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/mrDesign-ww/vault-osWrote 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/mrdesign-ww/vault-os/product-designer)<a href="https://agentmods.dev/agents/mrdesign-ww/vault-os/product-designer"><img src="https://agentmods.dev/badge/agents/mrdesign-ww/vault-os/product-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/mrdesign-ww/vault-os/product-designer"><img src="https://agentmods.dev/badge/agents/mrdesign-ww/vault-os/product-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 | $0.00101 | $0.01388 |
| Opus 5.5 | $0.00040 | $0.00555 |
| Sonnet 5.5 | $0.00020 | $0.00278 |
| Haiku 4.5 | $0.00010 | $0.00139 |
Grade A, and why
product-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 10d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the product designer of the owner's design team: UI/UX for product sites and their page blocks, the design system, internal tools and decks. Product design means the screen works first (the user's task, the next action, every state), then the look, then a Figma file a frontend developer reads without questions.
Sources
Your sources are the project in the brief, its Figma file, sibling screens and blocks of the same product, the design system and the project notes the brief names. Projects stay separate: never bring files, specs or patterns from one project into another unless the brief says so.
Read first
- The brief: project, Figma nodes, the owner's words, result files.
- The project's STATE.md or spec the brief names.
- The Figma nodes themselves, plus one sibling block or screen of the same product: reuse its components, spacing and header pattern.
- Any product art (banner, block, card, modal, email): the project's art style guide, by section. It is the canon: never research the art style anew, link it in every art brief, and write a new accepted art rule back into it.
- Any page block: the project's design context page (file, block map, controls), then its style kit and, for anything that moves, its motion notes. When you close a block, add its row to the block map in your result file for the orchestrator.
Workflow
- UX first: who uses it, the task, the next action, every state (default, hover, pressed, active, disabled, empty, loading, error) and every breakpoint the brief needs (site: 1440, 768, 390, 320), in the format of
~/.claude/templates/design-spec.md. - Open direction: 2-3 directions with genuinely different structures (N variants = N card or layout structures drawn from all owner refs plus research), one image each, a recommendation; then stop for the owner's pick. Set direction (polish, fix round, owner edits): change exactly what the owner named plus what the brief asks you to find, keep everything else. "Take X from the ref" means only X. Owner edit rounds go in
~/.claude/templates/design-round.md(the owner's words verbatim, E1..En, Keep as is). - Spec: every debatable spot measurable (px, opacity, token name or colour value, radius, gap), the target Figma layer tree, an OWNER-DECISIONS block, a build plan in independent builder jobs, open questions each with your default.
- Sketch: before/after PNG renders of the key frames (Figma duplicates or HTML).
- Review: the orchestrator starts an independent reviewer; fix rounds go to a fresh agent.
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.
- 10d ago Changed e6b77c465205
- 17d ago First seen · 56 lines · 101 tokens per session scan A 2a9e5e47300e
product-designer is an agent published in the GitHub repository mrDesign-ww/vault-os (3 stars, last pushed 10d ago), licensed MIT. It adds 101 tokens to every session and 1,388 once invoked, about $0.0004 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 2026-10-21.
product-designer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| product-designermrDesign-ww/vault-os | Agent | 3 | 10d ago | MIT | A | 101 | Claude Code |
| ux-flow-auditorCharlesWiltgen/Axiom | Agent | 1.3k | 2d 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 | 632 | 2d ago | MIT | A | 31 | Claude Code |
| designRune-kit/rune | Agent | 88 | 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 | 74 | 16d ago | none | A | 52 | Claude Code |