@after.math/aftermath@0.6.0
Post-failure recovery skill for AI coding agents: stop, revert cheap damage, return to last-known-good. Project-aware destructive guards, forward-edit freeze, checkpoints, and host parity for OpenCode, Claude Code, and Codex.
AI security review
scanned · by lpm-firewall-aiThe postinstall automatically wires the package’s own agent extension into project or user agent configurations without a separate setup request. This meets the warning category for automatic install-time setup of an extension; the inspected behavior does not show a broader agent-control change or another attack.