design-direction

A visual planning guide for choosing a deliberate style, color palette, typefaces, references, and motion before building a website or page.

In plain words
What is it for?
Writing a short design brief for a new site or page, including its visual direction, colors, fonts, reference products, and animation approach.
Why use it?
It helps prevent interfaces from looking like generic templates and gives the implementation a clear visual target.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/m-binimran/dev-pack/design-direction
Any agent
npx skills add m-binimran/dev-pack --skill design-direction
Clone the repo
git clone --depth 1 https://github.com/m-binimran/dev-pack

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 384 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00047 $0.00384
Opus 5 $0.00023 $0.00192
Sonnet 5 $0.00009 $0.00077
Haiku 4.5 $0.00005 $0.00038

Measured 2d ago against content hash 44ff71f93581, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-direction 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 2d 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.

skills/design-direction/SKILL.md · 28 lines

What it actually says

design-direction

The fastest way to ship template-looking UI is to start coding without a direction. Don't.

Do this first

  1. Pick a named direction — editorial/magazine, neo-brutalism, glass-with-real-depth, dark or light luxury, bento, scrollytelling, Swiss/International, retro-futurism. NOT "clean minimal." NOT auto dark mode.
  2. Palette intentionally: a base, 1–2 surfaces, a semantic accent (success/warn/danger), and ONE brand-defining color used with purpose. Define as Tailwind v4 @theme tokens (hand to theme-tokens).
  3. Type pairing: a display/heading face with character + a readable body face. State the pairing and why.
  4. Reference set: name 2–3 real sites/products this should feel like.
  5. Motion intent: how motion clarifies this product (subtle micro vs. cinematic scroll). Hand to animation-implement.

Output

  • A short "direction brief": style name, palette tokens, type pairing, references, motion intent.
  • This brief is the contract the rest of the build is judged against.

Guardrails (anti-template)

  • Every surface must show ≥4 of: scale hierarchy, spacing rhythm, depth/layering, real type, semantic color, designed interaction states, grid-breaking composition, texture, purposeful motion, designed data viz.
  • Final gut check: "would this look believable in a real product screenshot?" If no, iterate before building more.
Changes

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.

  1. 2d ago First seen · 28 lines · 47 tokens per session scan A 44ff71f93581

Subscribe to this mod's changes

design-direction is a skill published in the GitHub repository m-binimran/dev-pack (2 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 384 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.

Related

Other skills, from other repositories

image-gen

Image generation via Letta tool — artifacts saved locally; publish/external use is a red zone.

otto-haus/otto · 23 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

baoyu-youtube-transcript

Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…

JimLiu/baoyu-skills · 107 tokens