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-rag-knowledge/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-rag-knowledge)<a href="https://agentmods.dev/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-rag-knowledge"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-rag-knowledge/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-rag-knowledge"><img src="https://agentmods.dev/badge/skills/hoangsonww/ai-rag-assistant-chatbot/lumina-rag-knowledge.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 | $0.00083 | $0.00367 |
| Opus 5.5 | $0.00033 | $0.00147 |
| Sonnet 5.5 | $0.00017 | $0.00073 |
| Haiku 4.5 | $0.00008 | $0.00037 |
Grade A, and why
lumina-rag-knowledge 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 Rag Knowledge
Overview
Use this skill for retrieval, ingestion, and citation work. The repository treats knowledge management as a CLI-driven flow rather than a UI-managed feature.
Load The Right Reference
- Read
references/cli-workflow.mdwhen updating or using ingestion commands, manifests, or source files. - Read
references/retrieval-contract.mdwhen changing runtime retrieval, citation formatting, or grounded-answer behavior.
Preserve The Grounding Contract
- Keep answers grounded in indexed sources.
- Preserve inline citations and the associated sources list behavior when changing retrieval or response composition.
- Avoid adding UI-based mutation flows for knowledge content unless the task explicitly requires a product change.
- Prefer updating source content through the CLI and manifest workflows already documented in the repo.
Change Source Lifecycle Carefully
- Preserve stable
externalIdusage when designing repeatable updates. - Keep ingestion, deletion, listing, and sync semantics coherent across CLI commands and model storage.
- If a change affects both retrieval logic and general API behavior, coordinate with
lumina-backend-api.
Finish With Practical Validation
- Run
npm run buildinserver/after code changes. - Use the existing CLI commands for targeted runtime checks when environment variables and external services are available.
- If Pinecone or Gemini credentials are unavailable, state that runtime retrieval was not exercised.
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 · 35 lines · 83 tokens per session scan A 715018dd07c0
lumina-rag-knowledge is a skill published in the GitHub repository hoangsonww/AI-RAG-Assistant-Chatbot (50 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 367 once invoked, about $0.0003 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-rag-knowledge compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lumina-rag-knowledgehoangsonww/AI-RAG-Assistant-Chatbot | Skill | 50 | 1mo ago | MIT | A | 83 | Codex |
| difyznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | A | 115 | Claude Code, Codex |
| knowject-rag-evallynxlangya/knowject | Skill | 12 | 5mo ago | none | A | 148 | Codex |
| create-atomic-context-providerEigenwise/atomic-agents | Skill | 6.3k | 8d ago | MIT | A | 106 | Claude Code |
| rag-knowledgevstorm-co/full-stack-ai-agent-template | Skill | 2.0k | 7d ago | MIT | A | 76 | Claude Code |
| wegent-knowledgewecode-ai/Wegent | Skill | 882 | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| session-rag-evalchatboxai/chatbox | Skill | 42k | 8d ago | GPL-3.0 | A | 25 | Claude Code, Codex |