design-system-agent

design-system-agent is an agent for coding agents from Andytoizer/gtm-brain-builder. It costs 42 tokens per session (215 once invoked), scanned A, original, MIT.

A design-workflow guide for preparing a source-backed design-system brief, using a design tool, reviewing its drafts, and recording approved decisions in a GTM Brain.

In plain words
What is it for?
It helps create design briefs, guide visual generation, review drafts, and import approved reusable design rules and project records.
Why use it?
It helps keep visual decisions, product claims, proof, and positioning organised and reviewable instead of leaving them scattered across design projects and exports.

Agent

Part of the gtm-brain-builder plugin — 11 skills, 9 agents 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/andytoizer/gtm-brain-builder/design-system-agent
Clone the repo
git clone --depth 1 https://github.com/Andytoizer/gtm-brain-builder

Or install gtm-brain-builder, the plugin that ships this one along with the rest of its 11 skills, 9 agents.

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 design-system-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/andytoizer/gtm-brain-builder/design-system-agent.svg)](https://agentmods.dev/agents/andytoizer/gtm-brain-builder/design-system-agent)
Your own site
<a href="https://agentmods.dev/agents/andytoizer/gtm-brain-builder/design-system-agent"><img src="https://agentmods.dev/badge/agents/andytoizer/gtm-brain-builder/design-system-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 215 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 $0.00042 $0.00215
Opus 5 $0.00021 $0.00108
Sonnet 5 $0.00008 $0.00043
Haiku 4.5 $0.00004 $0.00021

Measured 4d ago against content hash 699dd3545870, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-system-agent 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 4d 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/design-system-agent.md · 24 lines

What it actually says

You are the design system agent.

Use the $design-system-agent skill as your playbook.

Owns

  • brand/design-system-brief.md
  • Design-system sections of brand/brandkit.md
  • Claude.ai/design or Codex design project notes in brand/design-resources.md
  • Import checklist for moving approved design decisions back into the GTM Brain

Output Standard

  • Prepare a structured brief before asking any design tool to generate assets.
  • Keep product claims, proof, positioning, and taste decisions source-backed.
  • Walk the operator step by step through tool setup, prompting, review, export, and import.
  • Treat generated design output as a draft until reviewed by an accountable owner.
  • Store approved reusable rules in the brain; store project links, exports, and prompt history in design resources.
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. 4d ago First seen · 24 lines · 42 tokens per session scan A 699dd3545870

Subscribe to this mod's changes

design-system-agent is an agent published in the GitHub repository Andytoizer/gtm-brain-builder (8 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 215 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 2026-08-31.

Related

Other agents, from other repositories

demo-producer

Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.

yonatangross/orchestkit · 42 tokens

ui-ux-designer

Use this agent when you need UI/UX design guidance, component design decisions, user experience improvements, accessibility recommendations, or design system advice. Examples: Context: User is working on improving the card creation interface in Zettelgarden. user: 'The card creation form feels clunky and users are…

Zettelgarden/Zettelgarden · 214 tokens

visual

Visual review role for the VISUALREVIEW stage (optional; full path only). Walks the rendered UI against the frontend design and design-quality guidelines, reporting issues. Queries the knowledge base for guidelines. Does not change code.

shenchangmin/cairnkit · 48 tokens

email-template-designer

Responsive email template and campaign optimization specialist.

viksant/vibe-coding-tools-content · 7 tokens

hormozi-persona

Alex Hormozi persona, always in first person, never breaking character. Use as the base voice in every hormozi-gtm command. Runs Value Equation + Core Four + Money Models analysis before executing any request. Brutal, constructive feedback.

henriquecaner/hormozi-gtm · 58 tokens

ad-architect

Video script specialist — long-form VSL (8-15min) and short-form (15-60s for Reels/Shorts/TikTok). Masters the hook framework, the VSL 7-step arc, and ad copy formula. Use to write new scripts, refine existing ones, or generate batches of variants.

henriquecaner/hormozi-gtm · 70 tokens