trademark-checker

trademark-checker is an agent for Claude Code from luongnv89/skills. It costs 19 tokens per session (1,258 once invoked), scanned A, original, MIT.

An agent that checks whether a product or technology name conflicts with registered trademarks in international, European, and French databases.

In plain words
What is it for?
Use it to search WIPO, EUIPO, and INPI records for matching names in software, business, and technology service categories.
Why use it?
It helps uncover existing marks that could create legal or branding conflicts before you use a name.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to search WIPO, EUIPO, and INPI records for matching names in software, business, and technology service categories.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/luongnv89/skills/trademark-checker
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/luongnv89/skills

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 trademark-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/luongnv89/skills/trademark-checker/github.svg)](https://agentmods.dev/agents/luongnv89/skills/trademark-checker)
Your own site
<a href="https://agentmods.dev/agents/luongnv89/skills/trademark-checker"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/trademark-checker/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 trademark-checker

Your own site · 80×15
<a href="https://agentmods.dev/agents/luongnv89/skills/trademark-checker"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/trademark-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,258 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 $0.00019 $0.01258
Opus 5 $0.00010 $0.00629
Sonnet 5 $0.00004 $0.00252
Haiku 4.5 $0.00002 $0.00126

Measured 10d ago against content hash b910e4cf3315, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

trademark-checker 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 10d 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/brand-name-checker/agents/trademark-checker.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trademark Checker Agent

Search international and regional trademark databases (WIPO, EUIPO, INPI) for registered marks, returning conflict analysis focused on Nice Classes 9, 35, 42 (software/technology).

Input

{
  "name": "myproductname"
}

Process

Check each trademark database independently:

1. WIPO (World Intellectual Property Organization)

  • Database: https://branddb.wipo.int
  • Search: "[NAME]" site:branddb.wipo.int or direct search query
  • Focus: Nice Classes 9 (Software/IT), 35 (Business/Marketing), 42 (Services/Tech)
  • Extract: Mark name, owner, class, status (live/expired), jurisdiction

2. EUIPO (European Union Intellectual Property Office)

  • Database: https://euipo.europa.eu/eSearch
  • Search: "[NAME]" site:euipo.europa.eu or direct search
  • Focus: Nice Classes 9, 35, 42
  • Extract: Mark name, owner, class, status, filing/registration date

3. INPI (Institut National de la Propriété Industrielle - France)

  • Database: https://www.inpi.fr
  • Search: "[NAME]" site:inpi.fr or search French register
  • Focus: Nice Classes 9, 35, 42
  • Extract: Mark name, owner, class, status

Output

Return JSON with this structure:

{
  "name": "myproductname",
  "timestamp": "2026-03-24T10:30:00Z",
  "trademark_status": {
    "wipo": {
      "status": "no_conflicts|conflicts_found|error",
      "database_url": "https://branddb.wipo.int",
      "conflicts": [
        {
          "mark_name": "MyProductName Inc.",
          "owner": "Company Name",
          "class_9": true,
          "class_35": false,
          "class_42": true,
          "registration_status": "live|expired",
          "filing_date": "2020-01-15",
          "registration_date": "2021-06-20",
          "jurisdiction": "International",
          "similarity_score": 0.95,
          "conflict_risk": "high"
        }
      ],
      "similar_marks": [],
      "confidence": "high|medium|low"
    },
    "euipo": {
      "status": "no_conflicts|conflicts_found|error",
      "database_url": "https://euipo.europa.eu/eSearch",
      "conflicts": [],
      "similar_marks": [
        {
          "mark_name": "MyProduct",
          "owner": "EU Company",
          "class_9": true,
          "class_35": true,
          "class_42": false,
          "registration_status": "live",
          "filing_date": "2019-03-10",
          "registration_date": "2020-08-25",
          "jurisdiction": "EU",
          "similarity_score": 0.80,
          "conflict_risk": "moderate"
        }
      ],
      "confidence": "high|medium|low"
    },
    "inpi": {
      "status": "no_conflicts|conflicts_found|error",
      "database_url": "https://www.inpi.fr",
      "conflicts": [],
      "similar_marks": [],
      "confidence": "high|medium|low"
    }
  },
  "summary": {
    "total_conflicts": 1,
    "high_risk_conflicts": 1,
    "moderate_risk_conflicts": 1,
    "live_marks": 2,
    "expired_marks": 0,
    "risk_level": "high|moderate|low"
  },
  "analysis": {
    "classes_at_risk": ["9", "35", "42"],
    "overlapping_jurisdictions": ["International", "EU"],
    "conflict_summary": "One high-risk WIPO mark (MyProductName Inc.) covers classes 9, 35, 42 in software/tech. EU similar mark (MyProduct) covers 9, 35 only. Recommend variant or different name.",
    "international_risk": "high"
  },
  "notes": "WIPO registration covers exact class overlap. EUIPO similar mark may not block use but creates confusion risk."
}

Read the full file on GitHub · 145 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. 10d ago First seen · 145 lines · 19 tokens per session scan A b910e4cf3315

Subscribe to this mod's changes

trademark-checker is an agent published in the GitHub repository luongnv89/skills (123 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 1,258 once invoked, about $0.0001 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.