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-planninggit 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-planning)<a href="https://agentmods.dev/skills/openraiser/nanoresearch/nanoresearch-planning"><img src="https://agentmods.dev/badge/skills/openraiser/nanoresearch/nanoresearch-planning/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-planning"><img src="https://agentmods.dev/badge/skills/openraiser/nanoresearch/nanoresearch-planning.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 | $0.00014 | $0.00279 |
| Opus 5 | $0.00007 | $0.00139 |
| Sonnet 5 | $0.00003 | $0.00056 |
| Haiku 4.5 | $0.00001 | $0.00028 |
Grade A, and why
nanoresearch-planning 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 13d 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.
What it actually says
Planning Skill
Purpose
Take the selected hypothesis from ideation and produce a detailed experiment blueprint specifying datasets, baselines, evaluation metrics, and ablation groups.
Tools Required
None. This skill operates entirely through LLM reasoning over the ideation output.
Input
ideation_output: Path topapers/ideation_output.jsonproduced by the ideation skill
Process
- Parse the selected hypothesis and supporting literature from the ideation output
- Identify candidate datasets that are publicly available and appropriate for validating the hypothesis
- Select 2-4 baseline methods from the surveyed literature for comparison
- Define primary and secondary evaluation metrics aligned with the hypothesis
- Design ablation groups that isolate each novel component of the proposed approach
- Estimate computational requirements and timeline for each experiment
- Compile everything into a structured experiment blueprint
Output
Produces papers/experiment_blueprint.json containing:
- Selected hypothesis (carried forward)
- Dataset specifications (name, source, splits, preprocessing steps)
- Baseline methods with references
- Evaluation metrics and success criteria
- Ablation study design (groups, variables, expected outcomes)
- Resource estimates and experiment schedule
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.
- 13d ago First seen · 35 lines · 14 tokens per session scan A 8281b5cd7234
nanoresearch-planning is a skill published in the GitHub repository OpenRaiser/NanoResearch (1,365 stars, last pushed 18d ago), licensed MIT. It adds 14 tokens to every session and 279 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…
auto-claim
Workflow 1: Claim-stage pipeline, controlled by two orthogonal axes. BEHAVIORSOURCE selects the behavior stage: given (default; behavior taken from task.md and assumed to hold — no ideation, no novelty, no M0), given-validation (behavior taken from task.md but the experiment plan opens with an M0 phenomenon-validation…
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…
mechanic-db-search
Paper retrieval via the cloud SEARCH service. The Agent builds a decomposed query JSON from its task context (preferred) or submits a polished free-form English query; the cloud service performs multi-ranker retrieval and fusion. Use as one of an important paper sources.
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…