find-name

find-name is a command for Claude Code from georgekhananaev/claude-skills-vault. It costs 61 tokens per session (3,907 once invoked), scanned A, original, MIT.

A command for generating and ranking short brand-name ideas, then checking whether their web addresses can be registered. A TLD is the ending of an address, such as .com or .io.

In plain words
What is it for?
Use it when naming a company or product and you need scored candidates with checked domain availability, exported as a CSV.
Why use it?
It filters out names whose required web addresses are already taken, premium, or being resold, so the results focus on available options.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .claude/skills/domain-checker/scripts/check_domains.py \.

Good fit Use it when naming a company or product and you need scored candidates with checked domain availability, exported as a CSV.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/georgekhananaev/claude-skills-vault
agentmods
npx agentmods add commands/georgekhananaev/claude-skills-vault/find-company-name

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 find-name

README.md
[![agentmods](https://agentmods.dev/badge/commands/georgekhananaev/claude-skills-vault/find-company-name/github.svg)](https://agentmods.dev/commands/georgekhananaev/claude-skills-vault/find-company-name)
Your own site
<a href="https://agentmods.dev/commands/georgekhananaev/claude-skills-vault/find-company-name"><img src="https://agentmods.dev/badge/commands/georgekhananaev/claude-skills-vault/find-company-name/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 find-name

Your own site · 80×15
<a href="https://agentmods.dev/commands/georgekhananaev/claude-skills-vault/find-company-name"><img src="https://agentmods.dev/badge/commands/georgekhananaev/claude-skills-vault/find-company-name.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,907 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 $0.00061 $0.03907
Opus 5 $0.00030 $0.01954
Sonnet 5 $0.00012 $0.00781
Haiku 4.5 $0.00006 $0.00391

Measured 12d ago against content hash 474b14a3993e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

find-name 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 12d 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/commands/find-company-name.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Find Name Command

Trigger: /find-name only. Generate, score, availability-check, filter, and rank short brand names.

Announce: "I'm using the find-name command to generate and rank brand-name candidates."

Core promise: every name that appears in the output has its required TLD(s) genuinely available — no taken, no aftermarket, no premium slip-throughs.

0. Skills Used (verify they exist)

Skill Path Purpose
domain-checker .claude/skills/domain-checker/scripts/check_domains.py Bulk availability + aftermarket/premium detection
data-wrangler .claude/skills/data-wrangler/scripts/data_wrangler.py Sort/filter the ranked CSV

If either path is missing, STOP and report which skill needs installing.

1. Discovery (single AskUserQuestion batch — 5 Qs)

Q# Question Header Options
1 What industry / what does the company do? Industry SaaS/tech · Consumer · B2B services · Healthcare · Finance · Other
2 What vibe should the name carry? Vibe Modern/minimal · Bold/distinctive · Playful · Trusted/classic
3 Max characters per name (excluding TLD)? Length ≤6 · ≤7 · ≤8 · ≤10
4 What MUST be available? (strictest filter) Required .com required · .com preferred (.ai/.io OK) · Any of .com/.ai/.io/.app/.dev · Modern only (.ai or .io)
5 Which domains should qualify? Domain mode Only ready-for-registration (recommended) · Include registry-premium (high registrar price) · Include aftermarket/marketplace (GoDaddy sale, Sedo, Dan) · Include both premium and aftermarket

Note user free-text: must-include words, target geos, brands to differentiate from, max budget for premium/aftermarket if relevant.

Important: if the user picked ≤6 AND .com required, warn upfront — the .com namespace is saturated for short pronounceable names. Offer to bump to ≤8 automatically (recommended) or proceed strict.

Q5 semantics — what each option means:

  • Only ready-for-registration: strictest. Domain must be unregistered and priced at the standard registrar rate. No registry-premium tier, no marketplace listings.
  • Include registry-premium: allow domains the registry flags as premium (often $100–$10,000+/yr at the registrar). Still "available" — you just pay more on year one (and sometimes recurring).
  • Include aftermarket/marketplace: allow domains currently registered but listed for sale on GoDaddy Auctions, Sedo, Afternic, Dan, etc. These are one-time purchases at the asking price.
  • Include both: widest net. Use when brand fit matters more than cost and the user has budget.

Read the full file on GitHub · 288 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. 12d ago First seen · 288 lines · 61 tokens per session scan A 474b14a3993e

Subscribe to this mod's changes

find-name is a command published in the GitHub repository georgekhananaev/claude-skills-vault (28 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 3,907 once invoked, about $0.0003 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.