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.
npx skills add Andytoizer/gtm-brain-builder --skill design-system-agentgit clone --depth 1 https://github.com/Andytoizer/gtm-brain-builderWrote 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.
[](https://agentmods.dev/skills/andytoizer/gtm-brain-builder/design-system-agent)<a href="https://agentmods.dev/skills/andytoizer/gtm-brain-builder/design-system-agent"><img src="https://agentmods.dev/badge/skills/andytoizer/gtm-brain-builder/design-system-agent/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.
<a href="https://agentmods.dev/skills/andytoizer/gtm-brain-builder/design-system-agent"><img src="https://agentmods.dev/badge/skills/andytoizer/gtm-brain-builder/design-system-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.00754 |
| Opus 5.5 | $0.00018 | $0.00302 |
| Sonnet 5.5 | $0.00009 | $0.00151 |
| Haiku 4.5 | $0.00005 | $0.00075 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design System Agent
Use this when the operator wants help creating a design system, preparing the right prompt/brief for a design tool, or importing design outputs into the GTM Brain.
Owns brand/design-system-brief.md, the visual-system parts of brand/brandkit.md, and design project notes in brand/design-resources.md.
Inputs
company/product-truth.mdcompany/approved-claims.mdicp/messaging/customers/proof-approval.mdbrand/brandkit.mdbrand/design-resources.mdbrand/voice-system.md- Existing website, app screenshots, logo files, decks, Figma, Canva, social posts, and public docs
- Operator/accountable-owner taste review
Outputs
brand/design-system-brief.md- Updated
brand/brandkit.md - Updated
brand/design-resources.md - Optional implementation notes for Codex when the design system needs to become code, components, CSS tokens, slides, or website assets
Walkthrough
- Read the smallest source-backed context needed for the design decision.
- Ask the operator what they are trying to make: brand kit, design system, deck style, landing page direction, social templates, component library, or coded UI.
- Build a design-system brief before generation:
- audience and category
- desired perception
- brand personality and tone boundaries
- product truths and approved claims
- proof constraints and do-not-claim rules
- visual references and anti-references
- required outputs
- review checklist
- If using Claude.ai/design, tell the operator to open
https://claude.ai/design, create a brand-kit or design-system project, paste the brief, and upload only approved assets. - If using Codex to implement or import the design system, convert the approved design brief into implementation instructions: tokens, typography, component rules, asset paths, responsive behavior, accessibility notes, and files to update.
- Review generated output with Grill-me before treating it as durable taste.
- Import approved decisions:
brand/brandkit.md: stable visual rules, tokens, typography, logo usage, layout rules, examples, and do/don't guidancebrand/design-resources.md: project links, prompts, uploaded inputs, exports, asset locations, and owner review statebrand/voice-system.md: only the voice implications, not visual rules- implementation notes: where Codex should apply tokens/components when building downstream assets
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 83 lines · 45 tokens per session scan A ed1958130c44
design-system-agent is a skill published in the GitHub repository Andytoizer/gtm-brain-builder (8 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 754 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
eval-graphics
Turn an eval study's numbers into on-brand, publish-ready figures using the Newsjack chart room (the eval design system), then validate them with Playwright. For producing the charts in a published eval/data study.
openkb-html-critic
Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…
ui-ux-gtm
Design GTM UI/UX patterns — landing pages (hero, proof, CTA), forms (progressive disclosure, inline validation), signup flows (activation, time-to-value), dashboards (KPI hierarchy, trend indicators), and accessibility (WCAG 2.2 AA). Use when designing or auditing GTM tool interfaces, landing pages, conversion flows…
design-system-gtm
Define brand-context for AI agents — visual identity systems, voice/tone guides, color palettes with hex/RGB/HSL, typography systems with font stacks and type scales, logo usage rules, asset templates, and brand guardrails. Use when creating a design system for AI-generated GTM content, ensuring brand consistency…
content-atomizer
Repurposes single content pieces into multiple formats for maximum distribution while maintaining brand voice. This skill should be used when maximizing ROI from pillar content, filling content calendars efficiently, reaching audiences across multiple platforms, or when creating original content for every channel…
orchestrator
Diagnoses marketing needs and sequences appropriate skills for comprehensive campaigns. This skill should be used when unsure which marketing skill to use, planning multi-step marketing campaigns, creating integrated marketing strategies, or when a project spans multiple marketing disciplines.