patent-check

patent-check is a command for Claude Code from illusionaireal/oh-my-patent. It costs 0 tokens per session (797 once invoked), scanned A, original, MIT.

A readiness check for a patent project, covering the active coding-agent adapter, search services, external tools, runtime, workspace, and saved project states.

In plain words
What is it for?
Use `/patent-check` for the current workspace or another project path to check services such as Google Scholar and patent databases, tools such as Mermaid and Git, Node.js, write access, and existing project state files.
Why use it?
It shows which setup items are missing before research begins without changing configuration or installing anything.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions Codex; mentions OpenCode.

Good fit Use /patent-check for the current workspace or another project path to check services such as Google Scholar and patent databases, tools such as Mermaid and Git, Node.js, write access, and existing project state files.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/illusionaireal/oh-my-patent/patent-check
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/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.

agentmods badge for patent-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/illusionaireal/oh-my-patent/patent-check/github.svg)](https://agentmods.dev/commands/illusionaireal/oh-my-patent/patent-check)
Your own site
<a href="https://agentmods.dev/commands/illusionaireal/oh-my-patent/patent-check"><img src="https://agentmods.dev/badge/commands/illusionaireal/oh-my-patent/patent-check/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 patent-check

Your own site · 80×15
<a href="https://agentmods.dev/commands/illusionaireal/oh-my-patent/patent-check"><img src="https://agentmods.dev/badge/commands/illusionaireal/oh-my-patent/patent-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 797 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 $0.00000 $0.00797
Opus 5.5 $0.00000 $0.00319
Sonnet 5.5 $0.00000 $0.00159
Haiku 4.5 $0.00000 $0.00080

Measured 15d ago against content hash 2155d0b82e2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

patent-check 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 15d 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.

src/commands/patent-check.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/patent-check

Check environment readiness in the active host before first RESEARCH or project resume.

Usage

/patent-check [project-path]

From the installed workspace root, run the bundled checker:

node "{{PATENT_CHECK_SCRIPT}}" --json

From another directory, resolve that installed script and pass its full path. The script uses its own location to select the workspace and the active host's configuration. It needs Node.js 22+ but no source checkout, global CLI, node_modules or npx cache.

The public CLI also supports oh-my-patent check --json --tool <host>. <host> is claude-code, codex or opencode; specify it in mixed-host workspaces.

Results and handoff

Return the actual timestamp, adapter, ready, blocking/warning counts, MCP configuration statuses and runtime/tool/project results. The check reads local configuration and probes local tools; it does not contact or authenticate MCP services. Observe actual host tools separately. A configured service has not passed a connectivity check.

Archimedes saves the real report and host capability observations in the selected project's references/init-report.json. Do not change formal workflow state here. Missing git or runtime capabilities block plugin readiness. Missing mmdc is an optional figure warning; only an elected Mermaid path requires its renderer. Report retrievalCoverage, configuredCount and degradedRetrieval: zero configured sources (none) blocks RESEARCH; academic sources only (google_scholar/semantic_scholar, fallback_only) blocks by default; at least one patent source (patsnap_search/uspto_patent/cnipa_patent, professional) passes the configuration gate. Missing individual sources remain warnings. Template priority is setup advice; retrievalRole determines coverage. No source must be individually required.

Only after explicit user acceptance of academic-only limitations, rerun the same checker with --accept-degraded-retrieval --degradation-reason "user acceptance reference/reason". Save the resulting confirmation, timestamp and limitation in the report. Consent applies to this invocation; recheck on resume. It cannot waive zero sources or runtime/tool blockers. Observe actual approved host retrieval tools too: none/unknown blocks formal RESEARCH, and academic-only tools require explicit acceptance even if a patent source is configured. Failed execution and unknown capabilities must never be recorded as passed. A search plan or supplied-material analysis cannot be described as completed retrieval.

Read the full file on GitHub · 71 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. 15d ago Changed · +22 lines 2155d0b82e2e
  2. 1mo ago First seen · 49 lines · 0 tokens per session scan A fbd122bc1b60

Subscribe to this mod's changes

patent-check is a command published in the GitHub repository illusionaireal/oh-my-patent (110 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 797 tokens. 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.