ARIS is a collection of Markdown-based skills that define a workflow for autonomous machine-learning research, including idea discovery, experiment automation, and review loops. Researchers and AI coding agents use it across tools such as Claude Code, Codex, Cursor, and OpenClaw without depending on a single framework. The catalogue entries are ARIS workflow skills and agents.
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 wanshuiyin/Auto-claude-code-research-in-sleep --skill prior-art-searchgit clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleepWrote 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/wanshuiyin/auto-claude-code-research-in-sleep/prior-art-search)<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/prior-art-search"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/prior-art-search/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/wanshuiyin/auto-claude-code-research-in-sleep/prior-art-search"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/prior-art-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00052 | $0.01290 |
| Opus 5 | $0.00026 | $0.00645 |
| Sonnet 5 | $0.00010 | $0.00258 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
prior-art-search 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- prior-art-search — 100% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prior Art Search
Search patents and literature for prior art relevant to: $ARGUMENTS
Adapted from /research-lit for patent-specific searching.
Constants
MAX_PATENT_RESULTS = 20— Maximum patent documents to analyze in detailMAX_PAPER_RESULTS = 15— Maximum academic papers to analyze in detailSEARCH_YEARS = 10— How many years back to searchPATENT_DATABASES = "google-patents, espacenet"— Patent databases to search
Inputs
Read the invention description from:
$ARGUMENTSif it contains technical detailspatent/INVENTION_BRIEF.mdif it existsINVENTION_BRIEF.mdif it exists at project root
Shared References
Load ../shared-references/prior-art-databases.md for search strategy templates and IPC/CPC classification guidance.
Workflow
Step 1: Extract Search Concepts
From the invention description, identify:
- Core inventive concept: The primary technical contribution (1-2 sentences)
- Technical problem: What problem it solves
- Key technical features: 4-6 specific technical elements that define the invention
- IPC/CPC classes: Predict relevant classification codes (e.g., G06N, G06F)
Step 2: Patent Search
For EACH search concept, search via:
Google Patents (via WebSearch):
WebSearch: "site:patents.google.com [keywords]"
WebSearch: "[keywords] patent"
- Try primary keywords + technical problem keywords
- Search in English regardless of target jurisdiction
- For CN inventions, also search Chinese keywords via WebSearch
Espacenet (via WebFetch):
- WebFetch worldwide.espacenet.com/search results for key queries
- Search by predicted IPC/CPC classes
Assignee/Inventor Search:
- If known companies/universities work in this area, search their patent portfolios
- WebSearch: "[assignee name] patent [technical area]"
For each potentially relevant patent found:
- WebFetch the patent page to extract: title, abstract, representative claims, filing date, assignee, current status
- Record IPC/CPC classification codes
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 · 147 lines · 52 tokens per session scan A 8793fb26c522
prior-art-search is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (16,030 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,290 once invoked, about $0.0003 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
privacy-by-design
Use when building apps that collect user data. Ensures privacy protections are built in from the start—data minimization, consent, encryption.
ethics-committee
Act as a research ethics committee — stress-test a protocol the way an IRB / REC / HREC would. Reviews informed consent, risk-benefit balance, vulnerable populations, data privacy, deception, debriefing, payment, dual-use risks, AI/LLM use in research, and equity in recruitment. Produces a committee-style decision…
freelance-dev-sow
When to use. A potential client wants a fixed-scope software project and needs a one-page SOW before they sign + pay deposit.
advogado-especialista
Advogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor, imobiliario, empresarial, civil e constitucional.
advogado-criminal
Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.