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.
npx skills add moonlight-lupin/agent-skills --skill notebooklm-modegit clone --depth 1 https://github.com/moonlight-lupin/agent-skillsWrote 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/moonlight-lupin/agent-skills/notebooklm-mode)<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/notebooklm-mode"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/notebooklm-mode/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/moonlight-lupin/agent-skills/notebooklm-mode"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/notebooklm-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.03899 |
| Opus 5 | $0.00046 | $0.01950 |
| Sonnet 5 | $0.00018 | $0.00780 |
| Haiku 4.5 | $0.00009 | $0.00390 |
Grade A, and why
notebooklm-mode 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.
How it starts
The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NotebookLM-Grounded Research Pipeline
Research a topic from sources — collect verbatim extracts, index them for semantic search, then answer questions and create deliverables grounded in those sources. Inspired by NotebookLM.
Trigger
- User asks to research a topic "from sources" or "grounded in sources"
- User mentions "notebooklm mode", "source-grounded", or "vault mode"
- User wants responses that cite collected sources, not general knowledge
- User asks to create deliverables from collected sources
Modes
Direct mode (default)
The orchestrator runs all roles inline — no subagents. Use for most topics.
Subagent mode (optional)
Spawn agents via delegate_task only when genuinely needed: parallel research
across distinct sub-topics, or user explicitly requests it. Not triggered by
source count alone — escalate when the work is genuinely parallel or the user
asks for isolation.
delegate_task(
goal="<user's request>",
context="You are the [Research|Response|Output] Agent in a NotebookLM
pipeline. Vault path: <vault_path>. Load skill 'notebooklm-mode'.
Your role: [Research|Response|Output]. Topic: <topic>.
Grounding mode: [strict|augmented].",
toolsets=[<appropriate toolsets per role>]
)
Sequential: Research → (user reviews) → Response → (user requests) → Output. Never dispatch a dependent agent before the previous one returns and files are verified.
Grounding modes
| Mode | Behavior |
|---|---|
| Strict (default) | Vault only. If it's not in the vault, you don't know it. Gaps are identified, never bridged with inference. |
| Augmented | Vault first. General knowledge allowed but must be explicitly tagged [background] and clearly separated from vault-sourced claims. User requests this explicitly. |
Augmented mode example:
According to Source #3: "The LTCI system covers 95% of seniors" [vault]
[background] LTCI was introduced in 2000 as part of Japan's long-term care insurance reform.
What ships with it
5 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.
- 12d ago First seen · 357 lines · 91 tokens per session scan A 5f79ab178505
notebooklm-mode is a skill published in the GitHub repository moonlight-lupin/agent-skills (64 stars, last pushed 5d ago), licensed MIT. It adds 91 tokens to every session and 3,899 once invoked, about $0.0005 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.
Other skills, from other repositories
SoloFlow
A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them.
hermes-tweet
Use Xquik in Hermes Agent for public X research, monitoring, thread summaries, creator discovery & approved actions. Not affiliated with X Corp. Use when the user requests X data or a named action. Trigger with "search X", "monitor X", "post tweet", or "X trends".
image
Create or optimize marketing images, social graphics, product mockups, banners, cover art, listing visuals, brand assets, image prompts, WebP files, and OG images.
video
Plan and produce video with available AI tools or programmatic frameworks. Use for video prompts, avatars, explainers, demos, templates, pipelines, and generation.
content-research-writer
Research, outline, draft, cite, and revise articles, reports, tutorials, newsletters, and case studies with traceable sources and preserved voice.
content-analysis
Analyze articles, documents, videos, podcasts, and transcripts for arguments, evidence, themes, assumptions, contradictions, insights, and unanswered questions.