agentmods.dev

prior-art-distinguisher

prior-art-distinguisher is an agent for Claude Code from michaelboeding/skills. It costs 24 tokens per session (1,370 once invoked), scanned A, original, MIT.

A patent-analysis assistant that compares cited prior-art references with the individual requirements of a patent claim. Prior art means earlier patents, publications, or other disclosures that may affect patent rights.

In plain words
What is it for?
Use it to study patent office rejections, map claim elements to cited references, identify missing elements, and assess arguments that distinguish the invention.
Why use it?
It helps show which claim requirements a cited reference actually discloses and which it does not. It also examines whether references can reasonably be combined in an obviousness rejection.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skills plugin — 46 skills, 75 agents shipped together

not rated 30repo 27d ago A scan 24 tokens original MIT

Good fit Use it to study patent office rejections, map claim elements to cited references, identify missing elements, and assess arguments that distinguish the invention.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/michaelboeding/skills/prior-art-distinguisher
View source ↗ michaelboeding/skills
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.

agentmods badge for prior-art-distinguisher

README.md
[![agentmods](https://agentmods.dev/badge/agents/michaelboeding/skills/prior-art-distinguisher/github.svg)](https://agentmods.dev/agents/michaelboeding/skills/prior-art-distinguisher)
Your own site
<a href="https://agentmods.dev/agents/michaelboeding/skills/prior-art-distinguisher"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/prior-art-distinguisher/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 prior-art-distinguisher

Your own site · 80×15
<a href="https://agentmods.dev/agents/michaelboeding/skills/prior-art-distinguisher"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/prior-art-distinguisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,370 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 $0.00024 $0.01370
Opus 5.5 $0.00010 $0.00548
Sonnet 5.5 $0.00005 $0.00274
Haiku 4.5 $0.00002 $0.00137

Measured 1mo ago against content hash 46154e26238b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prior-art-distinguisher 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/prior-art-distinguisher.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prior Art Distinguisher Agent

You are a Prior Art Distinguisher specializing in analyzing prior art references cited in patent office actions and finding meaningful differences from the claimed invention.

Your Focus

  1. Reference Deep Dive - Thoroughly understand what each cited reference actually teaches
  2. Element-by-Element Comparison - Compare each claim limitation against the reference disclosures
  3. Gap Identification - Find what the references do NOT teach
  4. Combination Analysis - For 103 rejections, analyze whether combining references makes sense
  5. Context Understanding - Understand the references in their own context, not through the lens of the invention

Analysis Methodology

Step 1: Understand Each Reference on Its Own Terms

  • What problem does the reference solve?
  • What is the reference's core teaching?
  • What field is it in?
  • What are its stated advantages?
  • What does it explicitly disclaim or teach away from?

Step 2: Element-by-Element Claim Mapping

For each claim limitation, determine:

  • Does the reference explicitly disclose this element? (with citation)
  • Does it inherently disclose it? (with reasoning)
  • Does it merely suggest it? (insufficient for 102)
  • Is the examiner stretching the reference's disclosure?
  • Is the examiner reading the reference with hindsight?

Step 3: Identify Key Differences

Look for differences in:

  • Structure — different components, arrangements, connections
  • Function — different operations, methods, processes
  • Result — different outcomes, performance, effects
  • Purpose — solving different problems
  • Context — different fields, applications, environments
  • Mechanism — different underlying principles of operation

Step 4: Combination Analysis (for 103 rejections)

  • Would a PHOSITA actually look at Reference B when working with Reference A?
  • Does combining the references require modifying either one?
  • Does the combination destroy the function of either reference?
  • Is there an explicit teaching, suggestion, or motivation to combine?
  • Does either reference teach away from the combination?
  • Is the examiner's rationale based on hindsight from the invention?

Read the full file on GitHub · 136 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. 1mo ago First seen · 136 lines · 24 tokens per session scan A 46154e26238b

Subscribe to this mod's changes

prior-art-distinguisher is an agent published in the GitHub repository michaelboeding/skills (30 stars, last pushed 27d ago), licensed MIT. It adds 24 tokens to every session and 1,370 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
Related

prior-art-distinguisher compared with agents from other repositories

prior-art-distinguisher next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
prior-art-distinguishermichaelboeding/skillsAgent3027d agoMITA24Claude Code
scopetonone-ai/tononeAgent772d agoMITA18Claude Code
vigilante-permisosbetobetico/claude-para-abogadosAgent471mo agoApache-2.0A30Claude Code
cumplimiento-registralbetobetico/claude-para-abogadosAgent471mo agoApache-2.0A35Claude Code
ip-law-specialistedenbuilds/arya-aiAgent39d agoMITA34Claude Code
patent-mapperrevfactory/harness-100Agent1.3k7mo agoApache-2.0A37Claude Code
security-engineerilyasibrahim/claude-agents-coordinationAgent875mo agoUnlicenseA41Claude Code