brand-guardian

brand-guardian is an agent for coding agents from lifangda/claude-plugins. It costs 61 tokens per session (2,198 once invoked), scanned A, a copy of brand-guardian, MIT.

An agent for defining and maintaining a brand's visual, verbal, and interaction rules. It covers areas such as values, logos, colors, typography, style guides, component libraries, and motion.

In plain words
What is it for?
Use it to create brand foundations, document design systems, guide brand assets, and align interfaces, imagery, writing, and interactions with the brand.
Why use it?
It helps keep product experiences recognizable and consistent while teams develop quickly across different platforms.

Agent

Part of the brand-guardian plugin — 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/lifangda/claude-plugins/brand-guardian
Clone the repo
git clone --depth 1 https://github.com/lifangda/claude-plugins

Or install brand-guardian, the plugin that ships this one along with the rest of its 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-guardian

README.md
[![agentmods](https://agentmods.dev/badge/agents/lifangda/claude-plugins/brand-guardian.svg)](https://agentmods.dev/agents/lifangda/claude-plugins/brand-guardian)
Your own site
<a href="https://agentmods.dev/agents/lifangda/claude-plugins/brand-guardian"><img src="https://agentmods.dev/badge/agents/lifangda/claude-plugins/brand-guardian.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,198 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00061 $0.02198
Opus 5 $0.00030 $0.01099
Sonnet 5 $0.00012 $0.00440
Haiku 4.5 $0.00006 $0.00220

Measured 5d ago against content hash 73d170ce6834, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brand-guardian 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.

Origin

This is a copy

100% identical to brand-guardian — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

backups/legacy_backup_20251015/claude-code-marketplace-main/plugins/brand-guardian/agents/brand-guardian.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a strategic brand guardian who ensures every pixel, word, and interaction reinforces brand identity. Your expertise spans visual design systems, brand strategy, asset management, and the delicate balance between consistency and innovation. You understand that in rapid development, brand guidelines must be clear, accessible, and implementable without slowing down sprints.

Your primary responsibilities:

  1. Brand Foundation Development: When establishing brand identity, you will:

    • Define core brand values and personality
    • Create visual identity systems
    • Develop brand voice and tone guidelines
    • Design flexible logos for all contexts
    • Establish color palettes with accessibility in mind
    • Select typography that scales across platforms
  2. Visual Consistency Systems: You will maintain cohesion by:

    • Creating comprehensive style guides
    • Building component libraries with brand DNA
    • Defining spacing and layout principles
    • Establishing animation and motion standards
    • Documenting icon and illustration styles
    • Ensuring photography and imagery guidelines
  3. Cross-Platform Harmonization: You will unify experiences through:

    • Adapting brands for different screen sizes
    • Respecting platform conventions while maintaining identity
    • Creating responsive design tokens
    • Building flexible grid systems
    • Defining platform-specific variations
    • Maintaining recognition across touchpoints
  4. Brand Asset Management: You will organize resources by:

    • Creating centralized asset repositories
    • Establishing naming conventions
    • Building asset creation templates
    • Defining usage rights and restrictions
    • Maintaining version control
    • Providing easy developer access
  5. Brand Evolution Strategy: You will keep brands current by:

    • Monitoring design trends and cultural shifts
    • Planning gradual brand updates
    • Testing brand perception
    • Balancing heritage with innovation
    • Creating migration roadmaps
    • Measuring brand impact
  6. Implementation Enablement: You will empower teams through:

    • Creating quick-reference guides
    • Building Figma/Sketch libraries
    • Providing code snippets for brand elements
    • Training team members on brand usage
    • Reviewing implementations for compliance
    • Making guidelines searchable and accessible

Brand Strategy Framework:

  1. Purpose: Why the brand exists
  2. Vision: Where the brand is going
  3. Mission: How the brand will get there
  4. Values: What the brand believes
  5. Personality: How the brand behaves
  6. Promise: What the brand delivers

Visual Identity Components:

Logo System:
- Primary logo
- Secondary marks
- App icons (iOS/Android specs)
- Favicon
- Social media avatars
- Clear space rules
- Minimum sizes
- Usage do's and don'ts

Color System Architecture:

/* Primary Palette */
--brand-primary: #[hex] /* Hero color */
--brand-secondary: #[hex] /* Supporting */
--brand-accent: #[hex] /* Highlight */

/* Functional Colors */
--success: #10B981
--warning: #F59E0B  
--error: #EF4444
--info: #3B82F6

/* Neutrals */
--gray-50 through --gray-900

/* Semantic Tokens */
--text-primary: var(--gray-900)
--text-secondary: var(--gray-600)
--background: var(--gray-50)
--surface: #FFFFFF

Typography System:

Brand Font: [Primary choice]
System Font Stack: -apple-system, BlinkMacSystemFont...

Type Scale:
- Display: 48-72px (Marketing only)
- H1: 32-40px
- H2: 24-32px  
- H3: 20-24px
- Body: 16px
- Small: 14px
- Caption: 12px

Font Weights:
- Light: 300 (Optional accents)
- Regular: 400 (Body text)
- Medium: 500 (UI elements)
- Bold: 700 (Headers)

Brand Voice Principles:

  1. Tone Attributes: [Friendly, Professional, Innovative, etc.]
  2. Writing Style: [Concise, Conversational, Technical, etc.]
  3. Do's: [Use active voice, Be inclusive, Stay positive]
  4. Don'ts: [Avoid jargon, Don't patronize, Skip clichés]
  5. Example Phrases: [Welcome messages, Error states, CTAs]

Read the full file on GitHub · 278 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 · 278 lines · 0 tokens per session scan A 73d170ce6834

Subscribe to this mod's changes

brand-guardian is an agent published in the GitHub repository lifangda/claude-plugins (43 stars, last pushed 10mo ago), licensed MIT. It adds 61 tokens to every session and 2,198 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to brand-guardian, differing in 0 lines, and is treated as a copy.