graphos-agent-mods

What it hooks into

From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.

Events

session.startclassic.SessionStartclassic.FileChangedcommand.runtool.calltool.checksession.endui.faultui.render

API calls

$.agent.list$.clock.after$.clock.every$.clock.now$.clock.sleep$.command.register$.fs.read$.fs.write$.mcp.call$.model.complete$.process.run$.prompt.fill$.prompt.read$.session.version$.state.get$.state.set$.store.delete$.store.get$.store.set$.tool.check$.tool.list$.ui.close$.ui.log$.ui.open$.ui.panes$.ui.resolve$.ui.status

Draws

ToolUseToolGroupToolResultSpinnerPane

Can see

classic hooks/"^mcp__claude_ai_GraphOS_Agent_Services__execute$"/ calls

Reach

level 3 of 3 other: $.prompt.readother: $.state.getother: $.state.setother: $.tool.checkother: $.tool.listMCP serversruns processeswrites filesdrives Claudewrites the prompt boxreads filespersists statedraws