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.
git clone --depth 1 https://github.com/jameywarren/shopify-claude-quickstartWrote 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/commands/jameywarren/shopify-claude-quickstart/brand-system)<a href="https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/brand-system"><img src="https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/brand-system/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/commands/jameywarren/shopify-claude-quickstart/brand-system"><img src="https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/brand-system.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 | $0.00014 | $0.00529 |
| Opus 5 | $0.00007 | $0.00264 |
| Sonnet 5 | $0.00003 | $0.00106 |
| Haiku 4.5 | $0.00001 | $0.00053 |
Grade A, and why
brand-system 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 9d 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.
What it actually says
You are capturing the visual identity of this client's brand. Ask questions one at a time. Wait for an answer before moving to the next question. Don't ask all questions at once.
The goal is to fill design/brand-system.md with enough specificity that any implementation decision — section layout, color application, font pairing, copy tone — can be made without asking again.
Start by reading:
client-brief/design-brief.md(orclient-brief-QUICK.md) — to avoid re-asking what's already documenteddesign/brand-system.md— to see what's already filled in and only ask about gaps
Then work through these questions, skipping anything already answered:
Colors
- What are the primary and secondary brand colors? (Hex values preferred — if they say a color name or describe it, push for hex.)
- What's the background color for most pages? Dark, light, or neutral?
- Is there an accent or call-to-action color that's different from the primary?
Typography 4. What fonts does the brand use? (Separate display/headline font from body font if different.) 5. Are these Google Fonts, Adobe Fonts, a custom font file, or a Shopify-native font? 6. Any rules about font weight or size hierarchy? (E.g. "headings are always thin weight", "body is 16px/1.6")
Visual Feel 7. Share 2–3 URLs of sites or brands this should feel like. What specifically do you like about them? 8. Share 1–2 examples of what this brand should NOT look like. What would feel wrong?
Voice in Visual Context 9. One sentence: what emotion should someone feel 5 seconds after landing on the homepage? 10. Any visual rules that are non-obvious? (E.g. "never use stock photography", "all images are black and white", "we never use rounded corners")
After all questions are answered:
Write a complete design/brand-system.md using the template format. Be specific — hex codes not color names, exact font names not categories. Flag any gaps where the client still needs to provide an asset (e.g. "SVG wordmark not yet received").
Confirm the file is written, then suggest the next step: if mockups exist in design/mockups/, run /design-intake. If not, run /homepage-from-brief to get a layout proposal grounded in the brand system.
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.
- 9d ago First seen · 38 lines · 14 tokens per session scan A 1792bf05583e
brand-system is a command published in the GitHub repository jameywarren/shopify-claude-quickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 529 once invoked, about $0.0001 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.
Other commands, from other repositories
profile
Save, load, inspect, update, reset, or delete diagram-design client profiles.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
team-ui
Orchestrate UI/UX design team.
p3-ux-wireframes
Creates wireframes (ASCII art) for the most important screens with interaction descriptions.