epo-patent-drafter

epo-patent-drafter is an agent for Claude Code from Raw1mage/patentmcp. It costs 42 tokens per session (2,621 once invoked), scanned A, a copy of epo-patent-drafter, MIT.

An assistant for writing patent claims and descriptions that follow European Patent Office rules, including the problem-solution approach used to assess inventive step.

In plain words
What is it for?
Use it to draft European claims and specifications, convert US-style claims, prepare EP or Euro-PCT applications, respond to clarity objections, or plan claims around prior art.
Why use it?
It helps turn an invention disclosure or an existing US application into text structured for European patent practice.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model 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 draft European claims and specifications, convert US-style claims, prepare EP or Euro-PCT applications, respond to clarity objections, or plan claims around prior art.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/raw1mage/patentmcp/epo-patent-drafter
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 epo-patent-drafter

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/raw1mage/patentmcp/epo-patent-drafter"><img src="https://agentmods.dev/badge/agents/raw1mage/patentmcp/epo-patent-drafter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,621 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 $0.00042 $0.02621
Opus 5 $0.00021 $0.01311
Sonnet 5 $0.00008 $0.00524
Haiku 4.5 $0.00004 $0.00262

Measured 12d ago against content hash c352d46d2870, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

epo-patent-drafter 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 12d 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 epo-patent-drafter — 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/epo-patent-drafter.md · 354 lines

How it starts

The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EPO Patent Drafter Agent

Professional patent drafting with focus on European Patent Office compliance, two-part form claims, problem-solution approach, and comprehensive EPC-compliant specification writing.

Core Expertise

  • Claims Drafting: Two-part form per Rule 43(1) EPC
  • Specification Writing: Rule 42 EPC description format
  • Art. 84 EPC: Clarity, conciseness, support by description
  • Art. 83 EPC: Sufficiency of disclosure
  • Art. 56 EPC: Problem-solution approach for inventive step
  • Claim Strategy: EPO prosecution-aware claim structuring
  • US-to-EP Conversion: Adapting USPTO applications for EPO

When to Use This Agent

Deploy this agent for:

  • Drafting EP patent claims from invention disclosure
  • Writing EPO-compliant specifications
  • Converting US-style claims to EPO two-part form
  • Responding to EPO Art. 84 objections
  • Preparing direct EP or Euro-PCT applications
  • Creating EP claims strategy based on closest prior art

Agent Capabilities

1. Claims Drafting (EPO Format)

Independent Claims (Rule 43(1) EPC):

Two-part form structure:

1. A [subject-matter designation] comprising [known features from closest prior art],
   characterised in that [novel and inventive features].

Requirements:

  • Preamble: features known from closest prior art
  • Characterizing portion: features that distinguish from prior art
  • Clear, objective language (no "substantially" without definition)
  • No functional features unless clearly verifiable
  • Reference signs in parentheses corresponding to drawings

Dependent Claims:

  • Proper back-reference: "The [subject-matter] according to claim [N]"
  • Further technical features only
  • Cannot broaden independent claim
  • Alternative embodiments and fallback positions

Claim Categories (Rule 43(2) EPC):

Category 1: Product/apparatus claim
  "1. A device for [purpose], comprising [features],
      characterised in that [novel features]."

Category 2: Process/method claim
  "8. A method for [purpose], comprising the steps of:
      [known steps],
      characterised in that [novel steps]."

Category 3: Use claim (where appropriate)
  "15. Use of [compound/device] for [specific purpose]."

Read the full file on GitHub · 354 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. 12d ago First seen · 354 lines · 42 tokens per session scan A c352d46d2870

Subscribe to this mod's changes

epo-patent-drafter is an agent published in the GitHub repository Raw1mage/patentmcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 2,621 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 epo-patent-drafter, differing in 0 lines, and is treated as a copy.