Support and limitations#
Platform |
Pre-flight deny |
Start/stop detection |
Desktop notification |
|---|---|---|---|
Linux |
yes |
yes |
|
macOS |
yes |
yes |
|
Windows |
yes |
yes |
PowerShell toast (best-effort, untested) |
Claude Code’s three layers and Codex’s native pre-flight spawn_agent denial have been exercised with synthetic payloads on Linux.
Known limits#
SubagentStopis detection, not prevention; that agent’s tokens have already been spent.Dynamic model options can escape workflow static analysis, then surface at stop-time.
A launch remains unobservable and therefore fails open when it has no explicit model, no resolvable on-disk definition, no readable parent transcript, and no remembered session model from the last six hours.
Codex provides the native pre-flight spawn_agent event, but not Claude-compatible start/stop lifecycle events; its runtime-only launches have no notification backstop.
A missing hook script blocks the matched Claude Code call; uninstall through the supported command instead of deleting files by hand.
New model families remain ungated until
superheavy_patternincludes them.Grant locking is advisory on network filesystems.
Notification throttling groups repeated detections by subject and session.