Marketplaces & plugins
This is where agentsync earns its keep. A plugin is a bag of components — MCP servers, skills, subagents, commands, hooks, LSP servers. Install it once and every enabled agent gets the components it understands.
Install a plugin
Section titled “Install a plugin”-
Add a marketplace (a registry of plugins):
Terminal window agentsync marketplace add github:anthropics/claude-plugins-official -
Install a plugin from it:
Terminal window agentsync plugin install atlassian@anthropic -
Fetch from the network —
updateis the only networked verb:Terminal window agentsync update -
Apply — renders from the local cache to all agents:
Terminal window agentsync apply
The translation report
Section titled “The translation report”Each component in a plugin is projected independently per agent — fully, lossily, or skipped — and the report tells you exactly which:
plugin: atlassian@anthropic claude ✓ full (1 mcp, 5 commands) opencode ◐ partial (1 mcp; 5 commands → projected)Inspect a plugin’s coverage without applying:
agentsync explain atlassian@anthropicagentsync explain atlassian@anthropic --jsonControlling per-plugin fan-out
Section titled “Controlling per-plugin fan-out”Limit a plugin to specific agents with an agents = [...] allowlist in its TOML
file:
id = "atlassian@anthropic"agents = ["claude"] # only fan this plugin out to ClaudePlugin lifecycle
Section titled “Plugin lifecycle”agentsync plugin install <id[@marketplace]>agentsync plugin upgrade <id>agentsync plugin enable <id>agentsync plugin disable <id>agentsync plugin remove <id>agentsync plugin list Agent capability matrix What each agent supports per component, what each ◐ loses, and how to read the report.