lidguard-product-runtimelisted

# LidGuard Product Runtime ## Overview Use this skill as the lightweight entry point for LidGuard runtime behavior. For detailed work, load only the narrow runtime skill that matches the task. - Power management, lid policy, suspend eligibility, and Emergency Hibernation: read `.codex/skills/lidguard-power-runtime/SKILL.md`. - Active session lifecycle, soft-locking, transcript activity, process watching, runtime cleanup, and session-end webhook semantics: read `.codex/skills/lidguard-session-runtime/SKILL.md`. - CLI command routing, settings defaults, permission commands, examples, suspend history, and failure modes: read `.codex/skills/lidguard-cli-runtime/SKILL.md`. - Regular MCP server tools and model-managed Provider MCP runtime behavior: read `.codex/skills/lidguard-mcp-runtime/SKILL.md`. - Provider hook installation, provider-specific payloads, and provider deployment behavior: read `.codex/skills/lidguard-provider-integrations/SKILL.md`. ## Product Goal LidGuard is a Windows-first utility with systemd/logind Linux support and macOS support for long-running local AI coding agents such as Codex, Claude Code, GitHub Copilot CLI, and OpenCode. The goal is to keep the supported local system awake while at least one tracked agent session still needs protection, then restore the user's original power policy after the session ends or becomes suspend-eligible. - Agent sessions start through provider hooks or Provider MCP tools. - LidGuard detects and tracks active sessio