agentmods.dev

setup

setup is a skill for Claude Code from southlab-ai/Claude-Plugin-Marketplace. It costs 38 tokens per session (802 once invoked), scanned C, original, MIT.

Setup instructions for connecting Horacio and KG Educación to Claude or Codex using a personal MCP API key. Horacio is a service that retrieves evidence from a private education knowledge base.

In plain words
What is it for?
For obtaining the key, configuring both clients, and refreshing the marketplace, client, and session after an update.
Why use it?
It explains how to authenticate the connection and recover from upgrade-related or unauthorized-request errors without exposing the key in chat.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the kg-educacion plugin — 5 skills, 1 command shipped together

not rated 3repo +1 2mo ago C scan 38 tokens original MIT

Good fit For obtaining the key, configuring both clients, and refreshing the marketplace, client, and session after an update.

Compare 6 skills from other repositories ↓
View source ↗ southlab-ai/Claude-Plugin-Marketplace
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add southlab-ai/Claude-Plugin-Marketplace
Claude Code
/plugin install kg-educacion

Made for: Claude Code.

Or install kg-educacion, the plugin that ships this one along with the rest of its 5 skills, 1 command.

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 setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/setup/github.svg)](https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/setup)
Your own site
<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/setup"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/setup/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.

agentmods 80×15 button for setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/setup"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 802 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00038 $0.00802
Opus 5.5 $0.00015 $0.00321
Sonnet 5.5 $0.00008 $0.00160
Haiku 4.5 $0.00004 $0.00080

Measured 1mo ago against content hash 8ec1e2e4089f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

setup scanned grade C with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

o define `env.HORACIO_MCP_API_KEY` en `~/.claude/settings.json`; reinicia Claude.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

- Claude Code: `.mcp.json` lee `Bearer ${HORACIO_MCP_API_KEY}`. Exporta la variable
plugins/kg-educacion/skills/setup/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configurar Horacio + KG Educación

El plugin conecta al MCP de Horacio. Horacio usa el KG educativo privado e independiente para recuperar evidencia con fuentes y resuelve en cada request los features, colegio y grants vigentes de la cuenta. Las capabilities efímeras para materiales se generan dentro del servidor; el usuario no debe crearlas ni guardar headers adicionales.

Elegir el flujo

  • Si ya existe HORACIO_MCP_API_KEY o el otro cliente funciona, no generes otra key: configura solo el cliente faltante.
  • Si no existe, sigue "Obtener la key".
  • Tras actualizar, conserva la key y refresca marketplace, cliente y sesión.

Obtener la key

  1. Indica al usuario que ingrese a Horacio.
  2. Debe abrir Mi cuenta → API key para Codex y MCP.
  3. Debe crear o regenerar la key y copiarla. Horacio la muestra una sola vez.
  4. No le pidas que pegue la API key en el chat.

Configurar ambos clientes

Resuelve <plugin-root> como dos niveles sobre este SKILL.md; no asumas CLAUDE_PLUGIN_ROOT, porque Codex no define esa variable. Pide al usuario que ejecute en su propia terminal interactiva:

bash "<plugin-root>/scripts/kg-onboard.sh"

El script solicita la key sin eco y configura Claude, Codex, el shell y las apps GUI de macOS. No recibe el secreto como argumento de línea de comandos.

Configurar un cliente con una key existente

  • Claude Code: .mcp.json lee Bearer ${HORACIO_MCP_API_KEY}. Exporta la variable o define env.HORACIO_MCP_API_KEY en ~/.claude/settings.json; reinicia Claude.

  • Codex:

    codex mcp add kg-educacion --url https://chatgpt.southlab.ai/mcp --bearer-token-env-var HORACIO_MCP_API_KEY

  • Apps macOS abiertas desde el Dock: launchctl setenv HORACIO_MCP_API_KEY "$HORACIO_MCP_API_KEY".

El manifiesto de Codex guarda el nombre de la variable, no el secreto.

Verificar

  1. Reinicia Claude o Codex y abre una sesión nueva.
  2. Ejecuta consultar_curriculum para Lenguaje 4° básico y verifica citas.
  3. Si la cuenta tiene acceso material, ejecuta consultar_recursos para un texto escolar.
  4. Si esa tool responde que la función no está habilitada, el plugin está autenticado pero la cuenta no tiene el feature o grant vigente; no regeneres la key.

Read the full file on GitHub · 76 lines

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. 1mo ago First seen · 76 lines · 38 tokens per session scan C 8ec1e2e4089f

Subscribe to this mod's changes

setup is a skill published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (3 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 802 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeMulti-Agentai-agentscomputer-visionmarketplacemcp
Related

Other skills, from other repositories

cosmergon

Persistent multi-agent economy where autonomous AI agents compete for resources, trade on a marketplace, and benchmark decision-making against a standing population of always-on agents. Two games, one goal — play the economy inside, and bring real buyers from outside; both count toward place 1. Auto-registers — no API…

rkocosmergon/cosmergon-agent · 68 tokens

sector-rotation

An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.

HKUDS/Vibe-Trading · 39 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

bdd-container-update

Update the BDD test container image when its dependencies or runtime change. Determines version bump (major vs minor vs patch), rebuilds the Docker image, pushes to GitLab registry, and updates the image tag in starttest.sh. Test source (tests/, features/, scripts/, data/, conftest.py) is bind-mounted from the host…

NVIDIA-AI-Blueprints/video-search-and-summarization · 117 tokens

oma-scholar

Search academic literature and generate, validate, or compare Knows paper sidecars. Use for claim/evidence analysis and literature synthesis.

first-fluke/oh-my-agent · 30 tokens

flow-next-tracker-sync

Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.

gmickel/flow-next · 44 tokens