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 leifericf/agentic-sdk --skill write-uigit clone --depth 1 https://github.com/leifericf/agentic-sdkWrote 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/leifericf/agentic-sdk/write-ui)<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/write-ui"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/write-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 5.1 | $0.00046 | $0.02686 |
| Opus 5 | $0.00023 | $0.01343 |
| Sonnet 5 | $0.00009 | $0.00537 |
| Haiku 4.5 | $0.00005 | $0.00269 |
Grade A, and why
write-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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
write-ui
Write the UI for the project. The UI core is pure data transformation: it takes the application state and returns a view-spec, lays it out, and resolves hits, all as data. The renderer sits at the edge and consumes the positioned view-spec. Read first:
- the project's view-spec reference (the widget vocabulary, data shapes, event format, layout model, hit-testing). This is the concrete spec; this skill is the recipe for authoring against it.
- the project's design-language reference (the principles, the token system, the component template, the state design every view must cover, and the design-review checklist).
- the project's token catalog (spacing, type, color, depth, motion). The vocabulary the view-spec references; never inline a raw value.
skills/shared/references/architecture.mdfor the Functional Core / Imperative Shell split. The whole UI core lives in its pure core.- design-ui (sibling), the design-first recipe that produces the surface's design spec before this recipe implements it. Implement against the design spec; do not re-decide the design here.
Where UI code lives
The whole UI core is pure functions under the UI module. None do IO, hold an atom, read a clock, call native, or transact. Input arrives as data from the shell; the view-spec leaves as data for the shell to render. If you reach for a side effect in this module, the design is wrong: move the effect to the shell and keep the decision here.
The contract: view-spec is description, not instruction
The view-spec is the UI's intermediate representation. It describes what the UI is right now; it never tells the renderer how to draw. Hold to this:
- Every widget is a plain map with a type and type-specific keys. No functions, no closures, no objects. A view-spec is serializable data: printable, diffable, testable, scriptable.
- Events are data, not callbacks. Handlers are vectors of action
data under an
:onkey. Late-binding values the UI cannot know yet use placeholder keys; the shell substitutes them when the event fires. - Re-derive the whole tree from the root each frame. No component-local state, no subtree subscriptions. All UI logic lives in one entry point; given the same state it returns the same view-spec.
- Persistent structures, deliberately. Build the new view-spec by transforming the old state's data, so unchanged subtrees stay identical objects. The renderer's diff exploits this structural sharing; a rebuild that copies unchanged subtrees defeats 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 · 226 lines · 46 tokens per session scan A 9195b4a1cd2c
write-ui is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 6d ago), licensed MIT. It adds 46 tokens to every session and 2,686 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 2026-09-03.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…