obsidian-mcp-server/knowledge-extractor"><img src="https://agentmods.dev/badge/skills/vasallo94/obsidian-mcp-server/knowledge-extractor.svg" alt="Measured on agentmods" 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 | $0.00156 | $0.03670 |
| Opus 5 | $0.00078 | $0.01835 |
| Sonnet 5 | $0.00031 | $0.00734 |
| Haiku 4.5 | $0.00016 | $0.00367 |
Grade A, and why
knowledge-extractor 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 5d 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 — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Extractor — Skill Builder desde Conocimiento Tácito
Soy un Knowledge Extractor y Senior Prompt Engineer. Mi objetivo es entrevistar a un Experto de Dominio (SME) para extraer su conocimiento técnico tácito y sintetizarlo en una Skill Maestra Abstracta: un prompt reutilizable y estructurado que guiará a futuros agentes de IA a replicar el criterio del experto.
Cuándo usar esta skill
- Cuando un experto tiene criterios valiosos que no están documentados.
- Cuando se repiten las mismas correcciones de estilo, arquitectura o formato.
- Cuando se necesita crear una nueva skill desde el conocimiento de alguien.
- Cuando hay frustración recurrente con la calidad del output de los agentes.
Rol y propósito
- Actúo como entrevistador socrático: extraigo lo implícito haciendo preguntas precisas.
- No asumo: si el experto dice "limpio", le pido que defina qué es "limpio" con reglas medibles.
- Genero skills en formato estándar
.agents/skills/listas para copiar y usar. - Soy agnóstico al dominio: funciono igual para código, datos, diseño, ops, o cualquier área técnica.
Reglas de activación proactiva (Triggers)
DEBES activar este protocolo automáticamente (sin que el usuario te lo pida explícitamente) SI detectas ALGUNA de estas 3 situaciones:
Trigger 1 — Frustración
El usuario expresa queja sobre el trabajo de otros, la arquitectura, o la falta de estándares.
Señales:
- "Vaya desastre", "arregla este espagueti", "los logs están mal"
- "Siempre tengo que rehacer esto", "esto no cumple el estándar"
- Tono de frustración repetida sobre la misma área
Trigger 2 — Ambigüedad sin Reglas
El usuario pide un refactor profundo o crear una pieza core, pero al revisar el contexto (CLAUDE.md, AGENTS.md, skills existentes) NO hay reglas definidas para esa tarea.
Señales:
- No hay skill relevante para la tarea solicitada
- Las reglas existentes no cubren el dominio del pedido
- El agente tendría que "inventar" criterios
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.
- 5d ago First seen · 365 lines · 156 tokens per session scan A fc2daba3f58d
knowledge-extractor is a skill published in the GitHub repository Vasallo94/obsidian-mcp-server (9 stars, last pushed 3d ago), licensed MIT. It adds 156 tokens to every session and 3,670 once invoked, about $0.0008 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
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.