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/shaan-ad/pm-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/plugins/shaan-ad/pm-os/marketplace)<a href="https://agentmods.dev/plugins/shaan-ad/pm-os/marketplace"><img src="https://agentmods.dev/badge/plugins/shaan-ad/pm-os/marketplace/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/shaan-ad/pm-os/marketplace"><img src="https://agentmods.dev/badge/plugins/shaan-ad/pm-os/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pm-os-marketplace 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 1mo 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": "pm-os-marketplace",
"owner": {
"name": "Shaan Agara",
"url": "https://github.com/shaan-ad"
},
"plugins": [
{
"name": "pm-os",
"description": "27 AI-powered skills for every PM workflow: PRDs, prioritization, competitive intel, stakeholder updates, launch planning, slide decks, and more.",
"source": {
"source": "url",
"url": "https://github.com/shaan-ad/pm-os.git"
},
"category": "productivity",
"homepage": "https://github.com/shaan-ad/pm-os"
}
]
}
The plugins it lists here
This marketplace lists 1 plugin kept in the same repository. Each has its own page, its own measurements and its own install command.
What ships with it
1 file beside marketplace.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.
- 1mo ago First seen · 20 lines scan A b1bd2e867c83
pm-os-marketplace is a plugin published in the GitHub repository shaan-ad/pm-os (31 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
brewcode
Brewcode - Claude Code authoring toolkit: skill, agent and rule creation and sync, semantic code search (semble), project conventions, E2E tests, generated review and domain-team skills, setup dashboard, post-compact plan re-anchor.
iterm-notify
macOS desktop notifications and iTerm2 badge management for Claude Code lifecycle events.
kimchi
Turns a raw product idea into a clean, build-ready doc set — locked decisions, API contracts, a story-by-story plan, and an execute.md your AI builds autonomously. Gets the clarity by grilling you through 11 world-class expert personas that counter and refuse to flatter. Ends the friction of prompting Claude to…
fp-yoohoo
Terminal-recall mode. When Claude Code stops to ask you something (a permission prompt, a question dialog, an agent blocked on input) it brings the terminal window to the foreground, so a waiting session is impossible to miss and you never have to remember to check back. Skips the raise when the terminal already has…
instinct
Skills and tools to help agents and users make better, calculated decisions.
skillbelt
Claude Code skills — Teams read/send, cmux doc + browser panes, and more.