full-review

full-review is a command for Claude Code from Raw1mage/patentmcp. It costs 14 tokens per session (465 once invoked), scanned A, a copy of full-review, MIT.

A complete review of a patent application for United States Patent and Trademark Office requirements, covering claims, the invention’s written explanation, and filing formalities.

In plain words
What is it for?
Use it to review claims, the specification, abstract, drawings, required sections, filing documents, prior art if requested, and preparation tasks.
Why use it?
It brings separate checks into one report, making it easier to find issues that could delay or weaken a filing.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. 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 review claims, the specification, abstract, drawings, required sections, filing…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/raw1mage/patentmcp/full-review
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 full-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/raw1mage/patentmcp/full-review.svg)](https://agentmods.dev/commands/raw1mage/patentmcp/full-review)
Your own site
<a href="https://agentmods.dev/commands/raw1mage/patentmcp/full-review"><img src="https://agentmods.dev/badge/commands/raw1mage/patentmcp/full-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 465 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 $0.00014 $0.00465
Opus 5 $0.00007 $0.00233
Sonnet 5 $0.00003 $0.00093
Haiku 4.5 $0.00001 $0.00047

Measured 6d ago against content hash 39d0b709f6a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

full-review 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 6d 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 full-review — 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/full-review.md · 69 lines

What it actually says

Complete Patent Application Review

Comprehensive USPTO compliance review of your complete application.

What You'll Get

  1. Claims Analysis - 35 USC 112(b) compliance
  2. Specification Review - 35 USC 112(a) compliance
  3. Formalities Check - MPEP 608 requirements
  4. Prior Art Search (optional) - Similar patents
  5. Consolidated Report - All findings in one place

How It Works

Three specialized reviews run in parallel:

  • /review-claims for claims
  • /review-specification for spec
  • /review-formalities for formalities

Results synthesized into one master report.

What I Need

  1. Patent claims (independent + dependent)
  2. Specification (or key sections)
  3. Abstract
  4. Drawings info (if any)

Provide all at once or incrementally.

Final Report Includes

  • Executive Summary - Overall readiness
  • Critical Issues - Must fix before filing
  • Important Issues - Strongly recommend fixing
  • Minor Improvements - Consider addressing
  • MPEP References - Citations for findings
  • Action Items - Prioritized to-do list
  • Filing Checklist - Everything needed
  • Timeline Estimate - Time to filing-ready

When to Use

Use /full-review when:

  • Have complete draft application
  • Want comprehensive feedback
  • Preparing to file soon

Use individual commands when:

  • Only checking one section
  • Working on specific part
  • Want faster, focused feedback

DISCLAIMER: This tool assists with patent application preparation but does NOT replace legal advice from a registered patent attorney. Always consult with legal counsel before filing. Not affiliated with or endorsed by the USPTO.

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. 6d ago First seen · 69 lines · 14 tokens per session scan A 39d0b709f6a5

Subscribe to this mod's changes

full-review is a command published in the GitHub repository Raw1mage/patentmcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 465 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 full-review, differing in 0 lines, and is treated as a copy.