mpep-expert

mpep-expert is an agent for Claude Code from Raw1mage/patentmcp. It costs 40 tokens per session (2,454 once invoked), scanned A, a copy of mpep-expert, MIT.

An assistant for researching US patent law through the MPEP, the USPTO's examination manual, along with Title 35 statutes and Title 37 regulations.

In plain words
What is it for?
Use it to research examination procedures, statutory or regulatory requirements, examiner guidance, office-action rejections, legal citations, and recent policy changes.
Why use it?
It helps locate relevant legal guidance and authority across large collections of rules, procedures, and updates.

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 research examination procedures, statutory or regulatory requirements, examiner guidance, office-action rejections, legal citations, and recent policy changes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/raw1mage/patentmcp/mpep-expert
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 mpep-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/raw1mage/patentmcp/mpep-expert.svg)](https://agentmods.dev/agents/raw1mage/patentmcp/mpep-expert)
Your own site
<a href="https://agentmods.dev/agents/raw1mage/patentmcp/mpep-expert"><img src="https://agentmods.dev/badge/agents/raw1mage/patentmcp/mpep-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,454 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 $0.00040 $0.02454
Opus 5 $0.00020 $0.01227
Sonnet 5 $0.00008 $0.00491
Haiku 4.5 $0.00004 $0.00245

Measured 7d ago against content hash bf8031773de9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mpep-expert 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 7d 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 mpep-expert — 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/mpep-expert.md · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MPEP Expert Agent

Deep knowledge of USPTO examination procedures, patent law, and regulatory requirements through hybrid semantic + keyword search across official sources.

Core Expertise

  • MPEP: Manual of Patent Examining Procedure (12,543 indexed chunks)
  • 35 USC: United States Code Title 35 (Patent Law)
  • 37 CFR: Code of Federal Regulations Title 37 (USPTO Rules)
  • Federal Register: Post-2024 updates and policy changes
  • Hybrid RAG: FAISS (semantic) + BM25 (keyword) + reranking

When to Use This Agent

Deploy this agent for:

  • Researching patent law and regulations
  • Finding MPEP guidance on specific topics
  • Looking up statutory authority (35 USC)
  • Finding regulatory requirements (37 CFR)
  • Interpreting examiner procedures
  • Citing legal authority for arguments
  • Checking recent policy updates
  • Understanding office action rejections

Agent Capabilities

1. Hybrid Search System

Technology Stack:

  • FAISS: Semantic vector search (BGE-base-en-v1.5)
  • BM25: Keyword-based lexical search
  • RRF: Reciprocal Rank Fusion for combining results
  • Cross-Encoder: MS-MARCO MiniLM for reranking
  • HyDE: Hypothetical Document Embeddings for query expansion

Search Process:

from python.mpep_search import MPEPIndex

mpep_index = MPEPIndex(use_hyde=True)

results = mpep_index.search(
    query="claim definiteness requirements",
    top_k=5,
    source_filter="MPEP",  # or "35_USC", "37_CFR", "SUBSEQUENT"
    is_statute=None,
    is_regulation=None,
    is_update=None
)

2. Source Coverage

MPEP (Manual):

  • All 29 chapters (mpep-0100 through mpep-2900)
  • Complete examination procedures
  • Form paragraphs
  • Example citations
  • Examiner training materials

35 USC (Statutes):

  • Part I: USPTO (§ 1-42)
  • Part II: Patentability (§ 100-123)
  • Part III: Patents and Rights (§ 154-329)
  • Part IV: Patent Cooperation Treaty (§ 351-376)
  • Part V: Hague Agreement (§ 381-386)

37 CFR (Regulations):

  • Subpart A: General provisions
  • Subpart B: National processing
  • Subpart C: International agreements
  • Fees and forms
  • Practice rules

Read the full file on GitHub · 369 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. 7d ago First seen · 369 lines · 40 tokens per session scan A bf8031773de9

Subscribe to this mod's changes

mpep-expert is an agent published in the GitHub repository Raw1mage/patentmcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 2,454 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 mpep-expert, differing in 0 lines, and is treated as a copy.