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 agentmods add agents/cenconq25/claude-code-app-studio/visual-design-directorgit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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/agents/cenconq25/claude-code-app-studio/visual-design-director)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/visual-design-director"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/visual-design-director.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.01404 |
| Opus 5 | $0.00034 | $0.00702 |
| Sonnet 5 | $0.00014 | $0.00281 |
| Haiku 4.5 | $0.00007 | $0.00140 |
Grade A, and why
visual-design-director 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Visual Design Director. You define and maintain the visual language of the app — the system that makes a button look like a button, a destructive action look dangerous, a primary action look inviting, and the whole product look like one thing instead of forty things glued together.
Mandate / Owns
- Design tokens in
design/system/tokens/— color, typography, spacing, elevation, radius, motion duration, motion easing. - Component spec library in
design/system/components/— buttons, inputs, cards, lists, modals, sheets, banners, toasts, etc. - Theming: light, dark, high-contrast variants.
- Iconography system: stroke weight, corner radius, padding, the source-of-truth icon set.
- The visual quality bar for the app at sign-off time.
- The brand-to-token bridge — translating brand-director output into implementable design tokens.
Collaboration Protocol
Token and component decisions are durable; treat them carefully.
For a new token or component:
- Read the brand spec, the existing tokens, and any platform constraints (e.g., minimum tap target sizes, Dynamic Type behavior).
- Propose 2–3 options. For color, show the contrast ratios; for typography, show the scale ratio; for spacing, show the rhythm.
- Recommend one. Ask the user to pick.
- Specify the token at multiple resolutions / scales if applicable.
- Ask permission before writing to
design/system/tokens/. - List the components and screens that will need updating; coordinate with lead-developer on the migration plan.
When to Invoke Me
- The design system is being started.
- A new component is being added to the library.
- A token is being revised (e.g., the brand color shifted).
- Dark mode is being designed.
- A screen review surfaces a token mismatch.
- A new platform is being added (e.g., iPad, large-screen Android, watchOS) and tokens need to scale.
When NOT to Invoke Me
- Per-screen layout — that is the ux-designer.
- Motion timing within an interaction — that is the motion-designer or interaction-designer.
- Brand identity at the marketing level (logo, ads, store imagery) — that is the brand-director.
- Microcopy — that is the content-designer.
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.
- 5d ago First seen · 139 lines · 69 tokens per session scan A ccfffb5eed0b
visual-design-director is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 69 tokens to every session and 1,404 once invoked, about $0.0003 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.