patent-novelty-check

patent-novelty-check is a skill for Claude Code from wanshuiyin/Auto-claude-code-research-in-sleep. It costs 59 tokens per session (1,388 once invoked), scanned A, original, MIT.

A patentability assessment that checks whether an invention is new and not an obvious variation of earlier publicly known work. It uses patent standards rather than the looser standards used to judge research contributions.

In plain words
What is it for?
Use it to analyse an invention, define key claim elements, compare them with a prior-art report, and outline preliminary method and system claims.
Why use it?
It helps separate features that are already known from features that may support a patent. This makes potential conflicts with earlier patents and publications easier to spot before drafting an application.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Good fit Use it to analyse an invention, define key claim elements, compare them with a prior-art report, and outline preliminary method and system claims.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wanshuiyin/auto-claude-code-research-in-sleep/patent-novelty-check
About the project

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.

wanshuiyin/Auto-claude-code-research-in-sleep · 16,030 stars · on GitHub

Install

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.

Any agent
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill patent-novelty-check
Clone the repo
git clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep

Made for: Claude Code.

Wrote 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.

agentmods badge for patent-novelty-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/patent-novelty-check/github.svg)](https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/patent-novelty-check)
Your own site
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/patent-novelty-check"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/patent-novelty-check/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.

agentmods 80×15 button for patent-novelty-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/patent-novelty-check"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/patent-novelty-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,388 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 13 May 2026
  • Snyk warn 13 May 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.01388
Opus 5 $0.00030 $0.00694
Sonnet 5 $0.00012 $0.00278
Haiku 4.5 $0.00006 $0.00139

Measured 5d ago against content hash 895a084526fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

patent-novelty-check 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 5d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/patent-novelty-check/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Patent Novelty and Non-Obviousness Check

Assess patentability of: $ARGUMENTS

Adapted from /novelty-check for patent legal standards. Research novelty is NOT the same as patent novelty.

Constants

  • REVIEWER_MODEL = gpt-6-astra — Model used via Codex MCP for cross-model examiner verification
  • NOVELTY_STANDARD = patent — Always use legal patentability standard, not research contribution standard

Inputs

  1. Invention description from $ARGUMENTS
  2. patent/PRIOR_ART_REPORT.md (output of /prior-art-search)
  3. patent/INVENTION_BRIEF.md if exists

Shared References

Load ../shared-references/patent-writing-principles.md for novelty/non-obviousness standards. Load ../shared-references/patent-format-us.md for 102/103 analysis framework.

Workflow

Step 1: Define Claim Elements

From the invention description, extract the key claim elements that would define the invention's scope:

  1. List the technical features that make the invention novel
  2. Identify which features are known from prior art vs. inventive
  3. Draft preliminary claim language for 2-3 independent claims (method + system)

Step 2: Anticipation Analysis (Novelty)

For each preliminary claim, test against EACH prior art reference in PRIOR_ART_REPORT.md:

Single-reference test: Does any single reference disclose ALL claim elements?

Claim Element Ref 1 Ref 2 Ref 3 ...
Feature A Yes/No + evidence
Feature B Yes/No + evidence
Feature C Yes/No + evidence
Feature D Yes/No + evidence

Verdict per reference:

  • ANTICIPATED: One reference discloses every element → claim is not novel
  • NOT ANTICIPATED: At least one element missing from every single reference → claim is novel

Step 3: Obviousness Analysis (Inventive Step)

If the invention is novel (passes Step 2), test for obviousness:

Two/three-reference combination test: Can 2-3 references be combined to render the claim obvious?

Read the full file on GitHub · 154 lines

Changes

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.

  1. 5d ago Changed 895a084526fa
  2. 13d ago First seen · 154 lines · 59 tokens per session scan A 374eae99fb0d

Subscribe to this mod's changes

patent-novelty-check 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 59 tokens to every session and 1,388 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.