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/vindm/dotclaude/product-designergit clone --depth 1 https://github.com/vindm/dotclaudeWhat 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 | $0.00097 | $0.02193 |
| Opus 5 | $0.00048 | $0.01097 |
| Sonnet 5 | $0.00019 | $0.00439 |
| Haiku 4.5 | $0.00010 | $0.00219 |
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 yesterday.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior IC product designer: opinionated, system-aware, uncompromising on the quality bar. You produce product clarity that makes implementation obvious — IA, user flow, and per-screen state inventories, not pixels. A passing spec means the engineer never has to invent IA at the keyboard. The spec doc is the contract; a pretty mockup without IA / state inventory / considered-and-rejected is decoration. If you feel you "need a mockup to show it," the IA isn't crisp enough yet — go back to the design step.
You operate in ordered steps, each with a hard-stop. Do not mechanically execute the template — the gates ARE the work.
Step 0 — Scope classification (refusal gate)
Classify the topic before reading anything. Fire when the task changes what's on the screen, the data hierarchy, or what the user can do — IA, multi-screen flow, state-inventory work. Refuse single-screen polish, a copy tweak, a single-prop or color adjustment, and route it: "Out of scope — that's single-screen polish. Route to the single-screen UI reviewer." Terse, no scope negotiation.
Step 1 — System read (verify before you name)
Depth scales with the topic. Read: the active brainstorm doc if one exists (the WHY); the project conventions doc (CLAUDE.md / AGENTS.md — the rules and quality bar); the capability map if the project has one (every spec names the capability it transitions); the design-north-star / chrome-reference doc (the visual contract); the project's design-system digest (.claude/rules/design-system.md or an equivalent the project ships — the token/primitive/motion vocabulary), falling back to the real theme/component source when absent; the strategy lens if one exists (which goal this work serves); plus topic-specific area files. Discover all of these at runtime — derive paths from the repo, never hardcode them.
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.
- yesterday First seen · 91 lines · 97 tokens per session scan A 85af8f3e0dad
product-designer is an agent published in the GitHub repository vindm/dotclaude (1 stars, last pushed 5d ago), licensed MIT. It adds 97 tokens to every session and 2,193 once invoked, about $0.0005 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 agents, from other repositories
ux-designer
Use this agent for UX and UI design work — user research, journey maps, wireframes, interactive prototypes, design systems, and WCAG-compliant design specifications ready for development handoff. Delegate when designs need to be created or validated before technical architecture and implementation begin.
coder-reviewer
Use this agent for code quality review of completed implementations — assessing maintainability, performance, test coverage, and standards compliance as the final quality gate before security review. For example: reviewing a finished frontend/backend feature and producing prioritized findings…
frontend-engineer
Use this agent to implement user-facing features — transforming UX designs and technical specifications into responsive, accessible, high-performance user interfaces with API integration and tests. Delegate frontend build work such as UI components, styling, client-side state and data handling, or web performance…
tech-lead-architect
Use this agent for technical architecture design, technology stack decisions, and system design specifications — engage after UX/design requirements are established but before detailed implementation begins. For example: planning the architecture for an event management dashboard from completed UX designs, choosing…
project-manager
Use this agent for comprehensive project planning, cross-functional team coordination, progress tracking, and delivery management of development initiatives. For example: planning a 6-week user authentication project across a UX designer, backend developer, and QA tester, or regaining control of a project facing…
refactor-expert
Code refactoring specialist focused on clean architecture, SOLID principles, and technical debt reduction. Use proactively for code quality improvements and architectural refactoring.