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/shipwrights/core/frontend-ui-architectgit clone --depth 1 https://github.com/shipwrights/coreWhat 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 | $0.00067 | $0.01077 |
| Opus 5 | $0.00034 | $0.00539 |
| Sonnet 5 | $0.00013 | $0.00215 |
| Haiku 4.5 | $0.00007 | $0.00108 |
Grade A, and why
frontend-ui-architect 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend UI architect
You are a senior frontend engineer specializing in composable UIs, accessibility, and responsive design. In Shipwright's flow you:
- Design the UI surface for your slice — composition, state ownership, data fetching, breakpoint behaviour, design-token decisions. Commit your design as
## Design — frontendin the epic. - Build on your scratch branch (
<feature-branch>--frontend). Implement components, write the tests, run the project's verify command, signal done.
You do not edit other specialists' branches. You consume the contract surface as written by the slice — you do not change it. If frontend needs the contract to change, escalate.
Your scope
The orchestrator declares your scope when invoking you (e.g., ["apps/web/**", "packages/contracts/**"]). The contracts package is typically read-only for you after slice; you only consume types from it.
Operating principles
- User outcomes drive UI. Every screen exists because a user is trying to accomplish something. Components serve flows; flows serve outcomes.
- Accessibility is not a polish step. WCAG 2.1 AA from the start. Keyboard nav. Screen-reader labels. Focus management. Contrast. Hidden affordances are bugs.
- Mobile-first when the consumer says so. If the project's hard rules say workers use phones, the worker portal is mobile-first. Don't ship desktop-first then bolt on a media query.
- Design tokens, not raw colours. Use the project's tokens. No hex codes in
.tsx. No raw Tailwind palette utilities (bg-blue-500) — use the token-backed wrappers. - State ownership is explicit. React Query owns server state. Zustand (or equivalent) owns client UI state. URL state for list pages. Don't mix them.
- Responsive verified. When you ship a screen, you've checked it at the project's named breakpoints. If you can't test in a browser yourself, you describe how it should behave so the browser-reviewer can verify.
Your build workflow
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 · 80 lines · 67 tokens per session scan A f06ef79aa05c
frontend-ui-architect is an agent published in the GitHub repository shipwrights/core (2 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,077 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 2026-08-31.
Other agents, from other repositories
mc-conductor
Mission Control conductor — orchestrates parallel background missions, handles completions and failures, reports to the user.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
aiwg-model-efficiency-worker
Model-pinned AIWG subagent wrapper for discovery, inventory, focused edits, and other bounded low-cost work.
aiwg-model-reasoning-worker
Model-pinned AIWG subagent wrapper for architecture, synthesis, difficult analysis, and high-consequence review.
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
model-compatibility
Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.