search-prior-art

search-prior-art is a command for Claude Code from Raw1mage/patentmcp. It costs 19 tokens per session (2,006 once invoked), scanned A, a copy of search-prior-art, MIT.

A search for earlier patents and other patent records that may describe parts of an invention. Prior art is existing public knowledge used to judge whether an invention is new and patentable.

In plain words
What is it for?
Use it to define an invention, build search terms, search patent classifications, study technology history, and produce a patentability assessment.
Why use it?
It helps reveal similar inventions before filing and highlights features that may affect patentability.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the claude-patent-creator-standalone plugin — 17 skills, 16 commands, 13 agents, 2 hooks shipped together

Good fit Use it to define an invention, build search terms, search patent classifications, study technology history, and produce a patentability assessment.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/raw1mage/patentmcp/search-prior-art
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.

Clone the repo
git clone --depth 1 https://github.com/Raw1mage/patentmcp

Made for: Claude Code.

Or install claude-patent-creator-standalone, the plugin that ships this one along with the rest of its 17 skills, 16 commands, 13 agents, 2 hooks.

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 search-prior-art

README.md
[![agentmods](https://agentmods.dev/badge/commands/raw1mage/patentmcp/search-prior-art/github.svg)](https://agentmods.dev/commands/raw1mage/patentmcp/search-prior-art)
Your own site
<a href="https://agentmods.dev/commands/raw1mage/patentmcp/search-prior-art"><img src="https://agentmods.dev/badge/commands/raw1mage/patentmcp/search-prior-art/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 search-prior-art

Your own site · 80×15
<a href="https://agentmods.dev/commands/raw1mage/patentmcp/search-prior-art"><img src="https://agentmods.dev/badge/commands/raw1mage/patentmcp/search-prior-art.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,006 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 100% copy Near-identical to another mod 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 $0.00019 $0.02006
Opus 5 $0.00010 $0.01003
Sonnet 5 $0.00004 $0.00401
Haiku 4.5 $0.00002 $0.00201

Measured 10d ago against content hash f7bc48385c94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

search-prior-art 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.

Origin

This is a copy

100% identical to search-prior-art — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

refs/Claude-Patent-Creator/commands/search-prior-art.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Search for Prior Art

Professional patent prior art search with patentability assessment.

What This Command Does

Executes a systematic 7-step prior art search methodology:

  1. Invention Definition (2-3 min) - Extract key features
  2. Keyword Strategy (2-3 min) - Build search terms
  3. Broad Search (3-5 min) - Cast wide net
  4. CPC Identification (2-3 min) - Find classifications
  5. Deep CPC Search (5-10 min) - Thorough classification search
  6. Timeline Analysis (2-3 min) - Technology evolution
  7. Patentability Report (5-10 min) - Assessment + recommendations

Total Time: 25-45 minutes for thorough search

Who This Is For

  • Inventors before filing
  • Patent attorneys/agents
  • Companies conducting due diligence
  • Researchers checking novelty
  • Anyone assessing patentability

Process

Step 1: Tell Me About Your Invention

I'll ask you:

  • What problem does it solve?
  • How does it work?
  • What are the key features?
  • What makes it novel?

Example:

> Describe your invention...

User: A blockchain-based authentication system that uses
distributed ledger verification instead of centralized
password databases.

> Got it. Key features I extracted:
> - Blockchain technology
> - Authentication/verification
> - Distributed ledger
> - No centralized database
>
> Is this correct? Any other key features?

Step 2: Keyword Search

I'll search BigQuery (100M+ patents) using keywords derived from your description:

# I'll run searches like:
"blockchain authentication"
"distributed ledger verification"
"decentralized identity"
"cryptographic authentication"

I'll review 20-30 results per query and identify the most relevant patents.

Step 3: CPC Classification Search

I'll:

  • Extract CPC codes from relevant patents found
  • Identify primary classification areas
  • Search thoroughly within those classifications

Common CPC codes:

  • G06F: Computing/data processing
  • H04L: Digital communication
  • G06Q: Business methods
  • G06N: AI/neural networks

Read the full file on GitHub · 327 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 · 327 lines · 19 tokens per session scan A f7bc48385c94

Subscribe to this mod's changes

search-prior-art is a command published in the GitHub repository Raw1mage/patentmcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 2,006 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to search-prior-art, differing in 0 lines, and is treated as a copy.