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/llmsresearch/paperbanana/generate-plotnpx skills add llmsresearch/paperbanana --skill generate-plotgit clone --depth 1 https://github.com/llmsresearch/paperbananaWhat 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 | $0.00000 | $0.00314 |
| Opus 5 | $0.00000 | $0.00157 |
| Sonnet 5 | $0.00000 | $0.00063 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
generate-plot 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- generate-plot — 98% identical, 4 lines differ
What it actually says
Generate Plot
Generate a publication-quality statistical plot from a data file using PaperBanana.
Instructions
- Read the data file at
$ARGUMENTS[0]. - Prepare the data for the MCP tool:
- If the file is CSV: parse it and convert to a column-keyed dictionary (keys = column names, values = arrays of column values), then serialize with
json.dumps()to produce a JSON string. - If the file is JSON: use the raw file content as-is (it is already a JSON string).
- If the file is CSV: parse it and convert to a column-keyed dictionary (keys = column names, values = arrays of column values), then serialize with
- If
$ARGUMENTS[1]is provided, use it as the plot intent. Otherwise, ask the user for a description of the desired plot (e.g., "Bar chart comparing model accuracy across benchmarks"). - Call the MCP tool
generate_plotwith:data_json: the JSON string (not a parsed object)intent: the plot descriptioniterations: 3 (default)
- Present the generated plot to the user.
CLI Fallback
If the MCP tool is not available, fall back to the CLI:
paperbanana plot --data <file> --intent "<intent>"
Example
/generate-plot results.csv "Bar chart comparing model accuracy"
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.
- 3d ago First seen · 39 lines · 0 tokens per session scan A cf99f70a6656
generate-plot is a skill published in the GitHub repository llmsresearch/paperbanana (2,294 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 314 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.
Other skills, from other repositories
paper-search-pro
Find academic papers across up to 7 sources (OpenAlex / Semantic Scholar / CrossRef / PubMed / arXiv for English, plus native-Chinese retrieval via NSSD 国家哲社文献中心 + yiigle 中华医学期刊) with adjustable depth — Quick scan (5 min) to Audit prep (3 hr). Use when the user wants to find papers, run a literature search, gather…
paper-banana
Generates publication-ready academic illustrations using the PaperBanana five-agent pipeline (arXiv:2601.23265). Diagram mode runs 5 Gemini API agents with multimodal in-context learning from curated reference images. Plot mode generates executable Python matplotlib/seaborn code. Use when the user asks for: research…
hugging-face-trackio
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
acl-experiments
Use when designing or auditing experiments for an ACL paper, covering tuned LLM baselines, multi-dataset and multilingual evaluation, statistical significance and variance, human evaluation with agreement reporting, contamination and prompt-sensitivity controls, ablations, and error-analysis expectations in NLP…
acmmm-experiments
Use when designing or auditing the experiments of an ACM MM (ACM Multimedia) paper — matched baselines per modality, ablations that isolate the cross-modal fusion, user studies or QoE measurement where the claim is subjective, dataset and media licensing, and honest compute reporting, so evidence supports a multimedia…