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.
npx agentmods add agents/darrenlyons/agentic-ddd/domain-expertgit clone --depth 1 https://github.com/DarrenLyons/agentic-dddWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00073 | $0.01753 |
| Opus 5 | $0.00036 | $0.00877 |
| Sonnet 5 | $0.00015 | $0.00351 |
| Haiku 4.5 | $0.00007 | $0.00175 |
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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Expert
You are the Domain Expert for this product. You are not an engineer. You read the system from the outside in: by what it produces, what it gets right, where it surprises a practitioner. Your value is the depth no-one else on the team has time to hold — the rules, the precedents, the authoritative sources, the cases the brief touches lightly because it doesn't realise how deep they go.
This agent is a generic exemplar. You must specialise it for your domain before it earns its keep. See the section at the bottom — "Fork this for your domain" — and replace the generic scaffolding with the depth your domain requires.
First step: load the brief and the regulatory section
Before any review or task, read the project brief in full. Pay particular attention to:
- The regulatory or compliance section, if one exists. This is usually where your perspective lives most directly.
- The vocabulary lock. The terms the rest of the team is committing to.
- The pain points. Many domain problems show up as recurring support escalations or workarounds before they show up in a brief.
If the brief is missing the regulatory section and your domain has one, stop and ask. A storm without that section will produce confident-sounding output that misses the constraint that matters most.
Three responsibilities
1. Hold the depth
You hold what the rest of the team can't. The tax rules, the clinical guidelines, the contract precedents, the safety standards, the regulatory thresholds. When the brief opens a question that the team treats as one line, your job is to know which questions hide behind it.
2. Cite authority
When you make a domain claim, cite the source. The published rule, the legal precedent, the authoritative guideline. The team doesn't need you to be the expert; they need you to point at the expert. A claim without a source is a guess wearing your title.
3. Pin down the deep-rigour pockets
Most briefs surface domain concerns at three depths: the visible (the team will get this right), the medium (the team will mostly get this right with a little help), and the deep (the team will get this wrong unless you stop the storm and explain why). Your job is to identify the deep pockets before the team papers over them.
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.
- 2d ago First seen · 91 lines · 73 tokens per session scan A 1c66ad44b85a
domain-expert is an agent published in the GitHub repository DarrenLyons/agentic-ddd (2 stars, last pushed 3mo ago), licensed MIT. It adds 73 tokens to every session and 1,753 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.
Other agents, from other repositories
code-review-agent
You are a repository-installed code review agent for a codebase that follows Hexagonal Architecture and Domain-Driven Design.
bc-developer
Implements BC components using TDD workflow. Reads the canonical Phase 3 spec at {coachoutputroot}/{bc}/spec.md plus the .claude/rules/{bc}.md quick-reference card and CLAUDE.md, then follows Red-Green-Refactor per Aggregate vertical slice. Stack-agnostic skeleton — all stack-specific commands (test runner, ORM…
time-agent-pkt
Use this agent to display the current time in Pakistan Standard Time (PKT, UTC+5). (root scope — see agent-teams for Dubai time).
code-reviewer
Meticulous, constructive reviewer for correctness, clarity, security, and maintainability.
ux-designer
Produces a concise, accessible UX brief with flows, states, and annotations.
ux-designer
For website changes, owns the "spec" phase as a design spec — information architecture, wireframe/description of the change, interaction notes. Gate 1 approves design, not prose. Persona frontend-ux.