Agent Sh Agentsys
agent-sh-agentsys is a Claude Code plugin marketplace for the Ship phase that automates reviews, preship gates, onboarding, and multi-agent workflows beyond raw code generation.
by agent-sh · github.com/agent-sh/agentsys
Install AgentSys when AI writes your code but you still need automated onboarding, preship gates, audits, browser checks, and multi-agent orchestration across Claude Code, OpenCode, Codex, and Cursor.
Add it to Claude Code
Install the plugin in Claude Code. One command, paste-ready.
/plugin install agent-sh-agentsys@agent-sh/agentsysBuilt to be called by your agent
Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.
Retrieve this entry with skillselion.get_details("plugin:agent-sh/agentsys") and the paste-ready config with skillselion.get_install_config("plugin:agent-sh/agentsys").
What it does
agent-sh-agentsys is a large automation-oriented Claude Code plugin ecosystem positioned as the layer that runs when “AI writes code” but everything else—onboarding, reviews, browser verification, documentation hygiene, and release discipline—still needs a system. The catalog cites nineteen plugins, forty-seven agents, and forty skills, reflecting breadth across preship gates, performance profiling motifs, multi-round planners, and cross-model handoffs named in repository keywords. Solo builders adopt it to inject consistent agents.md-style orientation, automated audits, and structured handoffs between implementation and review without maintaining bespoke hooks for every repo. It spans Build (agent tooling and docs), Ship (review, security, launch prep), and Operate (monitoring drift and iteration), so Skillselion treats it as journey-wide with Ship → review as the primary shelf where buyers feel the pain most acutely. It is an orchestration marketplace, not a single integration.
Highlights
- Marketplace scale: 19 plugins, 47 agents, and 40 skills in one AgentSys repo
- Cross-tool support for Claude Code, OpenCode, Codex, Cursor, and Kiro
- Preship and delivery gates with doc-code sync, deslop, and drift detection motifs
- Multi-agent orchestration, debate, and parallel analyzers for investigations
- Browser headless workflows, onboarding orientation, and changelog-oriented automation
Why builders use it
Teams let LLMs ship features fast but lack automated gates, orientation, and cross-agent rituals—so quality, docs, and delivery discipline become manual bottlenecks.
After you register AgentSys, your coding agents gain plugins, agents, and skills for preship checks, orchestrated reviews, and repeatable delivery automation.
At a glance
- Type - Plugin in Automation.
- Adoption - 0 installs, 699 stars, 0 votes.
FAQ
Who is agent-sh-agentsys for?
It is for developers using Claude Code, OpenCode, Codex, Cursor, or Kiro who want nineteen plugins and dozens of agents to automate everything after the model writes code.
When should I use agent-sh-agentsys?
Use it when you need preship gates, automated audits, browser-assisted checks, onboarding orientation, or multi-agent review chains on real repositories.
How do I add agent-sh/agentsys to my agent?
Install the agent-sh/agentsys marketplace in your supported coding agent, then enable the plugins and skills that match your onboarding, review, and delivery workflow.
Comments
Share how you use agent-sh-agentsys, gotchas, or tips for other indie builders.
No comments yet - be the first to share how you use it.