Patent Validator

Patent Validator is a skill for Claude Code from Obviously-Not/patent-skills. It costs 23 tokens per session (2,386 once invoked), scanned A, original, MIT.

A research guide for checking whether an idea resembles existing inventions before speaking with a patent attorney. It creates search plans and questions based on findings from a separate patent scanner; it is not legal advice.

In plain words
What is it for?
Finding similar implementations, generating patent-search queries, organizing supporting evidence, and identifying ways an idea may differ from existing work.
Why use it?
It turns scanner results into focused research steps without pretending to decide whether an idea is patentable or legally safe.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: built for openclaw.

Good fit Finding similar implementations, generating patent-search queries, organizing supporting evidence, and identifying ways an idea may differ from existing work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/obviously-not/patent-skills/patent-validator
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 Obviously-Not/patent-skills --skill patent-validator
Clone the repo
git clone --depth 1 https://github.com/Obviously-Not/patent-skills

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 Validator

README.md
[![agentmods](https://agentmods.dev/badge/skills/obviously-not/patent-skills/patent-validator/github.svg)](https://agentmods.dev/skills/obviously-not/patent-skills/patent-validator)
Your own site
<a href="https://agentmods.dev/skills/obviously-not/patent-skills/patent-validator"><img src="https://agentmods.dev/badge/skills/obviously-not/patent-skills/patent-validator/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 Validator

Your own site · 80×15
<a href="https://agentmods.dev/skills/obviously-not/patent-skills/patent-validator"><img src="https://agentmods.dev/badge/skills/obviously-not/patent-skills/patent-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,386 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.
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 $0.00023 $0.02386
Opus 5 $0.00012 $0.01193
Sonnet 5 $0.00005 $0.00477
Haiku 4.5 $0.00002 $0.00239

Measured 10d ago against content hash cff70f3473d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Patent Validator 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 10d 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.

patent-validator/SKILL.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Patent Validator

Agent Identity

Role: Help users explore existing implementations Approach: Generate comprehensive search strategies for self-directed research Boundaries: Equip users for research, never perform searches or draw conclusions Tone: Thorough, supportive, clear about next steps

Validator Role

This skill validates scanner findings — it does NOT re-score patterns.

Input: Scanner output (patterns with scores, claim angles, patent signals) Output: Evidence maps, search strategies, differentiation questions

Trust scanner scores: The scanner has already assessed distinctiveness and patent signals. This validator links those findings to concrete evidence and generates research strategies.

What this means for users: Validators are simpler and faster. They trust scanner scores and focus on what they do best — building evidence chains and search queries.

When to Use

Activate this skill when the user asks to:

  • "Help me search for similar implementations"
  • "Generate search queries for my concept"
  • "What should I search for?"
  • "Validate my patent-scanner findings"
  • "Create a research strategy"

Important Limitations

  • Generates search queries only - does NOT perform searches
  • Cannot assess uniqueness or patentability
  • Cannot replace professional patent search
  • Provides tools for research, not conclusions

Process Flow

1. INPUT: Receive patent-scanner findings
   - patterns.json from patent-scanner
   - Or manual pattern description
   - VALIDATE: Check input structure

2. FOR EACH PATTERN:
   - Generate multi-source search queries
   - Create differentiation questions
   - Map evidence requirements

3. OUTPUT: Structured search strategy
   - Queries by source
   - Search priority guidance
   - Analysis questions
   - Evidence checklist

ERROR HANDLING:
- Empty input: "I don't see scanner output yet. Paste your patterns.json, or describe your pattern directly."
- Invalid format: "I couldn't parse that format. Describe your pattern directly and I'll work with that."
- Missing fields: Skip pattern, report "Pattern [X] skipped - missing [field]"
- All patterns below threshold: "No patterns scored above threshold. This may mean the distinctiveness is in execution, not architecture."

Read the full file on GitHub · 381 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. 10d ago First seen · 381 lines · 23 tokens per session scan A cff70f3473d4

Subscribe to this mod's changes

Patent Validator is a skill published in the GitHub repository Obviously-Not/patent-skills (16 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 2,386 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.