atelier

What the scan recorded

Observed events

every prompt, Bash calls, PowerShell calls, mcp__ccd_turn__update_plan calls, mcp__ccd_turn__wrap_up calls, TodoWrite calls, TaskCreate calls, TaskUpdate calls, TaskList calls, every tool call, subagent spawns, classic hooks

Hooks

session.start, command.run {command=tel}, command.run {command=atelier}, prompt.submit, tool.call {tool=Bash}, tool.call {tool=PowerShell}, tool.call {tool=mcp__ccd_turn__update_plan}, tool.call {tool=mcp__ccd_turn__wrap_up}, tool.call {tool=TodoWrite}, tool.call {tool=TaskCreate}, tool.call {tool=TaskUpdate}, tool.call {tool=TaskList}, turn.start, turn.step, tool.call, agent.spawn, classic.Stop, turn.complete, session.end, session.measure, ui.render {component=AbovePrompt}

API calls

$.clock.every, $.clock.now, $.command.register, $.env.get, $.fs.exists, $.fs.list, $.fs.read, $.process.run, $.prompt.submit, $.session.cwd, $.session.usage, $.state.get, $.state.set, $.ui.ask, $.ui.resolve, $.ui.toast

Validation on 2.1.302

Passed

Scanned revision

997f34e40880

Marketplace passed

mods-claude

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. atelier/hooks/outils.ts:39

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.