What is oh-my-patent CLAUDE.md?

A repository guide for oh-my-patent, a command-line tool that coordinates specialised AI agents to turn a technical idea into a patent disclosure document. It explains the project, commands, tests, build process, and editor integrations.

Use it when developing oh-my-patent, running its test suites, building the TypeScript command-line tool, or working with its Claude Code and Codex adapter files.

It gives contributors the commands and background needed to build, test, lint, and run the project correctly.

How illusionaireal/oh-my-patent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to illusionaireal/oh-my-patent. 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/illusionaireal/oh-my-patent/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/illusionaireal/oh-my-patent

Made for: Claude Code.

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/illusionaireal/oh-my-patent/claude-md/github.svg)](https://agentmods.dev/instructions/illusionaireal/oh-my-patent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/illusionaireal/oh-my-patent/claude-md"><img src="https://agentmods.dev/badge/instructions/illusionaireal/oh-my-patent/claude-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/illusionaireal/oh-my-patent/claude-md"><img src="https://agentmods.dev/badge/instructions/illusionaireal/oh-my-patent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,135 This file is loaded in full into every session.

When invoked 2,135 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	$0.02135	$0.02135
Opus 5	$0.01068	$0.01068
Sonnet 5	$0.00427	$0.00427
Haiku 4.5	$0.00214	$0.00214

Measured 7d ago against content hash ed3b460da1a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

oh-my-patent CLAUDE.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 7d 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.

CLAUDE.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

oh-my-patent is a CLI tool that orchestrates 11 specialized AI agents (defined as markdown prompts in src/agents/) to turn a technical idea into a complete patent disclosure document. The CLI itself does not run the agents — it manages the state, decision path, diagrams, and adapter configs that the agents (running in the user's editor) read and write.

The agent prompts live in src/agents/*.md and are consumed by editors via adapters (.claude/ for Claude Code, .codex/ for Codex). The TypeScript code is the runtime bridge those agents call.

Commands

npm run build        # tsc → dist/  (required before running the CLI from source)
npm test             # vitest run — full suite
npm test:watch       # vitest in watch mode
npm test tests/unit/        # unit tests only
npm test tests/integration/cli-commands.test.ts   # single test file
npm run lint         # tsc --noEmit (the project uses strict mode, zero errors expected)

node dist/cli.js     # run the CLI from a source build (the published bin is `oh-my-patent`)
npx -p . oh-my-patent  # alternative way to run from local build

The CLI has four domains — path, diagram, adapt, tui — each with subcommands. See node dist/cli.js --help for the full reference.

Quick Start for Local Development

git clone https://github.com/illusionaireal/oh-my-patent
cd oh-my-patent
npm install
npm run build
node dist/cli.js adapt setup --workspace-dir /path/to/test/project

Architecture

Two-layer model: definitions vs. engine

Orchestration layer (plugin.jsonc, opencode.jsonc, src/agents/*.md, src/skills/*/SKILL.md, src/commands/*.md): tool-agnostic definitions of agents, skills, and commands. Pure data and prompt text.
Engine layer (src/core/, src/cli.ts, src/commands/*.ts): the TypeScript runtime that operates on .brainstorm/, .patent/, figures/, and references/ directories inside a user's patent project.

Read the full file on GitHub · 128 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.

7d ago Changed ed3b460da1a9
11d ago First seen · 128 lines · 2,135 tokens per session scan A b2b4fa381c04

Subscribe to this mod's changes

oh-my-patent CLAUDE.md is an instructions file published in the GitHub repository illusionaireal/oh-my-patent (94 stars, last pushed 10d ago), licensed MIT. It adds 2,135 tokens to every session, about $0.0107 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.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

oh-my-patent: Instructions file for Claude Code