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 agentmods add skills/ytvee-dev/webdev-agent-kit/frontend-design-directornpx skills add ytvee-dev/webdev-agent-kit --skill frontend-design-directorgit clone --depth 1 https://github.com/ytvee-dev/webdev-agent-kitWhat 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 | $0.00043 | $0.01951 |
| Opus 5 | $0.00022 | $0.00975 |
| Sonnet 5 | $0.00009 | $0.00390 |
| Haiku 4.5 | $0.00004 | $0.00195 |
Grade A, and why
frontend-design-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 3d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Design Director
Purpose
Define a concrete, subject-grounded frontend design direction before implementation when a task requires visual judgment.
This skill prevents generic AI-generated UI by making deliberate choices about audience, single job, lead thesis, visual position, typography, color, layout, structure, motion, interface copy, and anti-template risks.
It does not implement code by default. It creates a Design Direction Contract that can be handed to frontend-layout-implementer and verified by frontend-visual-qa or frontend-quality-reviewer.
Design Lead Stance
Act as a design lead, not a style randomizer.
- The page needs a point of view that fits this subject and audience.
- Take one real visual risk only when it can be justified.
- Spend boldness in one place and keep the rest disciplined.
- The hero or lead section must express the page thesis.
- Typography, structure, motion, and copy are design material, not filler.
- Structural devices such as numbers, dividers, badges, grids, and labels must encode meaning.
When To Use
Use this skill after prompt intent routing when the task is Standard Workflow or Deep Workflow and includes visual judgment.
Use this skill when the user asks to create, redesign, polish, critique, make distinctive, or define visual acceptance criteria for a rendered frontend surface.
When Not To Use
Do not use this skill for one small bug, one obvious type error, one direct file-scope edit, one isolated code refactor, purely technical debugging, UI library selection, package installation, or testing workflows.
Do not use this skill as a required step for every frontend task. Use it only when design judgment affects the current slice.
Required Context
- Read
AGENTS.md. - Read
common/prompt-intent-routing-rules.mdwhen workflow level is unclear. - Read
common/design-quality-rubric.md,common/anti-template-defaults.md,common/interface-copy-rules.md, andcommon/motion-rules.md. - Read
skills/frontend-design-intelligence/SKILL.mdonly when product category, page pattern, design dials, or domain-specific anti-patterns need grounding. - Read only relevant project overlays:
project/stack-profile.md;project/styling-profile.md;project/design-reference-profile.md;project/visual-memory.mdwhen present;project/active-goals.mdor the compact goal contract when present.
- Read supplied screenshots, design references, copied inspect values, or written brief.
- Read affected route or component files only when existing project constraints are needed.
- Do not read all source files, all skills, or all references for routing.
What ships with it
2 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.
- 3d ago First seen · 195 lines · 43 tokens per session scan A 1995466242a0
frontend-design-director is a skill published in the GitHub repository ytvee-dev/webdev-agent-kit (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,951 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
design-dna
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides…
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
shipping-reproducible-results
Package completed data analysis and ML work so an independent recipient can reproduce the claimed results, verify artifact lineage, and operate the handoff within its stated scope. Use when finalizing a project, study, model package, or review bundle; not for deploying to a live system.
actions-reusable-workflows
Wire a repository to the bitwise-media-group/github-workflows reusable workflows — thin, SHA-pinned caller workflows for CI, security (CodeQL) scanning, release (release-please/GoReleaser/Zensical docs), the signature-preserving fast-forward /merge + merge-review-ack + merge-notice flows, and add-to-project — plus the…
go-style
Modern Go code style for stdlib-first programs — error wrapping with %w, sentinel errors, structured logging with log/slog, context threading, consumer-defined interfaces, nil-safe constructors, net/http servers with method-pattern routing, flag/env configuration for services, and cobra commands with viper…
diagnosing-ml-failures
Isolate the root cause of ML performance drops, inconsistent evaluations, prediction errors, and training-serving mismatches across data, labels, splits, pipelines, models, metrics, and runtime behavior. Use when investigating a reproducible failure or regression, not routine model selection or general performance…