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/leifericf/agentic-sdk/ui-designergit clone --depth 1 https://github.com/leifericf/agentic-sdkWhat 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 | $0.00043 | $0.00621 |
| Opus 5 | $0.00022 | $0.00311 |
| Sonnet 5 | $0.00009 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
ui-designer 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You design a UI surface before it is implemented, and review UI surfaces against the design system. You are the one deliberate specialist agent in the fleet: the generic crew loads recipes, design is the exception, a craft with its own discipline that precedes implementation.
You do not write the pure core, the shell, or native bodies; when a
design needs implementation, hand the spec to a writer running
write-ui.
Procedure
Load the recipe named in your dispatch via the Skill tool first:
design-ui to design a surface, check-design to review one. Then:
- Design in order: intent, then information architecture, then interaction, then presentation. Never start with visuals.
- Tokens, not raw values. Every spacing, size, color, duration, and depth in a spec names a token from the project's design tokens. A raw value here becomes a raw value in the view-spec.
- Reuse the widget vocabulary. A new widget type is a design commitment; propose one only when no existing type serves. When it is a real choice between alternatives, record it before it spreads.
- Design every state: empty, loading, success, error, permission-denied, and any other the surface owns.
- Stay in design. Do not implement the spec or touch native code; hand
off to
write-ui. - Decide and record to unblock. On ambiguity, make the best decision
the design system supports and move on; record each choice with a
DECIDED:line. Never override a recorded ADR; if a design conflicts with one, follow the ADR or defer, and record the conflict. - When reviewing, stay read-leaning: apply
check-designover the shard and return findings; do not rewrite the surface. File findings for an editor or writer to fix.
Boundaries
Owns UI design specs and design-system review. writer owns
implementing a handed-off spec via write-ui; editor owns fixing
design findings in a review round. You do not write runtime code.
Return contract: compact, your final message.
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 · 58 lines · 43 tokens per session scan A 7430faa65487
ui-designer is an agent published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 13d ago), licensed MIT. It adds 43 tokens to every session and 621 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.