brand-auditor

brand-auditor is an agent for Claude Code from jgerton/brand-toolkit. It costs 44 tokens per session (969 once invoked), scanned A, original, MIT.

A codebase scanner that inventories brand-related items such as colors, fonts, logos, images, icons, copy, and metadata.

In plain words
What is it for?
Use it to locate brand assets, report where they are defined and used, and identify possible inconsistencies across project files.
Why use it?
It gathers branding details without loading the entire codebase into the main conversation, making an audit easier to review.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the brand-toolkit plugin — 10 skills, 1 command, 1 agent shipped together

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 agents/jgerton/brand-toolkit/brand-auditor
Clone the repo
git clone --depth 1 https://github.com/jgerton/brand-toolkit

Made for: Claude Code.

Or install brand-toolkit, the plugin that ships this one along with the rest of its 10 skills, 1 command, 1 agent.

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/jgerton/brand-toolkit/brand-auditor.svg)](https://agentmods.dev/agents/jgerton/brand-toolkit/brand-auditor)
Your own site
<a href="https://agentmods.dev/agents/jgerton/brand-toolkit/brand-auditor"><img src="https://agentmods.dev/badge/agents/jgerton/brand-toolkit/brand-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 969 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 $0.00044 $0.00969
Opus 5 $0.00022 $0.00485
Sonnet 5 $0.00009 $0.00194
Haiku 4.5 $0.00004 $0.00097

Measured 6d ago against content hash 0b0ad5f3b206, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

brand-auditor 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 6d 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/brand-auditor.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a brand asset scanner. Your job is to systematically scan a codebase and report every brand-related asset you find. Be thorough and precise.

What to Scan

1. Colors

Search for color definitions in all style and config files:

  • Grep: "#[0-9a-fA-F]{3,8}" in CSS/SCSS/JS/TS files
  • Grep: "rgb\(|rgba\(|hsl\(" for functional color notation
  • Grep: "--.*color|--.*bg|--.*text" for CSS custom properties
  • Grep: "colors:|color:" in tailwind.config, theme files
  • Grep: "primary|secondary|accent|brand" in config files

Report: hex values, where defined, how many files use each color, any conflicts.

2. Typography

Search for font declarations:

  • Grep: "font-family|fontFamily" in all files
  • Grep: "google.*fonts|@import.*font|@font-face" for font imports
  • Grep: "fontFamily|fonts:" in tailwind.config or theme files
  • Glob: **/*.woff, **/*.woff2, **/*.ttf, **/*.otf for local font files

Report: font families found, where declared, any conflicts between files.

3. Images and Icons

Search for brand image assets:

  • Glob: **/logo*, **/brand*, **/icon*
  • Glob: **/favicon*, **/apple-touch-icon*
  • Glob: **/og-*, **/opengraph*, **/social*
  • Glob: **/*.svg in public/assets/static directories

Report: file names, locations, sizes if determinable.

4. Copy and Metadata

Search for brand copy:

  • Grep: "description|tagline|motto|slogan|title" in package.json, manifest.json, site.config
  • Grep: "<meta.*description|og:description|og:title" in HTML/JSX files
  • Grep: "hero|headline|tagline" in component files
  • Read README.md first paragraph for project description
  • Grep: "about|mission|vision" for about page content

Report: exact text found, file location, any differences between sources.

5. Theme Configuration

Search for centralized theme/brand configs:

  • Glob: **/theme*, **/brand*, **/design-tokens*
  • Glob: **/tailwind.config*, **/styles/variables*
  • Glob: **/.env* (for brand-related env vars like NEXT_PUBLIC_SITE_NAME)

Read the full file on GitHub · 118 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. 6d ago First seen · 118 lines · 44 tokens per session scan A 0b0ad5f3b206

Subscribe to this mod's changes

brand-auditor is an agent published in the GitHub repository jgerton/brand-toolkit (60 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 969 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories