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 mehrdad03/localdev-mcp --skill frontend-craft-directorgit clone --depth 1 https://github.com/mehrdad03/localdev-mcpWrote 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/mehrdad03/localdev-mcp/frontend-craft-director)<a href="https://agentmods.dev/skills/mehrdad03/localdev-mcp/frontend-craft-director"><img src="https://agentmods.dev/badge/skills/mehrdad03/localdev-mcp/frontend-craft-director/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/mehrdad03/localdev-mcp/frontend-craft-director"><img src="https://agentmods.dev/badge/skills/mehrdad03/localdev-mcp/frontend-craft-director.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 | $0.00047 | $0.06747 |
| Opus 5 | $0.00023 | $0.03374 |
| Sonnet 5 | $0.00009 | $0.01349 |
| Haiku 4.5 | $0.00005 | $0.00675 |
Grade A, and why
frontend-craft-director 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 11d 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 — 1,306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Craft Director — Chat All-in-One
This is the self-contained edition. All required rules and references are included in this single file.
Mandatory usage rule
Before any frontend design, redesign, implementation, audit, responsive fix, UI polish, or visual-QA task:
- Read this entire file.
- Inspect the real project before changing files.
- Preserve the existing architecture, routes, APIs, forms, permissions, analytics hooks, SEO-critical content, and working behavior unless the user explicitly asks to change them.
- Select a concrete design direction before writing UI code.
- Reject generic AI-looking patterns.
- Validate the rendered result at relevant viewports before claiming completion.
- Do not install packages or replace the stack without explicit approval.
Frontend Craft Director
Create interfaces that feel intentionally designed for their product, audience, and content—not assembled from common AI defaults.
This skill governs four modes:
- Build: create a new page or interface.
- Redesign: improve an existing interface without breaking product behavior.
- Audit: inspect an implementation and report prioritized visual/UX defects.
- Study: analyze a reference image, page, or design system and extract reusable principles without cloning it.
Non-negotiable contract
- Inspect before editing.
- Preserve working architecture and product behavior.
- Choose a clear design direction before writing UI code.
- Use real product content and real interface states when available.
- Prefer structural differentiation over decorative novelty.
- Validate the rendered result, not only the source code.
- Never claim visual success without evidence.
- Do not install packages, replace the stack, rewrite routes, or change APIs unless the user explicitly approves it.
- Do not invent metrics, testimonials, customers, notifications, pricing, or product capabilities.
- Do not copy a reference page literally; extract its design logic and adapt it.
What ships with it
5 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.
- 11d ago First seen · 1,306 lines · 47 tokens per session scan A 9311442ad87c
frontend-craft-director is a skill published in the GitHub repository mehrdad03/localdev-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 6,747 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 2026-08-31.
Other skills, from other repositories
frontend-ui-ux
Designer-turned-developer expertise for crafting stunning UI/UX even without design mockups.
component-design
Apply a coherent visual system, responsive behavior, interaction states, and accessibility to Kun components.
uicraft
Create, improve, audit, and polish distinctive production-grade web interfaces, including marketing/landing pages and personal portfolio sites. Use for UI or frontend design, responsive layouts, typography, color, motion, UX copy, accessibility, performance, design-system alignment, onboarding, edge cases, or visual…
ag-referencia-motion
Motion/animação de UI: gate de frequência, 3 curvas canônicas, durações <300ms, springs, interruptibilidade, 13 receitas prontas (RECIPES.md). Carregar ANTES de animar qualquer componente, revisar motion ou escolher lib de animação.
design-system-starter
Create and evolve design systems with design tokens, component architecture, accessibility guidelines, and documentation templates. Ensures consistent, scalable, and accessible UI across products.
visual-qa-verification
Automated visual QA with pixel-level diff comparison, iterative fix loop, and cross-browser verification. Uses pixelmatch for programmatic screenshot comparison with region-based analysis. Covers responsive checks, Lighthouse audits, and accessibility validation. Keywords: verify app, visual QA, compare to Figma…