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 damianvtran/local-operator --skill frontend-designgit clone --depth 1 https://github.com/damianvtran/local-operatorWrote 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/damianvtran/local-operator/frontend-design)<a href="https://agentmods.dev/skills/damianvtran/local-operator/frontend-design"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/frontend-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/damianvtran/local-operator/frontend-design"><img src="https://agentmods.dev/badge/skills/damianvtran/local-operator/frontend-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 | $0.00045 | $0.00690 |
| Opus 5.5 | $0.00018 | $0.00276 |
| Sonnet 5.5 | $0.00009 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
frontend-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 5d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend design
A deliberate point of view, then construction, then adversarial self-review. Generic is a decision too, and usually the wrong one.
Pass 1: plan before pixels
Write down, before building:
- The audience and the ONE job of the screen.
- The primary action, and what the screen has to carry (real strings, real data volumes).
- The states: loading, empty, error, populated.
- Type plan: one scale (4 to 6 sizes, 2 to 3 weights). Colour plan: one accent, a neutral base, semantic roles (surface, border, text, danger). Say why each choice fits the audience.
Then attack the plan: describe what the default or template version of this screen would look like (hero, gradient, uniform card grid?). Remove or justify every piece of it that crept in. If the plan would work for any product, it is not a plan.
Pass 2: build and self-critique
- Build the states as designed. The empty state is part of the design, not a fallback.
- Capture frames at narrow, standard, and wide (harness
browsertool where available) and critique them against the plan: hierarchy, alignment, rhythm, legibility. - Fix and recapture until the frames match the plan. Then look once more for what you stopped seeing.
Anti-generic checklist
| Tell | Fix |
|---|---|
| Everything is a card in a uniform grid | Vary weight: some content is prose, some is data; not all containers are equal |
| Default gradient hero, centred everything | Choose one focal element; align to a grid on purpose |
| Three icon-title-blurb columns | Use the real content shape, or one strong statement with supporting detail |
| Filler copy ("empower your workflow") | Say what the control does, in the user's vocabulary |
| One font size everywhere | A scale, used consistently |
| Colour from a palette dump | One accent; colour for meaning, not decoration |
| Decoration that carries no meaning | Delete it; whitespace is a design element |
| Stock imagery that says nothing | Product truth, or nothing |
Quality floor (not negotiable)
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.
- 5d ago First seen · 57 lines · 45 tokens per session scan A b53244b5b0c2
frontend-design is a skill published in the GitHub repository damianvtran/local-operator (218 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 690 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 2026-10-11.
Other skills, from other repositories
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
better-ui
Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, micro-interactions, enter/exit animations, choosing or reviewing icons, or any visual detail work. Triggers on UI polish, design details…
ui-craft
Design, build, redesign, or modify browser-visible web interfaces with product-quality composition, visual systems, interaction states, responsive behavior, accessibility, and browser visual QA. Use for HTML, CSS, JavaScript, React, Vue, or Svelte pages and components, landing pages, dashboards, admin tools, settings…
figma-design-handoff
Figma-to-code design handoff patterns including Figma Variables to design tokens pipeline, component spec extraction, Dev Mode inspection, Auto Layout to CSS Flexbox/Grid mapping, and visual regression with Applitools. Use when converting Figma designs to code, documenting component specs, setting up design-dev…
accessibility
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy, and user preference honoring. Use when implementing screen reader support, keyboard navigation, ARIA patterns, focus traps, accessible component libraries…