What is search-prior-art?

A structured search for prior art, meaning earlier patents and other public information relevant to an invention. It uses a seven-step process to search a patent collection, classifications, keywords, and technology timelines, then assesses patentability.

Use it to define an invention's key features, find relevant patents, identify patent classifications, analyze the technology's history, and produce a patentability report with recommendations.

It helps determine what is already known before filing and identifies material that may affect novelty or obviousness. This can guide whether to file and how to frame the claims.

search-prior-art — Command for Claude Code by RobThePCGuy

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/RobThePCGuy/Claude-Patent-Creator

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/robthepcguy/claude-patent-creator/search-prior-art/github.svg)](https://agentmods.dev/commands/robthepcguy/claude-patent-creator/search-prior-art)

Your own site

<a href="https://agentmods.dev/commands/robthepcguy/claude-patent-creator/search-prior-art"><img src="https://agentmods.dev/badge/commands/robthepcguy/claude-patent-creator/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/robthepcguy/claude-patent-creator/search-prior-art"><img src="https://agentmods.dev/badge/commands/robthepcguy/claude-patent-creator/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 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.

Model	Per session	Once 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 11d 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 11d 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:

search-prior-art — 100% identical, 0 lines differ

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:

Invention Definition (2-3 min) - Extract key features
Keyword Strategy (2-3 min) - Build search terms
Broad Search (3-5 min) - Cast wide net
CPC Identification (2-3 min) - Find classifications
Deep CPC Search (5-10 min) - Thorough classification search
Timeline Analysis (2-3 min) - Technology evolution
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.

11d 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 RobThePCGuy/Claude-Patent-Creator (181 stars, last pushed yesterday), 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Legal and compliance Research bigquery claude-code-plugin faiss mcp-server mpep

setup-video-vision

Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies.

jordanrendric/claude-video-vision · 20 tokens

coding-audit

Medical-coding / revenue-cycle compliance audit. Invokes rcm-reviewer to assess autonomous ICD-10-CM / CPT / HCPCS coding for False Claims Act exposure (upcoding/unbundling), NCCI edits + MUEs, medical necessity (LCD/NCD), modifier discipline, HIPAA minimum-necessary — and force a certified-coder (CPC/CCS) sign-off.

avelikiy/great_cto · 81 tokens

search-prior-art