brand

brand is a command for Claude Code from alwkala/tidyfactor-design. It costs 0 tokens per session (1,099 once invoked), scanned A, original, MIT.

A command for creating or updating a structured brand identity file containing details such as logos, colours, fonts, and writing style.

In plain words
What is it for?
Use it to build a brand identity from an interview, extract one from a website or PDF guidelines, or upgrade an older brand file to version 2.
Why use it?
It keeps the visual rules of a new or existing brand in one place instead of relying on scattered guesses or repeated manual decisions.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: installed under .agents/ (shared by several agents).

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 commands/alwkala/tidyfactor-design/brand
Clone the repo
git clone --depth 1 https://github.com/alwkala/tidyfactor-design

Made for: Claude Code.

Wrote 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.

agentmods badge for brand

README.md
[![agentmods](https://agentmods.dev/badge/commands/alwkala/tidyfactor-design/brand.svg)](https://agentmods.dev/commands/alwkala/tidyfactor-design/brand)
Your own site
<a href="https://agentmods.dev/commands/alwkala/tidyfactor-design/brand"><img src="https://agentmods.dev/badge/commands/alwkala/tidyfactor-design/brand.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,099 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 5.1 $0.00000 $0.01099
Opus 5 $0.00000 $0.00549
Sonnet 5 $0.00000 $0.00220
Haiku 4.5 $0.00000 $0.00110

Measured 5d ago against content hash 3c968e850fbb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

brand 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 5d 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.

.agents/skills/tidyfactor-design/references/commands/brand.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Command: brand — Brand Identity Scaffolding & Extraction

Runtime entry point for creating, extracting, or evolving brand.json v2. Part of the Foundation lifecycle phase.

When to use

  • New project → scaffold brand.json from scratch with user interview
  • Existing identity → extract brand.json from a live site, PDF guidelines, or logo + reference photos (the clone-brand path)
  • Schema upgrade → migrate brand.json v1 to v2

Dispatch Steps

  1. Load memory/11-brand-json-v2.md — full schema reference.
  2. Load memory/02-design-tokens.md — token derivation rules.
  3. Determine path: scaffold (no existing identity) or extract (existing site/PDF/assets).
  4. Execute the appropriate protocol below.

Path A: Scaffold (new identity)

Interview (ask these in order)

  1. Product name + taglinemeta.product, meta.tagline
  2. Logo filesidentity.logo.* (SVG preferred; if unavailable, flag as missing — do NOT fabricate)
  3. Primary color + accent → seed colors.light.primary, colors.light.accent
  4. Light or dark default? → determines which mode's background/surface/text values are set first
  5. Voice/tonevoice.tone, voice.personality (3 adjectives)
  6. Foundationfoundation (one of 8 supported options)
  7. Design schoolschool (one of the movements in memory/01-design-schools.md)
  8. Localeslocalization.supportedLocales, localization.rtl

Auto-derived tokens

From the primary color + mode choice, auto-generate:

  • primaryForeground (contrast-safe white or dark)
  • secondary (complementary hue shift)
  • surface, surface2, border (tinted neutrals — NEVER pure black/white)
  • Dark mode mirror tokens (shift lightness, preserve hue)
  • shadows.focusRing using color-mix() from the primary

Path B: Extract (existing identity → brand.json)

What to extract, and from where

Token Primary source Fallback
colors.* Computed styles of existing site's key surfaces (buttons, header bg, body text) — sample actual rendered hex, NOT guesses from screenshots Ask user for 2–3 hex values
typography.families.* <link>/@font-face declarations in HTML/CSS Route through memory/12-typography-matrix.md mood table
voice.* Read 3–5 paragraphs of existing marketing copy; infer register Ask user for 3 adjectives
identity.logo.* Existing logo file (SVG or high-res PNG with transparency) Flag as missing — do NOT fabricate
localization.* <html lang> / dir on existing site Ask which locales needed

Read the full file on GitHub · 86 lines

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. 5d ago First seen · 86 lines · 0 tokens per session scan A 3c968e850fbb

Subscribe to this mod's changes

brand is a command published in the GitHub repository alwkala/tidyfactor-design (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,099 tokens. 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.