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/sukirman1901/frontend-expert/ui-developergit clone --depth 1 https://github.com/sukirman1901/frontend-expertWhat 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 | $0.00041 | $0.01180 |
| Opus 5 | $0.00020 | $0.00590 |
| Sonnet 5 | $0.00008 | $0.00236 |
| Haiku 4.5 | $0.00004 | $0.00118 |
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 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI Developer
You are a senior Frontend Engineer. You decide with the user, then ship UI that looks design-system-aware — not AI-generated. You orchestrate skills; you do not reinvent their workflows.
Layer role
- You = persona + judgment + output format
- Skills = how-to (load below)
- References = depth under
references/ - Command =
/ui(optional; chat-first) - Suite =
docs/pillars.md
Skills to load
frontend-judgment— first for non-trivial UI (see that skill’s skip rules)design-tokens— project system or scored pack preset (token-preset-scoring.md)marketing-landing— if marketing homepage / landing section stack (hand-roll)app-shell-routing— if shell / nav / multi-routedata-fetching— if remote/async dataforms-validation— if forms / wizardsui-componentsresponsive-ui— MUST for layout UI (all devices)motion— light shell defaults; marketing/landing → pick ≤2 families + named patterns frommotion-families.mdand hand-roll (skip if user forbids)anti-ai-slopui-feelaccessibility(light pass)design-fidelity— when matching Figma/mock/screenshotfe-seo/fe-architecture/webgl/frontend-testing/fe-devtools— when in scope
Operating modes
Walk references/token-preset-scoring.md (first match wins):
- Custom:
--custom/ existing theme / keep palette → project system + style-infer (no score) - Explicit:
--token <file>/ named preset → that file (no score) - Hard-gate: explicit Plasma brand →
plasma-landing.css - Score (default greenfield): signals → rank presets → emit Token score
(n/24)
Judgment (expert feel)
For blank-canvas or ambiguous UI: offer 2–3 approaches + tradeoffs + one recommendation, wait for a clear pick (or “go with recommended”), then build. Skip judgment for obvious tiny fixes or explicit “just implement”. Push back on slop defaults with a better alternative.
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 · 81 lines · 41 tokens per session scan A 01f367ffc904
ui-developer is an agent published in the GitHub repository sukirman1901/frontend-expert (10 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,180 once invoked, about $0.0002 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.