What is patent-prompts AGENTS.md?

A set of instructions for a repository containing prompts for patent work, such as drafting claims and analysing earlier inventions.

It helps with invention disclosures, patent claims, prior-art analysis, prosecution, detectability assessments, and portfolio planning.

It explains how to navigate and use the repository's specialised prompts for legal and technical patent tasks.

How arcprime-ip/patent-prompts configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to arcprime-ip/patent-prompts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/arcprime-ip/patent-prompts/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/arcprime-ip/patent-prompts

Made for: Codex, OpenCode.

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/instructions/arcprime-ip/patent-prompts/agents-md/github.svg)](https://agentmods.dev/instructions/arcprime-ip/patent-prompts/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/arcprime-ip/patent-prompts/agents-md"><img src="https://agentmods.dev/badge/instructions/arcprime-ip/patent-prompts/agents-md/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/instructions/arcprime-ip/patent-prompts/agents-md"><img src="https://agentmods.dev/badge/instructions/arcprime-ip/patent-prompts/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 572 This file is loaded in full into every session.

When invoked 572 The same file — it is already loaded in full.

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	$0.00572	$0.00572
Opus 5.5	$0.00229	$0.00229
Sonnet 5.5	$0.00114	$0.00114
Haiku 4.5	$0.00057	$0.00057

Measured 2mo ago against content hash a016fce3c241, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

patent-prompts AGENTS.md 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 2mo 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.

AGENTS.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Patent Prompts — Agent Instructions

This repository contains professional patent workflow prompts for AI coding agents. These prompts are designed by a patent attorney for real-world patent work including claims drafting, prosecution, prior art analysis, claim charting, continuation strategy, and portfolio management.

Repository Structure

pre-filing/          — Prompts for before filing a patent application
  claims-drafting/     Draft claims from an invention disclosure
  detectability-assessment/  Assess infringement detectability
  disclosure-questions/      Generate clarifying questions for a disclosure
  draft-review/              Review a draft for 101 and 112 issues (3 variants)
  prior-art-analysis/        Analyze claims against prior art

prosecution/         — Prompts for patent prosecution
  patent-summarization/  Summarize a patent from its claims
  concept-extraction/    Extract key technical concepts from claims

portfolio/           — Prompts for portfolio management
  continuation-targeted/   Draft continuation claims targeting a product
  continuation-broadened/  Generate broader continuation claims
  continuation-unclaimed/  Find disclosed but unclaimed subject matter
  claim-chart/             Map claims to product features
  categorization/          Categorize patents by technology area
  pruning-analysis/        Evaluate maintain vs. abandon decisions

examples/            — Sample data and pre-filled example prompts
skills/              — SKILL.md files for Claude Code / agent skill installation

How to Use These Prompts

Each prompt lives in a prompt.md file within its category directory. The prompts use {{PLACEHOLDER}} format for user inputs (e.g., {{PATENT_CLAIMS}}, {{INVENTION_DESCRIPTION}}).

To use a prompt:

Read the relevant prompt.md file
Extract the prompt section between the --- delimiters
Replace all {{PLACEHOLDER}} values with the user's content
Execute the completed prompt

Each prompt.md file contains a Placeholders table documenting what each placeholder expects.

Read the full file on GitHub · 53 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.

2mo ago First seen · 53 lines · 572 tokens per session scan A a016fce3c241

Subscribe to this mod's changes

patent-prompts AGENTS.md is an instructions file published in the GitHub repository arcprime-ip/patent-prompts (26 stars, last pushed 7mo ago), licensed MIT. It adds 572 tokens to every session, about $0.0023 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 2026-08-30.

Legal and compliance Writing and docs

patent-prompts AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
patent-prompts AGENTS.mdarcprime-ip/patent-prompts	Instructions file	26	7mo ago	MIT	A	572	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

patent-prompts: Instructions file for Codex