NanoResearch is an autonomous AI research system that turns research ideas into executable experiments and LaTeX papers supported by results from real training runs. It is for researchers validating prototypes, running GPU experiments, generating benchmarks, analyzing logs, and preparing paper drafts. The catalogue add-ons support its research pipeline and agent workflows.
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 OpenRaiser/NanoResearch --skill nanoresearch-writinggit clone --depth 1 https://github.com/OpenRaiser/NanoResearchWrote 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/openraiser/nanoresearch/nanoresearch-writing)<a href="https://agentmods.dev/skills/openraiser/nanoresearch/nanoresearch-writing"><img src="https://agentmods.dev/badge/skills/openraiser/nanoresearch/nanoresearch-writing/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/openraiser/nanoresearch/nanoresearch-writing"><img src="https://agentmods.dev/badge/skills/openraiser/nanoresearch/nanoresearch-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00017 | $0.00478 |
| Opus 5 | $0.00009 | $0.00239 |
| Sonnet 5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
nanoresearch-writing 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 11d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Skill
Purpose
Take all previous outputs (ideation, planning, experiment results) and produce a complete LaTeX paper draft with figures, tables, and bibliography.
Tools Required
generate_latex: Generate and assemble LaTeX source files for each paper sectioncompile_pdf: Compile the LaTeX source into a PDF documentgenerate_figure: Produce publication-quality figures from experiment results
Input
ideation_output: Path topapers/ideation_output.jsonfrom the ideation skillexperiment_blueprint: Path topapers/experiment_blueprint.jsonfrom the planning skillexperiment_results: Path toexperiments/directory containing code and results from the experiment skill
Process
- Parse all upstream outputs to gather hypotheses, literature, experiment design, and results
- Generate the paper outline following a standard structure (Abstract, Introduction, Related Work, Method, Experiments, Conclusion)
- Draft the Abstract summarizing the problem, approach, and key findings
- Draft the Introduction motivating the research question and stating contributions
- Draft Related Work synthesizing the surveyed literature from the ideation stage
- Draft the Method section describing the proposed approach in detail
- Draft the Experiments section with dataset descriptions, baseline comparisons, and ablation results
- Generate figures (performance plots, ablation charts, architecture diagrams) using
generate_figure - Generate tables summarizing quantitative results
- Draft the Conclusion with a summary of findings and future work directions
- Compile the bibliography from all cited papers
- Assemble the full LaTeX document using
generate_latex - Compile to PDF using
compile_pdfand verify the output
Output
Produces papers/draft/ directory containing:
main.tex: Complete LaTeX source of the paperreferences.bib: Bibliography file with all citationsfigures/: Generated figures in PDF or PNG formattables/: LaTeX table source filesmain.pdf: Compiled PDF of the paper draft
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.
- 11d ago First seen · 44 lines · 17 tokens per session scan A 9bfcca61dcd1
nanoresearch-writing is a skill published in the GitHub repository OpenRaiser/NanoResearch (1,365 stars, last pushed 16d ago), licensed MIT. It adds 17 tokens to every session and 478 once invoked, about $0.0001 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
auto-experiment
Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENTPLAN.md, routes mechanism family inline (Phase 1.5), implements experiment code, deploys to GPU, and collects initial results. Use when user says "implement experiments", "experiment", "deploy the plan", or has an experiment plan ready to…
hypothesis-batch
Automated pipeline for generating and refining multiple research hypotheses.
mechanism-audit
Audit the mechanistic experiment rigor for a specific claim. Catalogue currently has six slots A–F: A (steering coefficient sweep) is implemented; B–F are reserved for future checks (direction extraction quality, site/layer selection, neffective sufficiency, probe-vs-causal disentanglement, intervention scope). Uses…
shap
Use this skill when working with SHAP (SHapley Additive exPlanations) to explain machine learning model predictions, compute feature importance, generate SHAP values for tree ensembles (XGBoost, LightGBM, CatBoost, scikit-learn), deep learning models (TensorFlow, Keras, PyTorch), NLP transformers, or any…
mechanism-skills
Routing entry point for eleven families of mechanistic-interpretability methods that localize which internal object (layer, attention head, neuron, SAE feature, weight, or input feature) drives a model's behavior, how influential it is, and what changes when it is intervened on. Use this skill whenever the question is…
dynamic-components
Identify and manipulate language-specific neurons in multilingual Large Language Models (LLMs) to understand and control language-specific behaviors in models like LLaMA-2, BLOOM, OPT, Mistral, and Phi-2.