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.
curl -O https://raw.githubusercontent.com/hoangsonww/AI-RAG-Assistant-Chatbot/master/.agents/skills/lumina-agentic-mcp/SKILL.mdgit clone --depth 1 https://github.com/hoangsonww/AI-RAG-Assistant-ChatbotWrote 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/hoangsonww/ai-rag-assistant-chatbot/lumina-agentic-mcp)<a href="https://agentmods.dev/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-agentic-mcp"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-agentic-mcp/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/hoangsonww/ai-rag-assistant-chatbot/lumina-agentic-mcp"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-agentic-mcp.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 | $0.00060 | $0.00351 |
| Opus 5.5 | $0.00024 | $0.00140 |
| Sonnet 5.5 | $0.00012 | $0.00070 |
| Haiku 4.5 | $0.00006 | $0.00035 |
Grade A, and why
lumina-agentic-mcp 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 2mo 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.
What it actually says
Lumina Agentic Mcp
Overview
Use this skill for the Python subsystem under agentic_ai/. Keep changes consistent with the existing config-driven, async, multi-agent design rather than turning it into a one-off script.
Load The Right Reference
- Read
references/file-map.mdwhen you need to locate the pipeline, agent, config, or MCP surface that owns a behavior. - Read
references/commands.mdbefore finishing so validation and startup commands match the subsystem.
Preserve The Existing Architecture
- Keep pipeline behavior flowing through
core/,agents/, andmcp_client/rather than duplicating logic. - Respect async boundaries and existing command entry points in
agentic_ai/__main__.py. - Keep the MCP server contract explicit when changing tool names, prompt names, or resource URIs.
- Preserve configuration-driven behavior through files in
agentic_ai/config/.
Validate With What The Repo Actually Supports
- Prefer
python -m compileall agentic_aifor low-friction validation when dependencies or tests are unavailable. - Use targeted CLI smoke checks such as
python -m agentic_ai visualizeorpython -m agentic_ai run --task "..."only when the environment is ready. - Do not assume
pytestis runnable just because it appears inrequirements.txt; verify the test target exists first.
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.
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.
- 2mo ago First seen · 29 lines · 60 tokens per session scan A cd90bb2ea169
lumina-agentic-mcp is a skill published in the GitHub repository hoangsonww/AI-RAG-Assistant-Chatbot (50 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 351 once invoked, about $0.0002 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 2026-08-30.
lumina-agentic-mcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lumina-agentic-mcphoangsonww/AI-RAG-Assistant-Chatbot | Skill | 50 | 1mo ago | MIT | A | 60 | Codex |
| codigo-automacaoricneves-ai/flowgrammers-skills | Skill | 117 | 1mo ago | MIT | A | 56 | Claude Code, Codex |
| darto-add-routeevandersondev/darto | Skill | 44 | 4mo ago | MIT | A | 90 | Claude Code, Codex |
| darto-validate-requestevandersondev/darto | Skill | 44 | 4mo ago | MIT | A | 83 | Claude Code, Codex |
| darto-write-middlewareevandersondev/darto | Skill | 44 | 4mo ago | MIT | A | 86 | Claude Code, Codex |
| darto-scaffold-projectevandersondev/darto | Skill | 44 | 4mo ago | MIT | A | 81 | Claude Code, Codex |
| Express.js Testing PatternsPramodDutta/qaskills | Skill | 245 | 3d ago | MIT | A | 28 | Claude Code, Codex |