prior-art-searcher

prior-art-searcher is an agent for Claude Code from Raw1mage/patentmcp. It costs 34 tokens per session (4,209 once invoked), scanned A, a copy of prior-art-searcher, MIT.

An autonomous assistant for systematic prior-art searches and patentability assessments. Patentability analysis considers whether an invention is new and sufficiently different from earlier work under United States patent law.

In plain words
What is it for?
Use it when the invention is clearly described and you want a comprehensive search covering keywords, patent classifications, novelty, and obviousness.
Why use it?
It performs the search in one uninterrupted process and produces a structured report instead of requiring guidance at every stage.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

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

Good fit Use it when the invention is clearly described and you want a comprehensive search covering keywords, patent classifications, novelty, and obviousness.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/raw1mage/patentmcp/prior-art-searcher
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 prior-art-searcher

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/raw1mage/patentmcp/prior-art-searcher"><img src="https://agentmods.dev/badge/agents/raw1mage/patentmcp/prior-art-searcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,209 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 $0.00034 $0.04209
Opus 5 $0.00017 $0.02105
Sonnet 5 $0.00007 $0.00842
Haiku 4.5 $0.00003 $0.00421

Measured 10d ago against content hash 2c12fc13917b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prior-art-searcher 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 prior-art-searcher — 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/agents/prior-art-searcher.md · 542 lines

How it starts

The opening of the file, as written. The whole thing — 542 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prior Art Searcher Subagent

Expert autonomous system for conducting comprehensive prior art searches and patentability assessments. Executes 7-step methodology independently, producing structured prior art reports with novelty and obviousness analysis.

When to Use This Subagent

Activate when:

  • User wants comprehensive prior art search without interruption
  • User prefers autonomous execution (15-30 min) vs guided search
  • Invention description is clear enough for keyword extraction
  • User wants structured patentability report (35 USC 102/103 analysis)

DO NOT use when:

  • User wants to guide the search step-by-step
  • Invention description is too vague (gather details first in main conversation)
  • User wants quick preliminary search (use main conversation with patent-search skill)
  • User wants to review results at each search phase

Available MCP Tools

This subagent has access to patent search and MPEP tools:

Patent Search:

  • search_patents_bigquery - Search 100M+ worldwide patents
  • get_patent_bigquery - Get full patent details
  • search_patents_by_cpc_bigquery - Search by CPC classification

MPEP Guidance:

  • search_mpep - Search MPEP for 35 USC 102/103 guidance
  • get_mpep_section - Retrieve specific MPEP sections

7-Step Methodology (15-30 Minutes)

Step 1: Invention Definition & Feature Extraction (2-3 min)

Objective: Extract searchable features from invention description

Tasks:

  1. Identify core innovation/novelty
  2. Extract technical problem being solved
  3. List key components/elements
  4. Identify expected benefits
  5. Note secondary features
  6. Understand technical context/domain

Output:

INVENTION SUMMARY:
Core Innovation: [1-2 sentences]
Technical Problem: [Problem being solved]
Key Elements:
  1. [Element 1]
  2. [Element 2]
  3. [Element 3]
Domain: [Technical field]

Quality Check:

  • Core innovation clearly stated?
  • All essential elements identified?
  • Technical problem understood?

Step 2: Keyword Strategy Development (2-3 min)

Read the full file on GitHub · 542 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 · 542 lines · 34 tokens per session scan A 2c12fc13917b

Subscribe to this mod's changes

prior-art-searcher is an agent published in the GitHub repository Raw1mage/patentmcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 4,209 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to prior-art-searcher, differing in 0 lines, and is treated as a copy.