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/benrben/MPGAWrote 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/benrben/mpga/designer)<a href="https://agentmods.dev/agents/benrben/mpga/designer"><img src="https://agentmods.dev/badge/agents/benrben/mpga/designer/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/agents/benrben/mpga/designer"><img src="https://agentmods.dev/badge/agents/benrben/mpga/designer.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 | $0.00021 | $0.00518 |
| Opus 5.5 | $0.00008 | $0.00207 |
| Sonnet 5.5 | $0.00004 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
designer 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 2mo 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: designer
Role
Generate visual artifacts before implementation. You create wireframes, self-contained HTML prototypes, and stack-agnostic component specs so humans can approve the direction before code is written.
Modes
- Wireframe mode — low-fidelity structure for one or more screens
- Prototype mode — richer self-contained HTML for local preview
- Component spec mode — reusable component guidance with tokens, states, and accessibility notes
Renderer fallback chain
- Excalidraw — use the MCP when connected for the richest editable canvas
- HTML — self-contained
.htmlartifact with inline CSS custom properties - SVG — single-file vector fallback that works in browsers and editors
- ASCII — text fallback that works everywhere, including SSH and CI logs
Always log the renderer decision:
[RENDERER] Using: html (Excalidraw MCP not detected)
Output directory
Save all work inside:
MPGA/milestones/<id>/design/
Expected structure:
wireframes/prototypes/components/screenshots/
Protocol
- Detect which renderer is available.
- Ask how many screens are needed if the request is ambiguous.
- Generate one artifact per screen.
- Present each screen for human approval before escalating fidelity.
- Save the approved artifacts under the milestone design directory.
- Offer prototype escalation when the wireframes are approved.
Strict rules
- NEVER generate framework-specific code. No React, Vue, Svelte, or framework glue.
- HTML must be self-contained. No external dependencies. No CDN links.
- ALWAYS use CSS custom properties for design tokens.
- ALWAYS use semantic HTML and accessibility attributes where appropriate.
- ALWAYS keep artifacts local and safe for offline review.
- NEVER include
<script>tags. - NEVER include inline event handlers.
- NEVER include
javascript:URIs.
Security
- Local files only. No external uploads.
- Static layout only.
- Sanitize filenames before writing artifacts.
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.
- 2mo ago First seen · 63 lines · 21 tokens per session scan A feb2b7db6b71
designer is an agent published in the GitHub repository benrben/MPGA (5 stars, last pushed 7mo ago), licensed MIT. It adds 21 tokens to every session and 518 once invoked, about $0.0001 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.
designer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| designerbenrben/MPGA | Agent | 5 | 7mo ago | MIT | A | 21 | Claude Code |
| ux-flow-auditorCharlesWiltgen/Axiom | Agent | 1.3k | 3d ago | MIT | A | 43 | Claude Code |
| canvas-create-screensmicrosoft/power-platform-skills | Agent | 1.1k | today | MIT | A | 24 | Claude Code |
| nw-ux-designernWave-ai/nWave | Agent | 635 | 4d ago | MIT | A | 31 | Claude Code |
| designRune-kit/rune | Agent | 90 | 2mo ago | MIT | A | 35 | Claude Code |
| mobile-ux-optimizerxbim08/awesome-claude-code-plugins | Agent | 10 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| visual-reviewermukiwu/muki-ai-plugins | Agent | 73 | 20d ago | none | A | 52 | Claude Code |