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 patent-reviewgit 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/patent-review)<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/patent-review"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/patent-review/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/patent-review"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/patent-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk pass
- 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 | $0.00050 | $0.01674 |
| Opus 5 | $0.00025 | $0.00837 |
| Sonnet 5 | $0.00010 | $0.00335 |
| Haiku 4.5 | $0.00005 | $0.00167 |
Grade A, and why
patent-review 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 today.
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:
- patent-review — 94% identical, 16 lines differ
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patent Examiner Review via Codex MCP (xhigh reasoning)
Get a multi-round patent examiner review of the patent application based on: $ARGUMENTS
Adapted from /research-review. The reviewer persona is a patent examiner, not a paper reviewer.
Constants
REVIEWER_MODEL = gpt-6-astra— Model used via Codex MCPREVIEW_ROUNDS = 2— Number of review roundsEXAMINER_PERSONA = "patent-examiner"— GPT-6-Astra persona
Prerequisites
- Codex MCP Server configured:
claude mcp add codex -s user -- python3 "$HOME/aris_repo/mcp-servers/codex-exec/server.py" # your ARIS clone's path
Inputs
patent/CLAIMS.md— all drafted claimspatent/specification/— all specification sectionspatent/figures/numeral_index.md— reference numeral mappingpatent/PRIOR_ART_REPORT.md— known prior artpatent/INVENTION_DISCLOSURE.md— invention structure
Workflow
Step 1: Gather Patent Context
Before calling the external reviewer, compile a comprehensive briefing:
- Read all claims (independent + dependent)
- Read specification sections (at least summary and detailed description)
- Read prior art report for context
- Identify: core inventive concept, claim scope, known prior art, target jurisdiction
Step 2: Round 1 — Full Examiner Review
Send to REVIEWER_MODEL via mcp__codex__codex with xhigh reasoning:
mcp__codex__codex:
model: gpt-6-astra
config: {"model_reasoning_effort": "xhigh"}
prompt: |
You are a senior patent examiner at the [USPTO/CNIPA/EPO].
Examine this patent application and issue a detailed office action.
CLAIMS:
[all claims]
SPECIFICATION SUMMARY:
[key sections: title, technical field, background, summary, abstract]
PRIOR ART KNOWN:
[prior art references]
PATENTABILITY STANDARDS TO APPLY:
[US: 35 USC 101/102/103/112 | CN: Articles 22, 26 | EP: Articles 54, 56, 83, 84]
Please issue an office action covering:
1. CLAIM CLARITY (112(b)/Art 84):
- Are all terms definite?
- Any indefinite functional language?
- Antecedent basis issues?
2. WRITTEN DESCRIPTION (112(a)/Art 83 first para):
- Does the spec support ALL claim scope?
- Any claim elements without spec support?
3. ENABLEMENT (112(a)/Art 83):
- Can a POSITA practice the invention?
- Any missing algorithm/structure for functional claims?
4. NOVELTY (102/Art 54):
- Would any known reference anticipate any claim?
- Identify the closest single reference.
5. NON-OBVIOUSNESS (103/Art 56):
- Would any combination render claims obvious?
- What is the motivation to combine?
6. CLAIM SCOPE:
- Are independent claims broad enough to be commercially valuable?
- Do dependent claims provide meaningful fallback positions?
- Any claims that are too broad (likely rejected) or too narrow (not valuable)?
7. SPECIFICATION QUALITY:
- Language issues (subjective terms, relative terms, result-to-be-achieved)
- Reference numeral consistency
- Missing embodiments
Format your response as a formal office action with:
- GROUNDS OF REJECTION for each issue (cite statute)
- SUGGESTED AMENDMENTS for each issue
- OVERALL PATENTABILITY SCORE: 1-10
Be rigorous and specific. This is a real examination.
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.
- today Changed 8c02c3040f0f
- 5d ago Changed 69b9d09cf150
- 13d ago First seen · 204 lines · 50 tokens per session scan A dceadf86a54b
patent-review 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 50 tokens to every session and 1,674 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.