brand-assets

brand-assets is a skill for Claude Code from roslove44/brand-artisan. It costs 110 tokens per session (1,177 once invoked), scanned A, original, MIT.

A skill for creating or updating a project's logos, favicons, and related brand files while following its written design rules.

In plain words
What is it for?
Use it to regenerate brand assets, add variants such as OAuth icons, or set up the tools for a new project's brand files.
Why use it?
It avoids guessing at an existing logo's shape, colors, or proportions when making a replacement or variant.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **Env and commands: see [`tools/README.md`](../../tools/README.md).**.

Part of the brand-artisan plugin — 15 skills shipped together

Good fit Use it to regenerate brand assets, add variants such as OAuth icons, or set up the tools for a new project's brand files.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/roslove44/brand-artisan
agentmods
npx agentmods add skills/roslove44/brand-artisan/brand-assets

Made for: Claude Code.

Or install brand-artisan, the plugin that ships this one along with the rest of its 15 skills.

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-assets

README.md
[![agentmods](https://agentmods.dev/badge/skills/roslove44/brand-artisan/brand-assets/github.svg)](https://agentmods.dev/skills/roslove44/brand-artisan/brand-assets)
Your own site
<a href="https://agentmods.dev/skills/roslove44/brand-artisan/brand-assets"><img src="https://agentmods.dev/badge/skills/roslove44/brand-artisan/brand-assets/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for brand-assets

Your own site · 80×15
<a href="https://agentmods.dev/skills/roslove44/brand-artisan/brand-assets"><img src="https://agentmods.dev/badge/skills/roslove44/brand-artisan/brand-assets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,177 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00110 $0.01177
Opus 5 $0.00055 $0.00589
Sonnet 5 $0.00022 $0.00235
Haiku 4.5 $0.00011 $0.00118

Measured 12d ago against content hash 6f5f51fefbba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

brand-assets 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 12d 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/brand-assets/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

brand-assets: generating brand assets

Goal: produce or evolve a project's brand files (logo, favicon, icons, OAuth variants and so on) with the brand toolchain, faithfully to what already exists. This is a separate world from the TS/Satori engine: here you produce the files that brands/<project>/logo and /favicon contain; the engine consumes them through brand().

Env and commands: see tools/README.md. This skill does not duplicate the launch commands (npx tsx tools/…). It encodes how to do it well.

0. Prerequisites (blocking)

  • Resolve <project>. Check brands/<project>/brand.md (colors, geometry, rules). Missing guidelines -> STOP: /new-project <project> first.

1. Frame it

Three cases:

  • Regenerate an existing asset (the guidelines or the geometry changed).
  • Add a variant of an existing asset (new color, background, size, e.g. the oauth-120-* files).
  • Start a new brand (create tools/<project>/, see the appendix).

2. The discipline of faithful reproduction (the heart of it)

Never guess the geometry of an existing asset. Inspect it first. For each reference file, read off the palette:

npx brand-artisan colors brands/<project>/logo/logo.png

It gives the dimensions and the palette sorted by pixel count: the first block is the background (transparent? opaque white?), the following ones the inks and accents. For an element's scale and margins, boundingBox(decode(file)) from brand-artisan/colors returns the box of what is painted ({ x, y, width, height }, or null if everything is transparent). Don't hand-write a pixel walk: the function is there and it is tested.

A real example (the OAuth variants): the palette revealed that mark-white was blue arcs on a white background (not white arcs), and the bounding box gave the exact scale of the bracket-O inside the frame. That is what keeps a visual from being "roughly right".

Read the full file on GitHub · 95 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. 12d ago First seen · 95 lines · 110 tokens per session scan A 6f5f51fefbba

Subscribe to this mod's changes

brand-assets is a skill published in the GitHub repository roslove44/brand-artisan (4 stars, last pushed 15d ago), licensed MIT. It adds 110 tokens to every session and 1,177 once invoked, about $0.0006 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.