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 JOSETRA44/DUTIC-mcp --skill duticgit clone --depth 1 https://github.com/JOSETRA44/DUTIC-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/josetra44/dutic-mcp/dutic)<a href="https://agentmods.dev/skills/josetra44/dutic-mcp/dutic"><img src="https://agentmods.dev/badge/skills/josetra44/dutic-mcp/dutic/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/josetra44/dutic-mcp/dutic"><img src="https://agentmods.dev/badge/skills/josetra44/dutic-mcp/dutic.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 | $0.00183 | $0.09158 |
| Opus 5.5 | $0.00073 | $0.03663 |
| Sonnet 5.5 | $0.00037 | $0.01832 |
| Haiku 4.5 | $0.00018 | $0.00916 |
Grade A, and why
dutic 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 1mo 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 — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DUTIC — Aula virtual (Moodle UNSA)
Esta skill te conecta al aula virtual DUTIC del usuario para ver sus tareas, cursos, notas y recursos. Existe por un problema concreto y doloroso: Moodle esconde tareas. El "timeline" del estudiante (lo que la mayoría de apps y el propio Moodle muestran) sólo lista tareas accionables: futuras y sin entregar. Una tarea que el profesor crea sin fecha de calendario, o una que ya venció, desaparece de la vista — y el usuario ha perdido notas por no verlas. Tu trabajo es que eso no vuelva a pasar.
Regla de oro: busca siempre las tareas ocultas
Cuando el usuario pregunte qué tiene pendiente, NO te quedes con el timeline. Usa el barrido
completo (scope: "all" en el MCP, o dutic tasks --all en CLI), que recorre todos los cursos
y revela las tareas ocultas. Es unos segundos más lento pero es justo donde están los problemas.
Cómo actuar (flujo recomendado)
- Comprueba la sesión (
dutic_session_statusodutic status). Si no hay sesión válida, el MCP intenta renovarla solo; si no puede, pídele al usuario que ejecutedutic loginen una terminal (el login es OAuth de Google institucional y necesita una ventana de navegador, así que tú no puedes completarlo por él). - Trae las tareas con barrido completo. Prioriza las SIN ENTREGAR: ya vienen ordenadas
por urgencia (pendientes primero, por fecha de entrega). Fíjate en el flag
hidden: truey ensubmission: "not-submitted". - Resume con foco en lo accionable. Encabeza con lo urgente ("Tienes N tareas sin entregar, la más próxima vence el ..."). Señala explícitamente las ocultas y las vencidas. No entierres la alerta en una lista larga.
- Ofrece el siguiente paso: abrir la tarea (tienes su URL), ver el contenido del curso, o descargar los materiales.
Semestres: cada período es un aula distinta
El aula virtual monta un Moodle independiente por semestre (2025A, 2025B, 2026A…), con
sus propios cursos, tareas y notas. Todas las herramientas del aula aceptan un argumento opcional
semester; si lo omites, consultan el semestre activo, que es lo correcto para el 99 % de las
preguntas ("¿qué tengo pendiente?", "¿me subieron notas?").
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.
- 1mo ago Changed · +11 lines fb7bbc73686f
- 1mo ago Changed · +51 lines d4cd7dfec206
- 1mo ago Changed · +57 lines 9f77cc9ef8d6
- 1mo ago First seen · 374 lines · 183 tokens per session scan A ca06ec9d2450
dutic is a skill published in the GitHub repository JOSETRA44/DUTIC-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 183 tokens to every session and 9,158 once invoked, about $0.0007 per session on Opus 5.5. 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.