review-specification

review-specification is a command for Claude Code from RobThePCGuy/Claude-Patent-Creator. It costs 22 tokens per session (339 once invoked), scanned A, original, MIT.

A review of a patent specification, the detailed document explaining an invention, against the U.S. written-description, enablement, and best-mode rules in 35 U.S.C. §112(a).

In plain words
What is it for?
Use it to assess whether each claim is supported, whether a skilled person could make and use the invention, and whether the preferred version is disclosed. It produces section-by-section findings, recommendations, and a claim-support matrix.
Why use it?
It helps reveal missing explanations and unsupported claim elements before filing. It also points to relevant sections of the MPEP, the U.S. patent examination manual, while noting that it is not legal advice.

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 assess whether each claim is supported, whether a skilled person could make and use the invention, and whether the preferred version is disclosed. It produces section-by-section findings, recommendations, and a claim-support matrix.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/robthepcguy/claude-patent-creator/review-specification
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.

agentmods badge for review-specification

README.md
[![agentmods](https://agentmods.dev/badge/commands/robthepcguy/claude-patent-creator/review-specification.svg)](https://agentmods.dev/commands/robthepcguy/claude-patent-creator/review-specification)
Your own site
<a href="https://agentmods.dev/commands/robthepcguy/claude-patent-creator/review-specification"><img src="https://agentmods.dev/badge/commands/robthepcguy/claude-patent-creator/review-specification.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 339 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00339
Opus 5 $0.00011 $0.00169
Sonnet 5 $0.00004 $0.00068
Haiku 4.5 $0.00002 $0.00034

Measured 8d ago against content hash 39a5e44e995f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-specification 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 8d 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:

commands/review-specification.md · 49 lines

What it actually says

Specification Review

Check specification for written description, enablement, and best mode requirements.

Focus Area: $ARGUMENTS

What I'll Check

  1. Written Description (35 USC 112(a)) - Shows you possessed the invention
  2. Enablement (35 USC 112(a)) - Person skilled in art can make/use it
  3. Best Mode (35 USC 112(a)) - Preferred embodiment disclosed
  4. Claim Support - All claim elements described

Specified focus area receives extra detail.

Process

  1. Ask for specification (or key sections)
  2. Search MPEP for requirements
  3. Analyze against 112(a) standards
  4. Create claim support matrix
  5. Generate report with:
    • Section-by-section analysis
    • MPEP citations
    • Missing disclosures
    • Recommendations

Output

  • Written description adequacy assessment
  • Enablement scope analysis
  • Claim support matrix
  • Specific improvements needed
  • MPEP references for findings

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. 8d ago First seen · 49 lines · 22 tokens per session scan A 39a5e44e995f

Subscribe to this mod's changes

review-specification is a command published in the GitHub repository RobThePCGuy/Claude-Patent-Creator (179 stars, last pushed 15d ago), licensed MIT. It adds 22 tokens to every session and 339 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.