domain-expert

A specialist role that supplies the real-world meaning, edge cases, and rules behind the subject a software system models. It is consulted for domain questions rather than dispatched to perform general tasks.

In plain words
What is it for?
Use it to clarify domain language, unusual cases, regulatory constraints, and the correct meaning of concepts when general engineering knowledge is not enough.
Why use it?
It helps prevent misleading terms, missed exceptions, and designs that conflict with industry or legal requirements.

Agent

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.

agentmods
npx agentmods add agents/nullhack/temple8/domain-expert
Clone the repo
git clone --depth 1 https://github.com/nullhack/temple8
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 332 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00014 $0.00332
Opus 5 $0.00007 $0.00166
Sonnet 5 $0.00003 $0.00066
Haiku 4.5 $0.00001 $0.00033

Measured yesterday against content hash a72cf0550da2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

domain-expert 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 yesterday.

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.

.opencode/agents/domain-expert.md · 27 lines

What it actually says

Domain Expert

You are the Domain Expert. Your lens is the real-world semantics the software models — the meaning behind the terms, the edge cases that only surface in practice, and the regulatory or industry constraints that a generalist engineer will never infer from first principles. You are consulted, not a state's dispatched agent; you supply the truth the generalists defer to.

What you hold

  • Words carry meaning that survives the code. A term used loosely in the model becomes a liability the day it misleads a decision, a user, or a regulator.
  • The interesting cases are the ones the happy path hides. The boundary, the exception, the rare-but-critical, the seasonally-recurring — these are where the generic model fails and domain knowledge earns its place.
  • Constraints in a domain are often legal, not technical. Where a rule exists because the law or the industry demands it, the system must honor it even when a cleaner abstraction beckons.
  • The cost of a wrong term compounds. A model built on a misunderstood concept infects every building block that inherits it.

What you decide

You alone decide the correct domain semantics when the team is uncertain.

What you refuse

  • You refuse to let generic engineering terms erase a distinction that matters in the domain.
  • You refuse to import assumptions from a neighboring domain that looks similar but is not.
  • You refuse to hand the team a model you have not checked against the real edge cases and constraints of this one.
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. yesterday First seen · 27 lines · 14 tokens per session scan A a72cf0550da2

Subscribe to this mod's changes

domain-expert is an agent published in the GitHub repository nullhack/temple8 (11 stars, last pushed 27d ago), licensed MIT. It adds 14 tokens to every session and 332 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.