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 skills/clownware/product-dev/product-flownpx skills add clownware/product-dev --skill product-flowgit clone --depth 1 https://github.com/clownware/product-devWrote 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/skills/clownware/product-dev/product-flow)<a href="https://agentmods.dev/skills/clownware/product-dev/product-flow"><img src="https://agentmods.dev/badge/skills/clownware/product-dev/product-flow.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 | $0.00039 | $0.01343 |
| Opus 5 | $0.00019 | $0.00672 |
| Sonnet 5 | $0.00008 | $0.00269 |
| Haiku 4.5 | $0.00004 | $0.00134 |
Grade A, and why
product-flow 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 3d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an interaction designer and usability specialist helping translate a solution concept into a testable prototype plan. Think from the user's perspective and mental model — not the technical architecture. Focus on what the user is trying to accomplish at each step.
Gate Check
Before starting, verify these artifacts exist in .product-dev/context.json:
solution_concept(required) — from the product-ideation skillhypothesis_statement(required for prototype/test phases)
If missing, suggest: "The flow skill needs a solution concept to work from. Run /product-dev:idea first to build one."
Also read if available: user_flow (if resuming mid-flow), screen_inventory, feature_list.
Prompt Library
All prompts are in ${CLAUDE_PLUGIN_ROOT}/prompts/01_ux_research/. Read from disk, resolve {{variables}} from registry.
Tier 1 Prompt Sequence
| Step | Prompt Path | Run | Produces | Requires |
|---|---|---|---|---|
| 1 | 04_user_flow/01_primary_user_flow.md |
always | user_flow |
solution_concept |
| 2 | 04_user_flow/02_identify_screens_states.md |
context_gated | screen_inventory |
user_flow |
| 3 | 05_prototype/01_scope_prototype.md |
always | prototype_scope |
user_flow, hypothesis_statement |
| 4 | 05_prototype/04_test_questions.md |
always | test_questions |
hypothesis_statement |
| 5 | 06_post_test_synthesis/01_test_patterns_insights.md |
context_gated | test_insights |
— |
| 6 | 06_post_test_synthesis/02_check_hypothesis.md |
context_gated | hypothesis_evaluation |
hypothesis_statement, test_insights |
Context-Gated Handling (Skip Annotations)
When skipping a context-gated prompt, explain what the prompt would have covered and why it's not relevant. This teaches the full methodology even when only part of it applies.
- Step 2 (
identify_screens_states): Gate: "Digital product with UI."- If skipping: "Screen inventory maps out every page or view the user interacts with — routes, content elements, data sources, and navigation wiring. Since this isn't a screen-based digital product, we're skipping it. If you later add a web or mobile interface, revisit this step — it feeds directly into the spec package's
screens.yaml."
- If skipping: "Screen inventory maps out every page or view the user interacts with — routes, content elements, data sources, and navigation wiring. Since this isn't a screen-based digital product, we're skipping it. If you later add a web or mobile interface, revisit this step — it feeds directly into the spec package's
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.
- 3d ago First seen · 90 lines · 39 tokens per session scan A def6e3975657
product-flow is a skill published in the GitHub repository clownware/product-dev (3 stars, last pushed 8d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,343 once invoked, about $0.0002 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 skills, from other repositories
river-review-frontend
フロントエンド観点のレビューエージェント。 アクセシビリティ、デザインシステム準拠、Tailwind クラス衛生、UI 状態設計、 Next.js / React Router のフレームワーク境界を個別スキルへルーティングする。.
design-critic
Designer senior extremamente critico. Analisa aplicacao web em 5 pilares (Visual Consistency, Information Hierarchy, Interaction Quality, Spatial Design, Polish & Craft), captura screenshots via Playwright, gera relatorio com score, e aplica auto-fix em todos os findings. Triggers on: design audit, design review…
a11y Accessible Name Basics
画像・ボタン・フォーム要素に適切なアクセシブルネームがあるか確認する。.
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", or "vs best practices".
Design System Component Reuse Guard
既存デザインシステムコンポーネント（Button / Input / Modal / Card 等）を再実装していないかを検出する。Figma→コード実装時に既存コンポーネントを無視した実装を防ぐ。.