Code Patent Scanner

Code Patent Scanner is a skill for Claude Code from Obviously-Not/patent-skills. It costs 25 tokens per session (5,132 once invoked), scanned A, original, MIT.

A local code scanner that finds distinctive patterns in a codebase and organizes them as evidence for discussion with a patent professional. It does not give legal advice or decide whether something is patentable.

In plain words
What is it for?
Use it to identify possible inventions, describe their core mechanisms, and prepare scored findings with supporting evidence for a patent consultation.
Why use it?
It helps separate the underlying idea in the code from implementation details, making early patent conversations more focused.

Skill for Claude Code

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

Good fit Use it to identify possible inventions, describe their core mechanisms, and prepare scored findings with supporting evidence for a patent consultation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/obviously-not/patent-skills/code-patent-scanner
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 code-patent-scanner
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 Code Patent Scanner

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/obviously-not/patent-skills/code-patent-scanner"><img src="https://agentmods.dev/badge/skills/obviously-not/patent-skills/code-patent-scanner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,132 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 $0.00025 $0.05132
Opus 5 $0.00013 $0.02566
Sonnet 5 $0.00005 $0.01026
Haiku 4.5 $0.00003 $0.00513

Measured 9d ago against content hash 0fe0e76c39bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Code Patent Scanner 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 9d 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.

code-patent-scanner/SKILL.md · 498 lines

How it starts

The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Patent Scanner

Agent Identity

Role: Help users discover what makes their code distinctive Approach: Provide structured analysis with clear scoring and evidence Boundaries: Illuminate patterns, never make legal determinations Tone: Precise, encouraging, honest about uncertainty Safety: This skill operates locally. It does not transmit code or analysis results to any external service. It does not modify, delete, or write any files.

Patent Attorney Methodology (John Branch)

This skill incorporates patterns from patent attorney John Branch:

Key Insight: Lossy Abstraction is a Feature

"I don't need to see the code to draft claims. I need to understand what the invention IS." — John Branch

Why this matters: Broad claims are harder to design around. Implementation details limit claim scope. Focus on the CORE MECHANISM, not the IMPLEMENTATION.

The Abstraction Principle (JB-2)

If your description could only apply to YOUR implementation, it's too narrow. If a competitor could implement it differently and the description still applies, it's appropriately broad.

When analyzing code, abstract from implementation to core mechanism:

Implementation (Skip) Abstraction (Use)
"calls bcrypt.compare()" "applies cryptographic one-way function"
"stores in PostgreSQL" "persists to durable storage"
"uses Redis for caching" "maintains transient state in memory store"
"sends HTTP POST request" "transmits data via network protocol"
"parses JSON response" "deserializes structured data format"

Enablement preservation: Keep both abstract and concrete references:

  • abstract_mechanism: "applies cryptographic one-way function"
  • concrete_reference: "bcrypt.compare() at auth/verify.go:45"

When to Use

Activate this skill when the user asks to:

  • "Scan my code for distinctive patterns"
  • "Analyze this repo for unique implementations"
  • "Find innovative code in my project"
  • "What's technically interesting in this codebase?"

Read the full file on GitHub · 498 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. 9d ago First seen · 498 lines · 25 tokens per session scan A 0fe0e76c39bb

Subscribe to this mod's changes

Code Patent Scanner is a skill published in the GitHub repository Obviously-Not/patent-skills (16 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 5,132 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.