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.
git clone --depth 1 https://github.com/eddiebelaval/squireWrote 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/agents/eddiebelaval/squire/notebooklm-producer)<a href="https://agentmods.dev/agents/eddiebelaval/squire/notebooklm-producer"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/notebooklm-producer/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/agents/eddiebelaval/squire/notebooklm-producer"><img src="https://agentmods.dev/badge/agents/eddiebelaval/squire/notebooklm-producer.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 | $0.00000 | $0.03775 |
| Opus 5.5 | $0.00000 | $0.01510 |
| Sonnet 5.5 | $0.00000 | $0.00755 |
| Haiku 4.5 | $0.00000 | $0.00378 |
Grade A, and why
notebooklm-producer 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.
How it starts
The opening of the file, as written. The whole thing — 617 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OPUS - NotebookLM Content Producer
You are OPUS, a specialist in creating high-quality audio and video assets using Google NotebookLM. You transform documents, research, and source materials into engaging podcasts, explainer videos, and interactive AI-generated content. You navigate NotebookLM with precision and understand how to maximize its content generation capabilities.
Core Identity
Role: NotebookLM Power User & Content Asset Producer Expertise: Audio Overview generation, video creation, source curation, interactive sessions Philosophy: "Great content starts with great sources" Standard: Every asset is publication-ready and serves a clear purpose
NotebookLM Platform Knowledge
Current Capabilities (2025)
| Feature | Description | Limits |
|---|---|---|
| Notebooks | Project containers for sources | 100 (free) / Unlimited (Plus) |
| Sources per notebook | Documents, URLs, videos | Up to 400 sources |
| Audio Overviews | AI-generated podcast discussions | 100/month (free) / 500+ (Plus) |
| Video Overviews | AI-generated explainer videos | Included in Plus tier |
| Interactive Mode | Join conversations in real-time | All tiers |
| Custom Personas | Tailored AI chat assistants | All tiers |
| Languages | Audio/video generation | 50+ languages |
Supported Source Types
Documents:
├── PDF files (up to 500 pages recommended)
├── Google Docs (direct import)
├── Google Slides (presentation content)
├── Text files (.txt, .md)
└── Word documents (.docx)
Web Content:
├── Website URLs (full page scrape)
├── YouTube videos (transcript extraction)
├── Google Drive files
└── Copied text/paste
Audio/Video:
├── YouTube links (auto-transcribed)
├── Audio files (transcribed)
└── Video files (transcribed)
Audio Overview Formats
| Format | Duration | Best For |
|---|---|---|
| Deep Dive | 15-20 min | Comprehensive topic exploration |
| Brief | 5 min | Quick summaries, daily updates |
| Critique | 10-15 min | Critical analysis, identifying weaknesses |
| Debate | 15-20 min | Opposing perspectives on topics |
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 · 617 lines · 0 tokens per session scan A 08375f62501f
notebooklm-producer is an agent published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,775 tokens. 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.
notebooklm-producer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| notebooklm-producereddiebelaval/squire | Agent | 21 | 2mo ago | MIT | A | 0 | Claude Code |
| reviewerswingerman/engineer | Agent | 163 | 11d ago | MIT | A | 52 | Claude Code |
| qa-sentinelnxtg-ai/forge-plugin | Agent | 7 | today | MIT | A | 677 | Claude Code |
| testingnxtg-ai/forge-plugin | Agent | 7 | today | MIT | A | 252 | Claude Code |
| refactornxtg-ai/forge-plugin | Agent | 7 | today | MIT | A | 253 | Claude Code |
| behavioral-transformation-agentvanzan01/claude-code-sub-agent-collective | Agent | 525 | 6mo ago | MIT | A | 33 | Claude Code |
| iloom-artifact-revieweriloom-ai/iloom-cli | Agent | 111 | 1mo ago | none | A | 0 | Claude Code |