agent-radar

What the scan recorded

Observed events

every prompt, subagent spawns, every tool call

Hooks

session.start, command.run {command=canvas}, prompt.submit, command.run {command=radar}, agent.spawn, tool.call, turn.complete, ui.press, ui.input, ui.render {component=Pane, requestId=agent-radar}

API calls

$.agent.list, $.clock.every, $.clock.now, $.command.register, $.env.get, $.fs.read, $.fs.stat, $.fs.write, $.http.fetch, $.model.complete, $.model.fork, $.process.run, $.prompt.submit, $.session.cwd, $.session.id, $.state.get, $.state.set, $.tool.call, $.ui.open, $.ui.resolve, $.ui.status, $.ui.toast

Validation on 2.1.312

Passed

Scanned revision

d9c1182150a4

Marketplace passed

agent-radar

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. hooks/logic.ts:91

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.