nerv

What the scan recorded

Observed events

every prompt, subagent spawns, every tool call

Hooks

session.start, session.end, command.run {command=nerv}, ui.scroll {requestId=nerv}, ui.close {id=nerv}, prompt.submit, turn.start, turn.step, turn.complete, session.measure, agent.spawn, tool.call, ui.render {component=Pane}, ui.render {component=Spinner}, ui.render {component=ToolUse}, ui.render {component=ToolGroup}, ui.render {component=UserMessage}, ui.render {component=AssistantMessage}, ui.render {component=TurnDuration}, ui.render {component=InfoNotice}, ui.render {component=AbovePrompt}

API calls

$.clock.every, $.clock.sleep, $.command.register, $.command.run, $.env.get, $.fs.list, $.fs.read, $.fs.stat, $.fs.write, $.http.fetch, $.process.run, $.session.cwd, $.session.id, $.session.model, $.session.usage, $.settings.read, $.store.get, $.store.set, $.ui.ask, $.ui.blit, $.ui.close, $.ui.invalidate, $.ui.log, $.ui.open, $.ui.panes, $.ui.resolve, $.ui.toast

Validation on 2.1.302

Passed

Scanned revision

0da75ac9d34a

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/register.ts:438, hooks/register.ts:451, hooks/register.ts:579

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. How the scan works.