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 skills add wsauret/flywheel --skill interface-designgit clone --depth 1 https://github.com/wsauret/flywheelWrote 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/skills/wsauret/flywheel/interface-design)<a href="https://agentmods.dev/skills/wsauret/flywheel/interface-design"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/interface-design/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/skills/wsauret/flywheel/interface-design"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/interface-design.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 | $0.00023 | $0.00720 |
| Opus 5.5 | $0.00009 | $0.00288 |
| Sonnet 5.5 | $0.00005 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
interface-design 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interface Design
Plan and review user-facing surfaces that read as part of their host and spend the user's attention deliberately. This method applies when writing an interface plan, reviewing an interface plan, or reviewing implemented interface code. It does not implement frontend code. Correctness, accessibility, and the host platform's conventions are hard gates.
Input
Start with the requested surface change, the host it renders in, and the host's existing visual system: shared tokens, type scale, spacing rhythm, theme structure, and interaction conventions. Extend that system rather than introducing a parallel one, and report any deliberate deviation.
Principles
- Establish hierarchy before decoration. A reader must find the primary action and the primary information without scanning twice. Type scale, weight, and spacing carry hierarchy; color and ornament come last.
- Spend emphasis (color, motion, size, weight) only where the user's attention must go, and spend it in one place rather than everywhere.
- Keep one source of truth for shared visual values. Repeated or theme-dependent sizes, colors, radii, and durations live as tokens the components read. Keep a genuinely component-local decision local when it does not duplicate an existing token.
- Design every theme the host offers as a set. A color defined for one theme and inherited in another is a defect, not a default. Verify contrast on every theme's ground.
- Fit the host surface. An embedded panel reads as part of its editor, terminal, or window: its spacing rhythm, focus treatment, and typography. A surface that looks pasted in from another product is a defect even when it is attractive.
- Give every interactive element its states: hover, focus-visible, active, disabled, and busy. Design empty, loading, and error as first-class states, not as absences.
- Let layout own spacing. Sibling gaps come from the container, not from per-element margins that collapse or double. Wide content scrolls inside its own region; the page never scrolls sideways.
- Restrain motion. Animation explains a state change or directs attention; it never runs for its own sake, and reduced-motion preferences are respected.
- Treat copy as design material. Controls say exactly what happens, labels name what users recognize, and errors say what went wrong and what fixes it.
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 · 36 lines · 23 tokens per session scan A 7128ca69ece8
interface-design is a skill published in the GitHub repository wsauret/flywheel (19 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 720 once invoked, about $0.0001 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 2026-11-03.
interface-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| interface-designwsauret/flywheel | Skill | 19 | today | Apache-2.0 | A | 23 | Claude Code, Codex |
| frontend-designHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 21 | Claude Code, Codex |
| design-skillOverbrilliant/ob-1 | Skill | 29 | 12d ago | Apache-2.0 | A | 82 | Claude Code, Codex |
| ui-reviewerAbyssCN/oh-my-dag | Skill | 44 | 27d ago | MIT | A | 24 | Claude Code, Codex |
| accessibility-auditorlfyxhappy/lfcode | Skill | 2 | 1mo ago | MIT | A | 57 | Claude Code, Codex |
| visual-acceptancehuiliyi37/Tianshu-harness | Skill | 1.3k | 2d ago | Apache-2.0 | A | 89 | Claude Code, Codex |
| ui-featuresmarcus/sidecar | Skill | 1.1k | 1mo ago | MIT | A | 61 | Claude Code |