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/compare-papersgit 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 | $0.00621 |
| Opus 5 | $0.00004 | $0.00311 |
| Sonnet 5 | $0.00002 | $0.00124 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
compare-papers 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compare Papers
Create a single NotebookLM notebook with multiple papers as sources for comparison and analysis.
Arguments
Parse from: $ARGUMENTS
- PAPERS: Space-separated list of arXiv IDs or URLs (2-10 papers)
Options:
--name "NAME": Custom notebook name (default: "Paper Comparison - {date}")--slides: Generate comparison slide deck--audio: Generate audio discussion comparing papers--focus "TOPIC": Focus comparison on specific aspect
Workflow
- Parse all provided arXiv IDs/URLs
- Create new NotebookLM notebook with descriptive name
- Add each paper as a source: a. Click "Add sources" b. Click "Websites" c. Paste arXiv PDF URL d. Click Insert e. Wait for processing
- After all sources added, optionally: a. Generate comparison slide deck b. Generate audio overview
- Provide chat prompts for comparison analysis
Comparison Prompts
After creating the notebook, suggest these prompts for the user:
-
Methodology Comparison: "Compare the methodologies used in these papers. What are the key differences in approach?"
-
Results Comparison: "Compare the experimental results across these papers. Which approach performs best and under what conditions?"
-
Contribution Comparison: "What are the unique contributions of each paper? How do they complement or contrast each other?"
-
Timeline/Evolution: "How do these papers build upon each other? What is the progression of ideas?"
Example Usage
# Compare two papers
/notebooklm-papers:compare-papers 2601.02151 2601.03509
# Compare multiple papers with custom name
/notebooklm-papers:compare-papers 2601.02151 2601.03509 2601.03872 --name "LLM Fine-tuning Survey"
# Compare and generate slides
/notebooklm-papers:compare-papers 2601.02151 2601.03509 --slides --focus "performance benchmarks"
# URLs work too
/notebooklm-papers:compare-papers https://arxiv.org/abs/2601.02151 https://arxiv.org/abs/2601.03509
Output
Provides:
- Link to the comparison notebook
- List of all added papers
- Suggested comparison prompts
- Status of slides/audio generation if requested
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 · 83 lines · 8 tokens per session scan A e6588027f0bc
compare-papers 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 621 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
git
Git operations with intelligent commit messages and workflow optimization.
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.