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 commands/minihellboy/notebooklm-papers-plugin/list-notebooksgit clone --depth 1 https://github.com/minihellboy/notebooklm-papers-pluginWhat 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 | $0.00008 | $0.00335 |
| Opus 5 | $0.00004 | $0.00168 |
| Sonnet 5 | $0.00002 | $0.00067 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
list-notebooks 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 yesterday.
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
List NotebookLM Notebooks
Displays all notebooks in your NotebookLM account with their details.
Arguments
Parse from: $ARGUMENTS
Options:
--filter TERM: Filter notebooks by name containing TERM--recent N: Show only the N most recent notebooks--papers: Show only notebooks that look like paper notebooks (contain "Paper" or arXiv IDs)
Workflow
- Get browser context
- Navigate to
https://notebooklm.google.com - Read the notebooks list from the page
- For each notebook, extract:
- Title
- Number of sources
- Creation date
- Notebook URL
- Apply any filters
- Display formatted list
Output Format
# Your NotebookLM Notebooks
| Title | Sources | Created | Link |
|-------|---------|---------|------|
| Paper 1 - Entropy-Adaptive Fine-Tuning | 1 | Jan 9, 2026 | [Open](...) |
| Paper 2 - Evolving Programmatic Skill Networks | 1 | Jan 9, 2026 | [Open](...) |
...
Total: {count} notebooks
Example Usage
/notebooklm-papers:list-notebooks
/notebooklm-papers:list-notebooks --papers
/notebooklm-papers:list-notebooks --filter "Paper"
/notebooklm-papers:list-notebooks --recent 5
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.
- yesterday First seen · 54 lines · 8 tokens per session scan A 081da34cb2b6
list-notebooks is a command published in the GitHub repository minihellboy/notebooklm-papers-plugin (2 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 335 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.