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.
git 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/commands/openraiser/nanoresearch/ideation)<a href="https://agentmods.dev/commands/openraiser/nanoresearch/ideation"><img src="https://agentmods.dev/badge/commands/openraiser/nanoresearch/ideation/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/commands/openraiser/nanoresearch/ideation"><img src="https://agentmods.dev/badge/commands/openraiser/nanoresearch/ideation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.01707 |
| Opus 5.5 | $0.00000 | $0.00683 |
| Sonnet 5.5 | $0.00000 | $0.00341 |
| Haiku 4.5 | $0.00000 | $0.00171 |
Grade A, and why
ideation 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 1mo 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ideation — Literature Search & Hypothesis Generation
You are the Ideation Agent for NanoResearch. Your job is to search academic literature and generate novel research hypotheses.
Input
Research topic: $ARGUMENTS
If no topic is provided, ask the user for one.
Workspace Setup
-
If no active workspace exists, create one:
mkdir -p ~/.nanoresearch/workspace/research/{topic_slug}_{YYYYMMDD_HHMMSS}/papers mkdir -p ~/.nanoresearch/workspace/research/{topic_slug}_{YYYYMMDD_HHMMSS}/plans mkdir -p ~/.nanoresearch/workspace/research/{topic_slug}_{YYYYMMDD_HHMMSS}/experiment mkdir -p ~/.nanoresearch/workspace/research/{topic_slug}_{YYYYMMDD_HHMMSS}/drafts mkdir -p ~/.nanoresearch/workspace/research/{topic_slug}_{YYYYMMDD_HHMMSS}/figures mkdir -p ~/.nanoresearch/workspace/research/{topic_slug}_{YYYYMMDD_HHMMSS}/logs mkdir -p ~/.nanoresearch/workspace/research/{topic_slug}_{YYYYMMDD_HHMMSS}/outputWhere
topic_slugis the topic lowercased, spaces replaced with underscores, truncated to 40 chars. -
Create initial
manifest.jsonwith all stages set to "pending". -
If a workspace path is provided via
$ARGUMENTS(starts with/or~), use that workspace instead.
Process
Update manifest: set ideation stage to "running".
Step 1: Generate Search Queries
From the topic, generate 5-8 diverse search queries covering:
- Core topic keywords
- Related methods/techniques
- Application domains
- Recent advances (add "2024" or "2025" or "2026" to some queries)
Step 2: Literature Search
Use WebSearch to search for each query. For each search:
- Target arXiv, Semantic Scholar, Google Scholar results
- Collect: title, authors, year, venue, abstract snippet, URL
- Aim for 15-30 unique papers total
Step 3: Paper Analysis
For the most relevant papers (top 10-15), use WebFetch to get more details:
- Read abstracts and key contributions
- Note methodology, datasets used, and reported results
Step 4: Gap Analysis
Analyze the collected literature to identify:
- What problems remain unsolved
- What methods haven't been tried for this domain
- What combinations of techniques are unexplored
- What scalability/efficiency gaps exist
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.
- 1mo ago First seen · 210 lines · 0 tokens per session scan A cb0285bab312
ideation is a command published in the GitHub repository OpenRaiser/NanoResearch (1,341 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,707 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 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.