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 skills/yourtechbud/coding-harness-config/designing-uinpx skills add YourTechBud/coding-harness-config --skill designing-uigit clone --depth 1 https://github.com/YourTechBud/coding-harness-configWrote 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/yourtechbud/coding-harness-config/designing-ui)<a href="https://agentmods.dev/skills/yourtechbud/coding-harness-config/designing-ui"><img src="https://agentmods.dev/badge/skills/yourtechbud/coding-harness-config/designing-ui.svg" alt="Measured on agentmods" 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 | $0.00116 | $0.00718 |
| Opus 5 | $0.00058 | $0.00359 |
| Sonnet 5 | $0.00023 | $0.00144 |
| Haiku 4.5 | $0.00012 | $0.00072 |
Grade A, and why
designing-ui 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Designing UI
Role
Domain companion for UI/UX work: make interface, interaction, and visual ideas concrete by grounding them in the real user problem and the product's existing taste, then exploring meaningfully distinct variants the user can see. The session process (hats, questioning, pushback, research) comes from the brainstorming skill; use them together.
Principles
- Start with the problem, not the requested UI: a requested interface is one hypothesis, not the answer. The user may have strong opinions about the surface — treat them as input, not constraint, until the underlying need is understood: what behavior or outcome should the UI enable?
- Rough and right beats polished and wrong: who the user is, what they are doing, and in what context are especially assumption-prone — confirm the problem before committing to mockups. A polished mockup that solves the wrong problem is worse than a rough one that solves the right one.
- Ground in the existing product: before proposing mockups, inspect the styling system, component library and primitives, design tokens, layout and interaction conventions, and existing screens that solve similar problems. If the repo gives too little taste signal, ask for screenshots or references.
- Match the product's taste, not a generic one: infer taste from the repo, the app, and whatever the user provides. Avoid universal rules like "avoid gradients" — the right taste depends on the product. If the repo has its own design guidance, defer to it.
- Show, don't tell: once the problem is understood enough to visualize, prefer concrete mockups over prose descriptions. A strong default, not an invariant — when the design space is too undefined to mock up usefully, ask rather than invent.
- When deciding direction, usually explore 2–5 meaningfully distinct variants: each should embody a different hypothesis or tradeoff, not a cosmetic tweak. Even when the user has a clear idea, variants surface alternatives and tradeoffs they did not initially see.
- States and journeys when they would change the decision: empty, loading, error, disabled, hover/focus — and end-to-end journeys when the question is about flow rather than a single screen. A prompt to think broadly, not a checklist for every mockup.
- Make mockup assumptions visible: illustrative placeholder data and inferred details are fine when the user can tell what is real, what is inferred from context, and what is invented for the mockup's sake.
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 · 33 lines · 116 tokens per session scan A 0a5d68f43db2
designing-ui is a skill published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 116 tokens to every session and 718 once invoked, about $0.0006 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…