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 lfyxhappy/lfcode --skill ui-implementergit clone --depth 1 https://github.com/lfyxhappy/lfcodeWrote 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/lfyxhappy/lfcode/ui-implementer)<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/ui-implementer"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/ui-implementer/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/lfyxhappy/lfcode/ui-implementer"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/ui-implementer.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 | $0.00060 | $0.00344 |
| Opus 5.5 | $0.00024 | $0.00138 |
| Sonnet 5.5 | $0.00012 | $0.00069 |
| Haiku 4.5 | $0.00006 | $0.00034 |
Grade A, and why
ui-implementer 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 1mo 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.
What it actually says
UI Implementer
Turn a concrete interface requirement into maintainable, tested UI behavior.
Workflow
- Read applicable instructions and inspect the target route, components, state flow, design tokens, assets, existing tests, and current worktree changes.
- Establish the real startup or packaging path and reproduce the current state at relevant viewport sizes before editing.
- Translate the requirement into states and interactions including loading, empty, error, disabled, keyboard, narrow, and long-content cases.
- Reuse existing primitives and styles. Make the smallest scoped implementation and keep data, behavior, and presentation boundaries clear.
- Run focused unit or component checks, then build and exercise the real page when the change is UI-visible. Inspect DOM, screenshots, console errors, page errors, and failed requests.
- Check responsive layout, focus order, semantics, contrast, overflow, and persistence where applicable. Report unverified visual or platform states.
Boundaries
- Do not replace unrelated design systems, add placeholder behavior, or hide errors just to match a screenshot.
- Do not claim a source build updated the installed application; verify the actual served or packaged artifact when required.
- Avoid external assets and network calls unless explicitly requested and authorized.
Completion check
Report changed components, states exercised, build and runtime evidence, screenshots or DOM checks, and remaining browser or platform limitations.
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.
- 1mo ago First seen · 28 lines · 60 tokens per session scan A 28a62f536863
ui-implementer is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 344 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
getvect
Convert a raster image (PNG, JPEG, BMP) into a vector file (SVG, EPS, DXF, PDF) locally, with no network call and no account. Use when you have generated or been given a bitmap and need clean editable paths — a logo to scale, line art to cut, a diagram to embed at any size. Do not use for photographs you want to keep…
design-skill
Use BEFORE building or restyling anything a user will see — web/mobile UIs, landing pages, dashboards, components, emails, AND creative work like Three.js/WebGL/canvas/SVG scenes, data-viz, games, and animations — to make it look intentional and polished, not generic; covers tokens, type, color, layout, motion…
convert-package
Build a complete sales asset end-to-end via The Donahoe Method: diagnostic → primitives → fingerprint → page → integrity-gate → visual → audit → report. Composite orchestrator that calls 14-16 sub-skills via delegatetask in an 8-phase DAG (sequential where dependencies require it, parallel where they don't). Produces…
ux-researcher
Becomes a senior UX researcher who designs user studies, conducts usability evaluations, synthesizes qualitative and quantitative insights, and delivers evidence-based design recommendations. Use when the user needs persona development, usability test plans, user journey maps, interview guides, or research findings…
visual-designer
Becomes a senior visual designer who creates design systems, defines design tokens, builds component specifications, establishes visual hierarchy principles, and ensures accessibility compliance. Use when the user needs design system documentation, component libraries, color and typography specifications, layout…
market-landing
Run a section-by-section CRO teardown on a single landing page. Scores hero, value prop, social proof, features, objections, CTA, and footer; audits forms, mobile, and page speed; outputs prioritized fixes (quick wins / strategic / long-term) and A/B test hypotheses to a client-ready markdown report. Activates on…