just-domain

just-domain is a skill for Codex from just-done/just-domain-mcp. It costs 233 tokens per session (3,385 once invoked), scanned A, original, MIT.

A chat-based service for checking whether website addresses, such as example.com or example.io, are available and how much they cost. It can also provide a link for registering an available address in a browser.

In plain words
What is it for?
Use it to check specific domain names, compare prices, suggest names for a project or business, and open a registration link.
Why use it?
It removes the need to leave the conversation to check names and prices, while keeping the actual purchase outside the chat.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to check specific domain names, compare prices, suggest names for a project or business, and open a registration link.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/just-done/just-domain-mcp/just-domain
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.

Any agent
npx skills add just-done/just-domain-mcp --skill just-domain
Clone the repo
git clone --depth 1 https://github.com/just-done/just-domain-mcp

Made for: Codex.

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 just-domain

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/just-done/just-domain-mcp/just-domain"><img src="https://agentmods.dev/badge/skills/just-done/just-domain-mcp/just-domain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 233 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,385 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 $0.00233 $0.03385
Opus 5.5 $0.00093 $0.01354
Sonnet 5.5 $0.00047 $0.00677
Haiku 4.5 $0.00023 $0.00338

Measured 5d ago against content hash 30431eb2d0b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

just-domain 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 5d 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/just-domain/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Just Domain - check domain availability, pricing and transfers, straight from the chat

Just Domain (https://justdomain.ai) lets you check whether a domain name is available and what it costs, and whether a domain somebody already owns elsewhere could move here, without leaving the conversation. You call one of the read-only tools on the Just Domain MCP server:

  • search_domains - availability and pricing for names nobody owns yet.
  • check_domain_transfer - the transfer precheck for one domain the user already holds at another registrar.
  • check_trademark - a name against the US, EU and Israeli trademark registers, answered by Open Trademarks.

All of them look up information only: no order is created, no payment is taken, nothing is filed, and nothing about anybody's domain is changed. When a name is available, search_domains hands back a link the user opens in a browser to register it on justdomain.ai.

When to use this skill

The user says things like:

  • "is acme.com available?" / "check acme.io and acme.ai"
  • "what would acme.com cost?" / "how much is this domain?"
  • "find me a domain for <project/business/idea>" (propose specific names, then check them)
  • "give me a link to register acme.com"
  • "can I move acme.com to Just Domain?" / "why won't my domain transfer?"
  • "what would it cost to transfer acme.ai in?" / "will my site and email keep working if I move my domain?"

When NOT to use it

  • Buying / paying / completing a purchase in the chat. This skill never registers a domain and never takes payment. Registration happens only when the user opens the checkout_url in a browser on justdomain.ai and completes checkout there. Do not tell the user you bought or reserved a name.
  • Actually moving, unlocking, renewing or reconfiguring a domain. check_domain_transfer REPORTS whether a domain could move and what that would cost. It does not move it, and nothing here does. The move itself is self-service for the owner, signed in on justdomain.ai/transfer in a browser, where they paste the authorization code and pay. Unlocking a domain held at Just Domain, and issuing its authorization (EPP) code, ARE self-service - for the owner, signed in on justdomain.ai, in a browser. That is not a capability you have: there is no agent path to either. See "The one refusal" below.
  • Renewals, DNS edits and nameserver changes on a domain the user owns. Not available through this server at all.
  • Auto-expanding TLDs. The tool checks exactly the domains you pass. If the user wants alternatives, YOU propose the names and pass them explicitly.

Read the full file on GitHub · 251 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago Changed · +33 lines · -2 tokens per session 30431eb2d0b3
  2. 1mo ago Changed · +119 lines · +11 tokens per session 1f98bb9b163e
  3. 2mo ago First seen · 99 lines · 224 tokens per session scan A c567cfd629a8

Subscribe to this mod's changes

just-domain is a skill published in the GitHub repository just-done/just-domain-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 233 tokens to every session and 3,385 once invoked, about $0.0009 per session on Opus 5.5. 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.