AI-RAG-Assistant-Chatbot: Skill for Codex

.agents/skills/lumina-mcp-server/SKILL.md

lumina-mcp-server is a skill for Codex from hoangsonww/AI-RAG-Assistant-Chatbot. It costs 48 tokens per session (368 once invoked), scanned A, original, MIT.

A set of instructions for developing and maintaining Lumina's standalone MCP server, which lets AI clients use tools, shared information, and prompts.

In plain words
What is it for?
Use it when changing files in the MCP server, including tools, resources, prompts, middleware, configuration, or the way the server communicates.
Why use it?
It keeps server changes organized and protects the names and input formats that connected clients rely on. It also provides rules for authentication, rate limits, validation, and checking Python code.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is hoangsonww/AI-RAG-Assistant-Chatbot's own configuration. It tells Codex how to work on AI-RAG-Assistant-Chatbot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AI-RAG-Assistant-Chatbot configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hoangsonww/AI-RAG-Assistant-Chatbot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hoangsonww/AI-RAG-Assistant-Chatbot/master/.agents/skills/lumina-mcp-server/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hoangsonww/AI-RAG-Assistant-Chatbot

Made for: Codex.

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 lumina-mcp-server

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-mcp-server/github.svg)](https://agentmods.dev/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-mcp-server)
Your own site
<a href="https://agentmods.dev/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-mcp-server"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-mcp-server/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 lumina-mcp-server

Your own site · 80×15
<a href="https://agentmods.dev/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-mcp-server"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 368 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 $0.00048 $0.00368
Opus 5 $0.00024 $0.00184
Sonnet 5 $0.00010 $0.00074
Haiku 4.5 $0.00005 $0.00037

Measured 12d ago against content hash 793ce0ee96ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

lumina-mcp-server 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.

.agents/skills/lumina-mcp-server/SKILL.md · 36 lines

What it actually says

Lumina MCP Server

Overview

Use this skill for the standalone MCP server at mcp_server/. The server implements the Model Context Protocol with 32 tools across 8 categories, 7 resources, and 6 prompts.

Load The Right Reference

  • Read references/file-map.md to locate the tool, resource, prompt, or middleware that owns a behavior.
  • Read references/tool-development.md when adding or modifying MCP tools.

Preserve The MCP Contract

  • Tool names and input_schema definitions are external contracts — MCP clients depend on them.
  • Keep each tool category in its own module under tools/.
  • Extend by subclassing ToolHandler(ABC) with name, description, input_schema, and handle().
  • Register new tools in the category module's register(cfg) function.
  • New categories require a new module and a _ToolRegistry entry in tools/__init__.py.

Keep Middleware Composable

  • Authentication, rate limiting, and validation flow through MiddlewareChain.
  • Do not bypass middleware for individual tools.
  • Configuration overrides via environment variables (MCP_API_KEY, MCP_RATE_LIMIT, MCP_LOG_LEVEL).

Validate Carefully

  • Run python -m compileall mcp_server for compile-time validation.
  • Use python -m mcp_server --log-level DEBUG for startup smoke testing when dependencies are installed.
  • Do not assume external services (Pinecone, Git repos) are available during validation.
Files

What ships with it

3 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. 12d ago First seen · 36 lines · 48 tokens per session scan A 793ce0ee96ee

Subscribe to this mod's changes

lumina-mcp-server is a skill published in the GitHub repository hoangsonww/AI-RAG-Assistant-Chatbot (47 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 368 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

darto-add-route

Add or modify HTTP endpoints in a Darto (Dart) web app — verbs, path/query params, request-body reading, route groups, and Context response helpers. Use when building or changing API routes in a project that depends on the darto package (import 'package:darto/darto.dart'). Not for Express/Node — Darto handlers take a…

evandersondev/darto · 90 tokens

darto-validate-request

Validate the body, query, params, or headers of a Darto (Dart) request using the zValidator middleware and zard (Zod-style) schemas. Use when adding input validation to a Darto endpoint, defining a z.map/z.string/z.int schema, reading validated data with c.req.valid, or customizing the validation error response.…

evandersondev/darto · 83 tokens

darto-write-middleware

Write and register middleware in a Darto (Dart) app — the Middleware factory pattern, global/path-scoped/route-level registration, short-circuiting, per-request state, and global error/404 handlers. Use when adding cross-cutting behavior (auth, logging, CORS, timing) or configuring app.onError / app.notFound in a…

evandersondev/darto · 86 tokens

darto-scaffold-project

Scaffold, run, and build a Darto (Dart) web project using the dartocli — create a new project with a NestJS-style module structure, run a hot-reload dev server, compile a production binary, and generate a typed API client. Use when starting a new Darto app, setting up the project layout, or configuring dev/build…

evandersondev/darto · 81 tokens

codigo-automacao

Skills para desenvolvimento de software, debug, APIs, automações no-code e uso avançado de ferramentas de IA para desenvolvimento. Use quando precisar de diagnóstico de bugs, construção de APIs, containerização, testes automatizados, integrações ou engenharia de prompts.

ricneves-ai/flowgrammers-skills · 56 tokens

express

Build Express.js routers and middleware with request validation, async error handling, and clear application structure.

alivirgo/Major-AI-Skills · 21 tokens