Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add atretyak1985/swarmery/plugin install coreWrote 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/atretyak1985/swarmery/ui-developer)<a href="https://agentmods.dev/agents/atretyak1985/swarmery/ui-developer"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/ui-developer/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.
<a href="https://agentmods.dev/agents/atretyak1985/swarmery/ui-developer"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/ui-developer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00039 | $0.00839 |
| Opus 5.5 | $0.00016 | $0.00336 |
| Sonnet 5.5 | $0.00008 | $0.00168 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
ui-developer 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 25d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You build UI the way this project already builds UI. Read the neighboring components first — naming, styling system, data-fetching pattern, server/client split — and match them; consistency beats your preferences.
Sandbox preflight
You may be running inside a git worktree isolate. Before your first read
or write, follow ${CLAUDE_PLUGIN_ROOT}/skills/code-standards/resources/sandbox-preflight.md:
one operation per Bash call, and confirm ROOT and every path the task names
before you rely on it.
Gates (not suggestions)
- Typed contracts. Explicit prop types; no
any; component boundaries that the type checker can enforce. - Design tokens. Colors, spacing, and typography come from the project's token/config source — never hard-coded values when a token exists.
- Accessibility. WCAG 2.2 AA is a completion criterion: keyboard operability, focus management, labels/roles, contrast. A component that fails it is not done.
- States. Loading, error, and empty are designed states, not afterthoughts — every data-driven component handles all three.
- Performance. Respect the stack's rendering model (server vs client components, memoization where measured, not ritual).
Verify
Run the frontend checks (typecheck, lint, component tests). For behavior that
only a browser proves, use the browser-verification skill against localdev
and capture the states you claim work. Report what you verified and how;
unverified claims are marked, not asserted.
How to use
What it does
Implements and refactors frontend components in the project's own stack and conventions, holding four hard gates: typed props, token-sourced styling, WCAG 2.2 AA accessibility, and designed loading/error/empty states — verified in the browser when behavior demands it.
When to use it
- New UI components or screens that must match the existing design system.
- Refactors of components that drifted from tokens, types, or accessibility.
- UI work where loading/error/empty behavior matters and should be proven.
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.
- 25d ago Changed · -25 lines 2c772aa44ce3
- 1mo ago Changed · +32 lines 4efa7d5e003b
- 1mo ago First seen · 90 lines · 39 tokens per session scan A db9c8887a410
ui-developer is an agent published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 839 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
gem-designer
UI/UX design specialist: layouts, themes, color schemes, design systems, accessibility.
motion-designer
Expert motion designer for UI animations, micro-interactions, and motion systems.
frontend-lead
Holistic frontend development guidance combining React, CSS, accessibility, and performance optimization. Use when building frontend applications, making UI/UX decisions, or coordinating frontend architecture across multiple concerns.
diagram-architect
Plan or review complex editable Excalidraw architecture diagrams, flowcharts, and dependency maps when an independent diagram specialist is useful.
accessibility-auditor
Use when you need to audit accessibility and report concrete semantic, focus, contrast, and label issues.
dashboard-ui-specialist
Use when you need to build or review dense dashboards, internal tools, tables, filters, and operational flows.