pucp-context

pucp-context is a skill for Claude Code, Codex from Hellowda253/KIT-PUCP-MCP. It costs 51 tokens per session (489 once invoked), scanned A, original, MIT.

A source-checking guide for students at PUCP, a university in Peru, who need current information about university services and procedures. It directs questions to official sources and distinguishes public institutional facts from personal academic records or tutoring.

In plain words
What is it for?
Use it to find and verify official information about regulations, calendars, payments, scholarships, wellbeing, libraries, mobility, employability, and other PUCP services.
Why use it?
University rules, dates, costs, and procedures can change, so relying on memory may give an outdated or incorrect answer.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the pucp-mcp plugin — 3 skills shipped together

Good fit Use it to find and verify official information about regulations, calendars, payments…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hellowda253/kit-pucp-mcp/pucp-context
Install

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.

Any agent
npx skills add Hellowda253/KIT-PUCP-MCP --skill pucp-context
Clone the repo
git clone --depth 1 https://github.com/Hellowda253/KIT-PUCP-MCP

Made for: Claude Code, Codex.

Or install pucp-mcp, the plugin that ships this one along with the rest of its 3 skills.

Wrote 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.

agentmods badge for pucp-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/hellowda253/kit-pucp-mcp/pucp-context.svg)](https://agentmods.dev/skills/hellowda253/kit-pucp-mcp/pucp-context)
Your own site
<a href="https://agentmods.dev/skills/hellowda253/kit-pucp-mcp/pucp-context"><img src="https://agentmods.dev/badge/skills/hellowda253/kit-pucp-mcp/pucp-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 489 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.00489
Opus 5 $0.00026 $0.00244
Sonnet 5 $0.00010 $0.00098
Haiku 4.5 $0.00005 $0.00049

Measured 6d ago against content hash b9dbe6554185, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pucp-context 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 6d 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.

skills/pucp-context/SKILL.md · 28 lines

How it starts

The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contexto PUCP

Orienta consultas institucionales públicas de pregrado, posgrado y Educación Continua: reglamentos, procedimientos, calendarios, costos, becas, bienestar, bibliotecas, movilidad, empleabilidad, contactos y servicios. Funciona como enrutador de evidencia, no como una enciclopedia estática.

Para datos personales —notas, cursos, horario, matrícula, deuda o solicitudes— usa pucp-academic. Para enseñar, resolver ejercicios o mejorar rendimiento usa profe-pucp.

Buscar la fuente adecuada

  • Información pública que cambia: consulta la web oficial en vivo.
  • Procedimientos: usa la guía vigente de Ágora o del Portal del Estudiante y, si hay consecuencias académicas o económicas, contrasta la norma aplicable.
  • Reglamentos: prioriza el documento vigente y la fuente de la unidad competente.
  • Investigación: usa Biblioteca, Repositorio Institucional o Revistas PUCP.

Cargar el catálogo de fuentes oficiales solo cuando necesites descubrir o comparar una fuente. Busca por categories, target_audience y consult_when; el catálogo contiene puntos de entrada, no respuestas finales. Revalida contenido dynamic o per_cycle y verifica también lo estable cuando se requiera vigencia jurídica.

Autoridad y respuesta

Una página bajo dominio PUCP es fuente primaria. Un servicio externo solo hereda autoridad si una página oficial lo enlaza; conserva esa página como procedencia. Ante conflicto entre fuentes, compara ámbito, fecha y autoridad: norma o fuente específica aplicable, fuente institucional general y luego tutorial. Expón cualquier discrepancia material.

No uses redes sociales, blogs ni resultados del buscador como fuente normativa. No compartas enlaces con cookies, tokens, sesión SSO, formularios transaccionales o datos personales.

Da primero la respuesta útil, enlaza la página exacta e indica fecha o ciclo cuando afecte la validez. Distingue confirmación de inferencia. Si no hay evidencia pública suficiente, indica el canal oficial competente sin inventar reglas ni contactos.

Read the full file on GitHub · 28 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 6d ago First seen · 28 lines · 51 tokens per session scan A b9dbe6554185

Subscribe to this mod's changes

pucp-context is a skill published in the GitHub repository Hellowda253/KIT-PUCP-MCP (3 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 489 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

lecture-to-hw

A workflow for turning course materials and assignment files into concise Markdown homework answers. It can use PDFs, documents, slides, code, images, and earlier solutions as references.

vect-G/lecture-to-hw · 124 tokens

normalize-yonsei-courses

Query authorized Yonsei Underwood handbook rows directly, then normalize them or fallback screenshot, PDF, spreadsheet, pasted table, export, or JSON into stable course-planning data. Use when course data has Korean or English fields, campus aliases, Korean weekday/time strings, mixed section identifiers, or needs…

mrcha033/yonsei-skills · 74 tokens

plan-yonsei-mileage-strategy

Read a student's authorized Underwood mileage history and combine it with current capacity, applicant counts, catalogue data, tie-break context, graduation importance, and alternatives to plan a risk-aware Yonsei course-registration strategy. Use when a student asks how much mileage to put on each course or wants a…

mrcha033/yonsei-skills · 69 tokens

manage-learnus-session

Connect to Yonsei LearnUs in the student's persistent browser profile, reuse the official portal login, and recover from session expiry without receiving credentials in chat. Use when LearnUs login is required, a browser session expired, or the student asks to stay signed in; use the optional terminal session only…

mrcha033/yonsei-skills · 75 tokens

calculate-yonsei-graduation-progress

Read the student's authorized Underwood credit-progress table and calculate advisory Yonsei graduation progress from official entry-year, college, and major requirements. Use when a student asks what graduation requirements are complete, what credits or required courses remain, or whether a planned course can fill a…

mrcha033/yonsei-skills · 64 tokens

summarize-yonsei-today

A read-only daily briefing for Yonsei students, combining accessible information about classes, scholarships, mileage, graduation, teaching progress, LearnUs, attendance, and campus tasks.

mrcha033/yonsei-skills · 73 tokens