applying-visual-identity

A guide for applying a company’s visual identity—the rules for its colors, fonts, spacing, shapes, and other design choices—to digital work. It reads or creates a DESIGN.md file that records those rules.

In plain words
What is it for?
It helps make HTML, presentations, and documents follow defined brand tokens, and can set up a shared identity guide when one is missing.
Why use it?
It prevents each page or document from inventing its own brand style and keeps designs consistent across projects.

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/luccapinto/agentic-data-kit/applying-visual-identity
Any agent
npx skills add luccapinto/agentic-data-kit --skill applying-visual-identity
Clone the repo
git clone --depth 1 https://github.com/luccapinto/agentic-data-kit

Made for: Claude Code, Codex.

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 699 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 $0.00103 $0.00699
Opus 5 $0.00051 $0.00349
Sonnet 5 $0.00021 $0.00140
Haiku 4.5 $0.00010 $0.00070

Measured 3d ago against content hash 471a8fcf7389, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

applying-visual-identity 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.

.agent/skills/applying-visual-identity/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: applying-visual-identity

A company's visual identity lives in a DESIGN.md at the project root — the open spec from Google Labs (Apache-2.0, 2026). It pairs machine-readable design tokens (YAML frontmatter) with human-readable rationale (prose), so any AI tool renders the brand the same way across sessions. This skill reads that file and applies it; if none exists, it scaffolds one.

Workflow

  1. Locate. Look for DESIGN.md in the project root. If found, parse the frontmatter tokens — they are the normative values; the prose is guidance.
  2. Apply. Map tokens to the target medium:
    • HTML/reveal.js/Marp → CSS custom properties on :root (--brand-primary, --font-heading, …).
    • Markdown/docs → headings, callouts, accent usage per the Do's/Don'ts.
    • Resolve token references like {colors.primary} before output.
  3. Stay in-spec. Use only defined tokens; don't introduce off-palette colors or fonts. If a needed token is missing, ask or pick the closest defined one and note it.
  4. Scaffold when absent. If there's no DESIGN.md, offer to create one from templates/DESIGN.md — ask for (or extract from a provided logo/site) the primary color, font, and tone. Never silently invent a brand; fall back to a neutral theme until confirmed.

The DESIGN.md format (Google Labs spec)

YAML frontmatter holds the tokens; the body documents intent in fixed sections.

Frontmatter token groups: colors, typography (objects: fontFamily, fontSize, fontWeight, lineHeight, letterSpacing), spacing, rounded, shadows, components (per-component token refs). Colors accept hex / rgb / hsl / oklch(). Dimensions carry units (px, rem). References use braces: {colors.primary}, {typography.h1}.

Body sections (in order): Overview · Colors · Typography · Layout & Spacing · Elevation & Depth · Shapes · Components · Do's and Don'ts.

See templates/DESIGN.md for a complete, fillable example.

Read the full file on GitHub · 44 lines

Files

What ships with it

1 file 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.

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. 3d ago First seen · 44 lines · 0 tokens per session scan A 471a8fcf7389

Subscribe to this mod's changes

applying-visual-identity is a skill published in the GitHub repository luccapinto/agentic-data-kit (7 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 699 once invoked, about $0.0005 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.