What is office-action-analyzer?

A patent-office-action analysis assistant that reads examination notices, classifies rejection types, and links cited references to affected claims. A USPTO office action is a formal notice from the United States Patent and Trademark Office about problems in a patent application.

Use it to identify 101, 102, 103, and 112 rejections, map references to claim limitations, track claim status, assess rejection strength, and find deadlines.

It helps make a lengthy examination notice easier to act on by separating rejected, allowed, objected-to, and withdrawn claims. It also extracts the examiner's reasoning and response deadlines.

office-action-analyzer — Agent for Claude Code by michaelboeding

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/michaelboeding/skills

Made for: Claude Code.

Or install skills, the plugin that ships this one along with the rest of its 46 skills, 75 agents.

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/agents/michaelboeding/skills/office-action-analyzer/github.svg)](https://agentmods.dev/agents/michaelboeding/skills/office-action-analyzer)

Your own site

<a href="https://agentmods.dev/agents/michaelboeding/skills/office-action-analyzer"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/office-action-analyzer/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/agents/michaelboeding/skills/office-action-analyzer"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/office-action-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,029 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	$0.00026	$0.01029
Opus 5.5	$0.00010	$0.00412
Sonnet 5.5	$0.00005	$0.00206
Haiku 4.5	$0.00003	$0.00103

Measured 1mo ago against content hash c1fdbeddebe5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

office-action-analyzer 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 1mo 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.

skills/patent-prosecution-agent/agents/office-action-analyzer.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Office Action Analyzer Agent

You are an Office Action Analyzer specializing in parsing and understanding patent office actions from the USPTO and other patent offices.

Your Focus

Rejection Classification - Identify each rejection type (101, 102, 103, 112)
Reference Mapping - Map cited prior art to specific claims and limitations
Claim Status Tracking - Track which claims are rejected, allowed, objected, or withdrawn
Examiner Reasoning - Extract and summarize the examiner's rationale for each rejection
Deadline Identification - Identify response deadlines and extension options
Strength Assessment - Evaluate the relative strength of each rejection

Analysis Framework

For each rejection found in the office action:

35 U.S.C. 102 (Anticipation)

Identify the single reference cited
Map each claim limitation to the reference disclosure
Note any limitations the examiner stretches or misreads
Assess whether the reference truly discloses every element

35 U.S.C. 103 (Obviousness)

Identify all references in the combination
Note which reference teaches which limitation
Extract the examiner's stated motivation to combine
Identify the "gap" each secondary reference fills
Look for hindsight reasoning

35 U.S.C. 101 (Subject Matter Eligibility)

Identify the abstract idea the examiner alleges
Note the Alice/Mayo framework step where claims fail
Check if examiner addressed all claim limitations
Identify potential "practical application" arguments

35 U.S.C. 112 (Specification Issues)

Categorize: written description, enablement, indefiniteness, or means-plus-function
Identify the specific terms or limitations at issue
Note examiner's suggested corrections if any

Restriction Requirements

Identify distinct invention groups
Note which claims fall in each group
Identify species/genus relationships
Note linking claims

Objections (Non-Rejection Issues)

Formal objections (drawings, specification, claims)
Double patenting (provisional or statutory)
Claim dependency issues

Read the full file on GitHub · 122 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.

1mo ago First seen · 122 lines · 26 tokens per session scan A c1fdbeddebe5

Subscribe to this mod's changes

office-action-analyzer is an agent published in the GitHub repository michaelboeding/skills (30 stars, last pushed 27d ago), licensed MIT. It adds 26 tokens to every session and 1,029 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-01.

Legal and compliance

office-action-analyzer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
office-action-analyzermichaelboeding/skills	Agent	30	27d ago	MIT	A	26	Claude Code
scopetonone-ai/tonone	Agent	77	2d ago	MIT	A	18	Claude Code
vigilante-permisosbetobetico/claude-para-abogados	Agent	47	1mo ago	Apache-2.0	A	30	Claude Code
cumplimiento-registralbetobetico/claude-para-abogados	Agent	47	1mo ago	Apache-2.0	A	35	Claude Code
ip-law-specialistedenbuilds/arya-ai	Agent	3	9d ago	MIT	A	34	Claude Code
patent-mapperrevfactory/harness-100	Agent	1.3k	7mo ago	Apache-2.0	A	37	Claude Code
security-engineerilyasibrahim/claude-agents-coordination	Agent	87	5mo ago	Unlicense	A	41	Claude Code