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/pmprompt/claude-plugin-product-managementWrote 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/pmprompt/claude-plugin-product-management/claude-plugin-product-management)<a href="https://agentmods.dev/plugins/pmprompt/claude-plugin-product-management/claude-plugin-product-management"><img src="https://agentmods.dev/badge/plugins/pmprompt/claude-plugin-product-management/claude-plugin-product-management/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/pmprompt/claude-plugin-product-management/claude-plugin-product-management"><img src="https://agentmods.dev/badge/plugins/pmprompt/claude-plugin-product-management/claude-plugin-product-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pmprompt 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 9d 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": "pmprompt",
"description": "Claude plugin for product managers: reusable PM skills (PRDs, roadmaps, prioritization, positioning) for Claude Code and Cowork.",
"version": "0.2.0",
"author": {
"name": "pmprompt",
"url": "https://pmprompt.com"
},
"homepage": "https://pmprompt.com/claude-product-management-plugin",
"repository": "https://github.com/pmprompt/claude-plugin-product-management",
"license": "MIT",
"keywords": [
"claude",
"claude-plugin",
"claude-code",
"cowork",
"product-management",
"prd",
"roadmap",
"prioritization",
"jobs-to-be-done",
"shape-up",
"positioning"
]
}
What it installs
The manifest is a name and a version. 28 skills, 9 commands travel with it, and installing the plugin installs all of them — 1,859 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill opportunity-solution-trees A 68 tokens
- Skill positioning-canvas A 81 tokens
- Skill shaping A 30 tokens
- Skill competitive-analysis-framework A 26 tokens
- Skill design-sprint A 74 tokens
- Skill feature-prioritization-assistant A 33 tokens
- Skill growth-loops A 86 tokens
- Skill hierarchy-of-engagement A 84 tokens
- Skill hierarchy-of-marketplaces A 92 tokens
- Skill hooked-model A 76 tokens
- Skill monetizing-innovation A 80 tokens
- Skill okrs A 105 tokens
- Skill pmf-survey A 95 tokens
- Skill prd-writer A 24 tokens
- Skill product-led-growth A 83 tokens
- Skill product-led-seo A 90 tokens
- Skill radical-candor A 73 tokens
- Skill seven-powers A 70 tokens
- Skill shape-up A 85 tokens
- Skill stakeholder-update-generator A 27 tokens
- Skill strategic-narrative A 81 tokens
- Skill trustworthy-experiments A 71 tokens
- Skill working-backwards A 80 tokens
- Skill ab-test-designer A 28 tokens
- Skill breadboarding A 32 tokens
- Skill jobs-to-be-done A 78 tokens
- Skill thinking-in-bets A 76 tokens
- Skill user-feedback-synthesizer A 31 tokens
- Command competitive-intel A 0 tokens
- Command discover A 0 tokens
- Command growth A 0 tokens
- Command plan-launch A 0 tokens
- Command okr-planning A 0 tokens
- Command pricing A 0 tokens
- Command strategy A 0 tokens
- Command validate-idea A 0 tokens
- Command write-prd A 0 tokens
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 26 lines scan A 5a3f1b8b403a
pmprompt is a plugin published in the GitHub repository pmprompt/claude-plugin-product-management (49 stars, last pushed 6mo ago), licensed MIT. 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 2026-08-30.
Other plugins, from other repositories
pm-skills-marketplace
Product Management skills for AI agents.
pm-skills
68 product management skills (30 phase + 11 foundation + 12 utility + 15 tool) plus 6 sub-agents (pm-critic, pm-skill-auditor, pm-changelog-curator, pm-release-conductor, pm-workflow-orchestrator, pm-skill-router) for AI agents covering the full product lifecycle from discovery through iteration. v2.33.0 fixes the…
pm-execution
Execution and product management skills: PRDs, OKRs, roadmaps, sprints, pre-mortems, stakeholder maps, user stories, prioritization frameworks, and more.
prd-taskmaster
Zero-config goal-to-tasks engine for Claude Code (the Atlas engine). Graded PRD validation, dependency-ordered task graph, and CDD-verified execution.
pm-skills
Product manager skill suite for Claude Code — PRD writing, competitor research, daily briefing, HTML prototyping, feature acceptance, UI walkthrough.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.