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 ceilf6/FrontAgent --skill frontend-designgit clone --depth 1 https://github.com/ceilf6/FrontAgentWrote 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/ceilf6/frontagent/frontend-design)<a href="https://agentmods.dev/skills/ceilf6/frontagent/frontend-design"><img src="https://agentmods.dev/badge/skills/ceilf6/frontagent/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/ceilf6/frontagent/frontend-design"><img src="https://agentmods.dev/badge/skills/ceilf6/frontagent/frontend-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.00798 |
| Opus 5.5 | $0.00025 | $0.00319 |
| Sonnet 5.5 | $0.00012 | $0.00160 |
| Haiku 4.5 | $0.00006 | $0.00080 |
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 2mo 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Design
Use this skill to produce frontend work that feels intentionally designed rather than generic. The goal is not maximalism by default. The goal is a clear visual point of view that matches the product context and still ships as maintainable code.
Trigger
- New frontend surfaces where look and feel matter:
- landing pages
- dashboards
- product pages
- hero sections
- marketing sites
- polished application views
- Requests to beautify, restyle, refine, or modernize an existing UI
- Cases where the code must be working and production-usable, not just a mockup
Do Not Use
- Pure bug fixes, refactors, or backend tasks
- Review or audit requests
- Small code changes where the user did not ask for visual improvement
- Existing design-system work where the user only wants strict conformance and no meaningful visual interpretation
Workflow
- If the request is visually underspecified, ask only the next 1-3 questions needed to clarify audience, tone, and acceptance criteria. Use
requirement-interviewerwhen the ambiguity is material. - Read
references/design-direction.mdto choose one clear visual direction before coding. - Read
references/aesthetics-guidelines.mdfor typography, color, motion, composition, and background treatment. - Read
references/integration-guardrails.mdbefore modifying an existing codebase, design system, or shared component surface. - For a new page or major redesign, use
assets/templates/visual-brief.mdto form a short visual brief before implementation. - Implement working code that matches the chosen direction and stays within project constraints.
- Read
references/delivery-checks.mdbefore handing off.
Output Contract
- State the chosen visual direction in one short sentence when it meaningfully affects implementation.
- Produce working frontend code, not mood-board prose.
- Keep the implementation cohesive:
- typography should support the direction
- color should feel intentional
- motion should be meaningful, not noisy
- layout should feel composed rather than assembled from defaults
- When editing an existing product, preserve the established system unless the user explicitly wants a stronger redesign.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 82 lines · 62 tokens per session scan A d5d4edf990ab
frontend-design is a skill published in the GitHub repository ceilf6/FrontAgent (120 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 798 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 2026-08-30.
Other skills, from other repositories
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for publishartifact, outputiframe, or slackattachhtml.
surfsense-html
Make or change a web page from the user's sources - a report, a briefing, a dashboard, a comparison, a timeline, an explainer, an interactive calculator or a figure that shows how something works - by writing an HTML file and keeping it with surfsensesavepage. Load it whenever the user asks for a web page, an HTML…
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.
proto-bot-ops
A workflow for turning an existing application into interface prototypes, implementing approved page changes, and collecting review evidence. It checks the real code, pages, components, data, and visual states instead of treating a design file as an integrated product.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
omh-accessibility-audit
This is an OMH accessibility-audit workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).