domain-expert.codex

domain-expert.codex is a command for Claude Code from wonsukchoi/domain-experts. It costs 18 tokens per session (303 once invoked), scanned A, original, MIT.

A command that matches a task with the most suitable specialist role from a library of domain experts, then uses that role's guidance to reason about the task.

In plain words
What is it for?
Use it when a task needs specialized judgment and you want to route it to a matching accounting, engineering, acting, or other domain role.
Why use it?
It reduces the need to decide manually which expert perspective fits a problem.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it when a task needs specialized judgment and you want to route it to a matching accounting, engineering, acting, or other domain role.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/wonsukchoi/domain-experts/domain-expert.codex
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/wonsukchoi/domain-experts

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 domain-expert.codex

README.md
[![agentmods](https://agentmods.dev/badge/commands/wonsukchoi/domain-experts/domain-expert.codex/github.svg)](https://agentmods.dev/commands/wonsukchoi/domain-experts/domain-expert.codex)
Your own site
<a href="https://agentmods.dev/commands/wonsukchoi/domain-experts/domain-expert.codex"><img src="https://agentmods.dev/badge/commands/wonsukchoi/domain-experts/domain-expert.codex/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-expert.codex

Your own site · 80×15
<a href="https://agentmods.dev/commands/wonsukchoi/domain-experts/domain-expert.codex"><img src="https://agentmods.dev/badge/commands/wonsukchoi/domain-experts/domain-expert.codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 303 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 $0.00018 $0.00303
Opus 5 $0.00009 $0.00151
Sonnet 5 $0.00004 $0.00061
Haiku 4.5 $0.00002 $0.00030

Measured 9d ago against content hash db57f385fa55, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

domain-expert.codex 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 9d 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.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

commands/domain-expert.codex.md · 19 lines

What it actually says

Task: $ARGUMENTS

  1. Run: npx --yes domain-experts match "$ARGUMENTS" --json
  2. If confident: true:
    • Read the matched role's SKILL.md in full (path in best.file), and any references/ files the task needs the depth of.
    • Mention which role you loaded, in one line, before answering.
    • Adopt its reasoning for the rest of this response: follow its Decision framework, apply its Mental models & heuristics, match its Communication style.
    • If metadata.maturity is draft, use it fully but don't claim practitioner review if asked.
  3. If confident: false:
    • State plainly that no role covers this yet. Name the closest low-confidence candidates if any were returned.
    • Point at ROADMAP.md in the domain-experts repo for the nearest O*NET occupation, and mention a PR per CONTRIBUTING.md would add it.
    • Then answer the task as a generalist if that's clearly still wanted — flagged explicitly as improvised, not sourced from a vetted role.
  4. Never blend step 2 and step 3 framing — a loaded role's answer and an improvised one must read as visibly different confidence levels.
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. 9d ago First seen · 19 lines · 18 tokens per session scan A db57f385fa55

Subscribe to this mod's changes

domain-expert.codex is a command published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 303 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.