Skip to content
Marketing
Skill

/brand-mod

Put a brand inside Claude Code — a branded spinner for the terminal and the desktop app (brand colors, the brand's own words, its logo), previewed in HTML for approval before it is generated as an installable mod. Use when the user says "brand our Claude Code", "branded

From plugin
brand-skills
6817 skills

Claude Code

$ npx -y skills add cofoundy/brand-skills --skill brand-mod --agent claude-code

SKILL.md

brand-mod.SKILL.md
name: brand-mod
description: Put a brand inside Claude Code — a branded spinner for the terminal and the desktop app (brand colors, the brand's own words, its logo), previewed in HTML for approval before it is generated as an installable mod. Use when the user says "brand our Claude Code", "branded spinner", "Claude Code mod with our brand", "custom spinner", "make the terminal on-brand", "brand the agent", "spinner with our logo", "show our brand while Claude works", or wants their team's or a client's Claude Code to look like their brand (for screen recordings, demos, or daily use). Claude Code only — mods don't exist in other agents.
metadata:
  version: 1.0.0
disable-model-invocation: true

Brand Mod

<p align="center"><img src="examples/cofoundy/mod/cofoundy-spinner/media/terminal.gif" alt="Branded spinner in the terminal" width="640"></p>

You turn a finished brand into a Claude Code mod: while Claude works, the terminal and the desktop app show the brand's colors, words and logo. You never ship it blind. You **show it in HTML, get approval, then generate**.

Before You Start

**Load the brand package first.** Look for `brand.yaml` (in `./`, `./brand/`, or `brands/<slug>/`); read it, `identity.md` (palette) and `voice.md` (vocabulary) from the same folder. No package yet? Run `brand-init`, then `brand-identity` and `brand-voice`. You need at least a primary color and an SVG logo.

**Confirm the team uses Claude Code** (the terminal, or the Code tab of the desktop app). Mods are Claude Code plugins; they don't run in Cursor, claude.ai chat, or other agents. Ask; don't assume.

Steps

1. **Write `mod.json`** in the brand package (schema in the docstring of `scripts/brand-mod.py`):

  • `primary` from `identity.md` (the script derives an 8-tone scale for the glint), or `stops` if

the brand already has its scale.

  • `logo_svg` (color logo: desktop app, light theme) and `logo_light_svg` (light logo: terminal and

desktop dark theme) from `assets/`.

  • `words` per turn phase and `done` for the end of turn — see **Words** below.
  • `name`, `slug` and the domain come from `brand.yaml`; don't repeat them.

2. **Generate:** `python3 scripts/brand-mod.py <package>/mod.json --media --check` Writes `<package>/mod/<slug>-spinner/`: the installable plugin (also its own marketplace), `preview.html`, a `README.md` with the GIFs first, and `media/`. `--media` needs `agent-browser` and `ffmpeg`; `--check` runs `claude plugin validate` and `claude plugin test`. Both are optional; without `rsvg-convert` the terminal gets no logo. 3. **Show it:** open or share `preview.html` (two windows: Ghostty and the desktop app, light/dark toggle, "inside herdr" toggle). If your host can publish HTML pages (e.g. Claude Artifacts), publish it and hand over the link. 4. **Approval gate:** the owner approves the preview or asks for changes. Changes go into `mod.json` and you regenerate. Never edit `hooks/brand.ts` by hand, and never install or ship before approval. 5. **Ship:** the generated folder goes into a repo. Its README carries the install steps and the `/<slug>-spinner on|off` command. Set `artifacts.mod: true` in `brand.yaml`.

Words

  • Gerunds the team actually says, in their language: 3–6 per phase (`thinking`, `tool-use`,

`tool-input`, `responding`, `requesting`). Pull them from `voice.md` (vocabulary, tone), not from puns on the brand name.

  • Cut anything nobody says. In testing, invented phrases ("herding subagents", "big-braining") and

brand puns ("Cofounded") read as forced the moment people saw them.

  • The end of turn reads «<word> for 12s» (the engine adds "for"): past participles work ("Shipped",

"Cooked").

  • Have someone on the team read the list before shipping.

What the mod does

  • **Terminal:** a 2×2 square of three cubes with a turning gap, then the phase word; one glint in the

brand scale crosses the square and the word. The logo sits at the right edge in Ghostty or kitty run directly (kitty graphics); in herdr, tmux, zellij or screen there is no logo and no stand-in.

  • **Desktop app (Code tab):** the logo with a soft SMIL sweep, color logo on light themes and the

light one when the OS is dark, and the word in one readable color.

  • **End of turn:** the brand's `done` words instead of "Baked".
  • `/<slug>-spinner off` brings back Claude Code's own spinner and is remembered.

Design decisions and the failures behind them: [`method.md`](./method.md). Worked example: [`examples/cofoundy/`](./examples/cofoundy/) (package, `mod.json`, generated mod with its README).

Related skills

  • **brand-identity** — the palette and logo direction this skill reads.
  • **brand-voice** — the vocabulary the spinner words come from.
  • **brand-guidelines** — add the mod's preview to the brand book's applications section.
Read more
@cofoundy
Ships withbrand-skills

**Turn an idea into a real brand — name, identity, voice, and a brand book — without leaving your AI agent.** 16 open-source Agent Skills for founders, indie hackers, and agencies building AI-native — in Claude Code, Cursor, Windsurf, and 70+ agents. -->

Stars on GitHub

Momentum

stars in total
68
Star history of cofoundy/brand-skills on GitHub, a chart by star-history.com

Other skills on brand-skills.

brand-architecture

brand-architecture

Define how multiple brands, sub-brands, and product lines relate to each other under one organization. Use when the user says…

brand-audit

brand-audit

Assess the health and consistency of an existing brand — identity, messaging, voice, positioning, and market perception. Use when…

brand-context

brand-context

Foundation skill that captures and stores core brand context — identity, audience, positioning, values, and voice. Use when the…

brand-guidelines

brand-guidelines

Create a comprehensive brand standards document — covering logo usage, color, typography, voice, messaging, and application…

brand-identity

brand-identity

Create a visual identity brief for a brand — logo direction, color palette, typography, imagery style, and design system…

brand-init

brand-init

Initialize a structured, versioned brand package (and optionally register it in a brand portfolio). Use when the user says "start…

More skills from other plugins.

seo

seo

Comprehensive SEO analysis for any website or business type. Full site audits, single-page analysis, technical SEO (crawlability,…

@agricidaniel@agricidanielInstall Skill
brag

brag

Turn the current project website into a short, polished, shareable launch video using Hyperframes. Use when someone says "/brag",…

brag2w21k
@latent-spaces@latent-spacesInstall Skill
geo-audit

geo-audit

Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit…

Questions about brand-mod.

Which coding agents can use brand-mod?
brand-mod installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.