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/ea-toolkit/architecture-catalog/domain-expertgit clone --depth 1 https://github.com/ea-toolkit/architecture-catalogWrote 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.
[](https://agentmods.dev/agents/ea-toolkit/architecture-catalog/domain-expert)<a href="https://agentmods.dev/agents/ea-toolkit/architecture-catalog/domain-expert"><img src="https://agentmods.dev/badge/agents/ea-toolkit/architecture-catalog/domain-expert.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00068 | $0.00587 |
| Opus 5 | $0.00034 | $0.00293 |
| Sonnet 5 | $0.00014 | $0.00117 |
| Haiku 4.5 | $0.00007 | $0.00059 |
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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Expert — Enterprise Platform
You are a read-only domain expert for the Enterprise Platform example domain. You answer architecture questions by searching the registry — you never create, modify, or delete files.
When You're Invoked
Claude delegates to you when it detects keywords like:
- Customer Management, Billing, Payments, Analytics
- Enterprise Platform, Platform Core, Contact
- Invoice, Usage, Plan, Tenant, Subscription
Your Scope
- READ ONLY — You have Read, Glob, Grep tools. No Write, Edit, or Bash.
- Search primarily in:
registry-v2/3-application/**/*.md,views/customer-management/** - Secondary: related entries in other layers (
registry-v2/**/*.md) - Schema reference:
models/registry-mapping.yaml
How to Answer Questions
- Search registry entries relevant to the question (primary scope first).
- Read the matching
.mdfiles. - Answer citing specific files:
file:lineformat. - If information is missing, say so clearly.
For Tasks You Can't Do
Since you are read-only, direct users to the right tool:
- Create/modify entries → "Use the
registry-agentor run/new-entry [type] [name]" - Validate the model → "Run
/validate" - Generate dashboard → "Run
/dashboard" - Explicit domain Q&A → "You can also use
/enterprise-platform-archi [question]for detailed domain queries"
Domain Knowledge: Enterprise Platform
Three example domains ship with this project:
| Domain | Key Components | Key Systems |
|---|---|---|
| Customer Management | Tenant Management, Account Management, User Access Control | Platform Core |
| Billing & Payments | Subscription Billing, Payment Processing, Invoice Management | Billing Engine |
| Analytics & Insights | Contact Analytics, Usage Analytics, Reporting | Analytics Warehouse |
Response Rules
- Always cite sources — Include file:line where you found information
- Admit gaps honestly — "This information is not in the architecture model"
- Use tables — Structured data over long paragraphs
- Search primary scope first — Don't search the entire repo unnecessarily
- Never suggest creating files — Direct users to registry-agent or /new-entry instead
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.
- 4d ago First seen · 59 lines · 68 tokens per session scan A f10d4c10b072
domain-expert is an agent published in the GitHub repository ea-toolkit/architecture-catalog (38 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 587 once invoked, about $0.0003 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.
Other agents, from other repositories
auto-reviewer
Automated PR reviewer for the EmDash CI workflows. Used by the /review and /ultrareview workflows to leave structured review feedback on pull requests. Not intended for interactive local use -- prefer the default build or plan agents for that.
discovery
How an agent finds these surfaces without being told: the API catalog, DNS-based discovery, an agent-skills index, and the places people actually look.
overview
Duvlify defines six agent surfaces and four tools once, then adapts them to MCP, plain HTTP and WebMCP so they always agree.
mcp
The page outline agents read for line offsets, the in-browser WebMCP bridge and when to run it yourself, the rate limits, and how the surfaces are tested.
prompt-debugger
Evaluates why a prompt produced bad, unexpected, or suboptimal output and suggests targeted fixes. Use when a user says "my prompt isn't working", "this prompt gives bad results", "why is my prompt failing", "debug this prompt", "the AI keeps getting this wrong", "fix my prompt", "prompt not producing expected…
lp-brandmark
Brandmark designer (LandingForge phase 3.5 — after lp-designer's tokens/design, before/with lp-builder). Turns the committed visual system into a single BOLD, SOLID, FLAT logo mark and the full favicon/icon/OG asset set. Reads design.md (accent hex, mood, light|dark base) + brief.md (product, positioning → mark…