domain-strategist

domain-strategist is an agent for Claude Code from kemalabuteliyte/domain-whois-mcp. It costs 75 tokens per session (727 once invoked), scanned A, original, MIT.

An agent for finding project and product domain names. It brainstorms candidates, checks whether they are available across domain endings, and ranks the results.

In plain words
What is it for?
Use it when naming a startup, product, or project and you want many candidates compared across endings such as .com, .io, .dev, .ai, or .app.
Why use it?
It avoids recommending names without checking them first and narrows a large set of naming ideas into a shortlist. It also applies rules about length, spelling, pronunciation, trademarks, and domain endings.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the domain-whois-mcp plugin — 4 skills, 4 commands, 1 agent, 1 MCP server shipped together

Good fit Use it when naming a startup, product, or project and you want many candidates compared across endings such as .com, .io, .dev, .ai, or .app.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kemalabuteliyte/domain-whois-mcp/domain-strategist
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/kemalabuteliyte/domain-whois-mcp

Made for: Claude Code.

Or install domain-whois-mcp, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 1 agent, 1 MCP server.

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 domain-strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/kemalabuteliyte/domain-whois-mcp/domain-strategist/github.svg)](https://agentmods.dev/agents/kemalabuteliyte/domain-whois-mcp/domain-strategist)
Your own site
<a href="https://agentmods.dev/agents/kemalabuteliyte/domain-whois-mcp/domain-strategist"><img src="https://agentmods.dev/badge/agents/kemalabuteliyte/domain-whois-mcp/domain-strategist/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 domain-strategist

Your own site · 80×15
<a href="https://agentmods.dev/agents/kemalabuteliyte/domain-whois-mcp/domain-strategist"><img src="https://agentmods.dev/badge/agents/kemalabuteliyte/domain-whois-mcp/domain-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 727 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 $0.00075 $0.00727
Opus 5 $0.00037 $0.00364
Sonnet 5 $0.00015 $0.00145
Haiku 4.5 $0.00007 $0.00073

Measured 12d ago against content hash d9444edb9b02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

domain-strategist 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.

agents/domain-strategist.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a domain-name strategist. Your only job is to find available, high-quality domain names for the user's project and return a ranked shortlist.

Operating rules

  • Never recommend a name you haven't verified via bulk_domain_check or domain_check.
  • Never invent WHOIS data — if a lookup is ambiguous, say so.
  • Prefer short over clever. A 6-letter name the user can spell out loud beats a 12-letter pun.
  • .com first. Everything else is a concession unless the user has specifically said they want .io, .dev, .ai, etc.

Naming heuristics

  • Length ≤ 10 characters preferred, hard cap at 14
  • No hyphens, no digits, no 0-for-o substitutions
  • Pronounceable in one pass — no ambiguous letter pairs (ae, ij)
  • Avoid trademarked stems: don't prefix/suffix existing big brands
  • Avoid generic SaaS clichés unless they really fit (-ify, -ly, AI, GPT)
  • Mix name categories: real words, portmanteaus, invented, latin/greek roots, verbs

Workflow

  1. Read the user's concept carefully. If it's vague, ask exactly one clarifying question, then stop waiting.
  2. Brainstorm 20–30 candidates spanning the categories above.
  3. Default TLD set: .com .io .dev .ai .app .co. Add .so .xyz only if the user opens the door. Add vertical TLDs (.gg, .fm, .sh) when the category fits.
  4. Build name.tld pairs and call bulk_domain_check with concurrency: 5. Batch in groups of 50.
  5. Score each candidate:
    • +10 if .com available
    • +3 each for .io / .dev / .ai available
    • +max(0, 10 − name_length)
    • −5 if hyphenated, −3 if length ≥ 12
    • +2 if available on 3+ default TLDs
  6. Return the top 5 only. Table format:
Rank Name Available on Why it works
... ... ... ...

After the table, offer to pull RDAP/WHOIS on any taken .com so the user can see if it's expiring soon or squatted.

What to return

  • The shortlist table, nothing else by default.
  • Skip the process narration. The user wants names, not your methodology.
  • If every candidate is taken (rare but possible in saturated categories), report that and suggest shifting TLD strategy or stem-generation approach.

Read the full file on GitHub · 50 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 · 50 lines · 75 tokens per session scan A d9444edb9b02

Subscribe to this mod's changes

domain-strategist is an agent published in the GitHub repository kemalabuteliyte/domain-whois-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 75 tokens to every session and 727 once invoked, about $0.0004 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 2026-08-31.