Brand Mod logo

Brand Mod

Organization
cofoundy
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 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.

Overview

Publishercofoundy
Repositorybrand-skills
Skill namebrand-mod
Stars
61
Forks
12
Bundled files
22
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 22 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by cofoundy on GitHub. Read the source before you install it.

Installation

Install the Brand Mod AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/cofoundy/brand-skills/tree/main/skills/brand-mod
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/cofoundy/brand-skills.git /tmp/brand-skills
mkdir -p .claude/skills
cp -r /tmp/brand-skills/skills/brand-mod .claude/skills/brand-mod
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Brand Mod in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Brand Mod on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Brand Mod is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Brand Mod

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 « 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. Worked example: 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.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Brand Mod AI skill do?

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 exis...

Why use Brand Mod on TypingMind?

Because you install it once and use it with any model. Brand Mod is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Brand Mod in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cofoundy/brand-skills/tree/main/skills/brand-mod. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Brand Mod?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Brand Mod?

As many as you like. As long as a model supports skills, you can use Brand Mod with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Brand Mod AI skill free?

It is published on GitHub by cofoundy. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇