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 mishahanin/heading-os --skill notebooklmgit clone --depth 1 https://github.com/mishahanin/heading-osWrote 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/mishahanin/heading-os/notebooklm)<a href="https://agentmods.dev/skills/mishahanin/heading-os/notebooklm"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/notebooklm/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/mishahanin/heading-os/notebooklm"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/notebooklm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 15 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00138 | $0.02313 |
| Opus 5 | $0.00069 | $0.01156 |
| Sonnet 5 | $0.00028 | $0.00463 |
| Haiku 4.5 | $0.00014 | $0.00231 |
Grade A, and why
notebooklm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NotebookLM Integration
CLI wrapper for Google NotebookLM via notebooklm-mcp-cli. Creates topic notebooks, ingests sources, queries with grounded citations, generates audio overviews, runs research discovery, and bridges to Odin for knowledge ingestion.
CEO-only. Not synced to exec workspaces. Uses undocumented Google APIs - may break without notice.
CLI Access
The nlm CLI is installed but may not be on bash PATH directly on Windows. Use this exact invocation pattern for ALL commands:
NLM="$(command -v nlm 2>/dev/null \
|| ls "${APPDATA:-$USERPROFILE/AppData/Roaming}"/Python/Python*/Scripts/nlm.exe 2>/dev/null | head -1)"
NO_COLOR=1 PYTHONIOENCODING=utf-8 "$NLM" <subcommand> [flags]
The command -v nlm lookup prefers nlm on PATH (Linux, macOS, future). The fallback is for the Windows CEO machine, where pip installs to a user-scoped Scripts directory that is not on the Git Bash PATH. It derives the per-user Roaming location from $APPDATA, or from $USERPROFILE/AppData/Roaming when $APPDATA is unset. No username and no Python minor version is hardcoded. It then globs the Python*/Scripts/nlm.exe install path. On Linux/macOS $APPDATA and $USERPROFILE are unset and the glob matches nothing, so command -v nlm is authoritative there. Always set NLM as a variable at the start of each Bash call, then use "$NLM" for the command. The NO_COLOR=1 PYTHONIOENCODING=utf-8 prefix forces UTF-8 stdio across platforms (required on Windows console; harmless on Linux/macOS).
Variables
$ARGUMENTS- Mode and parameters. Format:[mode] [target/args]- Modes:
status,create,add,query,audio,research,report,describe,download
Phase 0: Auth Validation
Run before EVERY mode. No exceptions.
- Run (Bash, timeout 15000):
NLM="$(command -v nlm 2>/dev/null \ || ls "${APPDATA:-$USERPROFILE/AppData/Roaming}"/Python/Python*/Scripts/nlm.exe 2>/dev/null | head -1)" NO_COLOR=1 PYTHONIOENCODING=utf-8 "$NLM" login --check - If exit code 0: proceed to requested mode
- If exit code != 0: STOP. Display:
What ships with it
7 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.
- 8d ago First seen · 187 lines · 138 tokens per session scan A 2e07aae49fc8
notebooklm is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 138 tokens to every session and 2,313 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.