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 agentmods add skills/magicseek/nblm/nblmnpx skills add magicseek/nblm --skill nblmgit clone --depth 1 https://github.com/magicseek/nblmWhat 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 | $0.00049 | $0.05820 |
| Opus 5 | $0.00024 | $0.02910 |
| Sonnet 5 | $0.00010 | $0.01164 |
| Haiku 4.5 | $0.00005 | $0.00582 |
Grade A, and why
nblm 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 2d 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 — 622 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NotebookLM Quick Commands
Query Google NotebookLM for source-grounded, citation-backed answers.
Environment
All dependencies and authentication are handled automatically by run.py:
- First run creates
.venvand installs Python/Node.js dependencies - If Google auth is missing or expired, a browser window opens automatically
- No manual pre-flight steps required
Usage
/nblm <command> [args]
Commands
Notebook Management
| Command | Description |
|---|---|
login |
Authenticate with Google |
status |
Show auth and library status |
accounts |
List all Google accounts |
accounts add |
Add a new Google account |
accounts switch <id> |
Switch active account (by index or email) |
accounts remove <id> |
Remove a Google account |
accounts use <id> |
Set agent-specific active account (OpenClaw isolation) |
accounts clear |
Clear agent-specific account override |
local |
List notebooks in local library |
remote |
List all notebooks from NotebookLM API |
create <name> |
Create a new notebook |
delete [--id ID] |
Delete a notebook |
rename <name> [--id ID] |
Rename a notebook |
summary [--id ID] |
Get AI-generated summary |
describe [--id ID] |
Get description and suggested topics |
add <url-or-id> |
Add notebook to local library (auto-detects URL vs notebook ID) |
activate <id> |
Set active notebook |
Source Management
| Command | Description |
|---|---|
sources [--id ID] |
List sources in notebook |
upload <file> |
Upload a single file |
upload <folder> |
Sync a folder of files to NotebookLM |
upload-zlib <url> |
Download from Z-Library and upload |
upload-url <url> |
Add URL as source |
upload-youtube <url> |
Add YouTube video as source |
upload-text <title> [--content TEXT] |
Add text as source |
source-text <source-id> |
Get full indexed text |
source-guide <source-id> |
Get AI summary and keywords |
source-rename <source-id> <name> |
Rename a source |
source-refresh <source-id> |
Re-fetch URL content |
source-delete <source-id> |
Delete a source |
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.
- 2d ago First seen · 622 lines · 49 tokens per session scan A 1afee54177d3
nblm is a skill published in the GitHub repository magicseek/nblm (33 stars, last pushed 6mo ago), licensed MIT. It adds 49 tokens to every session and 5,820 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.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
browser_cdp
通过 Chrome DevTools Protocol (CDP) 连接已运行的浏览器，或扫描本机 CDP 端口，用于远程调试与多工具共享浏览器实例。.