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/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/plugins/clownware/product-dev/plugin)<a href="https://agentmods.dev/plugins/clownware/product-dev/plugin"><img src="https://agentmods.dev/badge/plugins/clownware/product-dev/plugin/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/plugins/clownware/product-dev/plugin"><img src="https://agentmods.dev/badge/plugins/clownware/product-dev/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
product-dev 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.
What it actually says
{
"name": "product-dev",
"description": "AI-assisted product development framework. Guides from vague idea to technical spec through structured UX research, hypothesis formation, and prototype planning.",
"version": "0.5.4",
"author": {
"name": "clownware"
},
"license": "Apache-2.0",
"keywords": [
"product-development",
"ux-research",
"prototyping",
"tech-spec"
]
}
What it installs
The manifest is a name and a version. 5 skills, 6 commands, 2 agents travel with it, and installing the plugin installs all of them — 354 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill status A 24 tokens
- Skill product-ideation A 40 tokens
- Skill tech-spec A 36 tokens
- Skill ux-optimization A 49 tokens
- Skill product-flow A 39 tokens
- Command compile A 10 tokens
- Command summary A 27 tokens
- Command idea A 10 tokens
- Command optimize A 14 tokens
- Command problem A 8 tokens
- Command spec A 8 tokens
- Agent tech-spec-writer A 41 tokens
- Agent ux-extractor A 48 tokens
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 Changed a618a1f5bafd
- 1mo ago First seen · 16 lines scan A 364d1c1f0ab1
product-dev is a plugin published in the GitHub repository clownware/product-dev (3 stars, last pushed 3d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
product
Product strategy, UX and usability audit, design systems, interface craft, brand expression, and visual direction.
fuse-design
Design Director for websites, web apps, iOS, and Android. Generates HTML/CSS directly (Gemini Design MCP, Magic/21st.dev, and shadcn MCP are optional). iOS/Android produce tokens + a device-framed mockup + a handoff spec, never SwiftUI/Compose. Design method, design system tokens, motion, UX copy, and a deterministic…
repo-doctor
Diagnostic skills for GitHub repos. Currently ships readme-doctor — a structured review of a repo's README against best-practice patterns (hero presence, install-to-first-success length, audience match, drift signals), output as a prioritized punch list.
dotnet-coverage-kit
Characterization-test backfill and spec-test enforcement for .NET services. Deterministic C0/C1 measurement via dotnet-coverage, with a checked-in manifest that explains every inclusion and exclusion.
repo-visuals
Designs bespoke GitHub README hero visuals — animated GIF, static PNG, or animated SVG — through a structured discovery dialog. Retina capture, scope-matched copy, optional upstream PR.
vstack
Stop prompting. Start pointing. Visual Stack adds a Figma-like feedback layer to Claude Code. Create a new screen from a prompt, screenshot, reference site, or design system, or open an app you already have running. Click any element and leave feedback exactly where the problem is hiding, and Claude publishes the next.