session-radar

What the scan recorded

Observed events

Agent calls, subagent spawns, every tool call, Skill calls, every skill, Bash calls, Monitor calls, TodoWrite calls, TaskCreate calls, TaskUpdate calls, ExitPlanMode calls, classic hooks, every prompt, CronCreate calls, CronDelete calls, ScheduleWakeup calls, TaskStop calls

Hooks

session.start, command.run {command=radar}, ui.close, session.measure, turn.step, tool.call {tool=Agent}, agent.spawn, tool.call, tool.call {tool=Skill}, skill.prompt, tool.call {tool=Bash}, tool.call {tool=Monitor}, tool.call {tool=TodoWrite}, tool.call {tool=TaskCreate}, tool.call {tool=TaskUpdate}, tool.call {tool=ExitPlanMode}, classic.PostToolUse, classic.Notification, prompt.submit, classic.SubagentStop, classic.Stop, tool.call {tool=CronCreate}, tool.call {tool=CronDelete}, tool.call {tool=ScheduleWakeup}, tool.call {tool=TaskStop}, session.receive, session.append, ui.render {component=Pane, requestId=session-radar}

API calls

$.agent.list, $.clock.every, $.clock.now, $.command.register, $.env.get, $.fs.read, $.fs.stat, $.process.run, $.session.cwd, $.session.model, $.session.usage, $.state.get, $.state.set, $.tool.call, $.ui.close, $.ui.copy, $.ui.open, $.ui.panes, $.ui.resolve, $.ui.toast

Validation on 2.1.304

Passed

Scanned revision

97e3731003f3

Marketplace passed

claude-mods

UI rewrite review

UI hook source contains control-character strings. Review any values passed to next() as rewritten props.text; the scanner does not trace whether these strings reach that call. mods/session-radar/hooks/lib.ts:122

These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. What a mod can access and how the scan works.