Resilient Coding Agent

Long-running coding tasks are vulnerable to interruption: orchestrator restarts, process crashes, network drops. This skill decouples Claude Code from the orchestrator using tmux, enabling fire-and-forget execution with automatic resume on interruption. The orchestrator specifies which model to use; the skill handles session lifecycle, crash recovery, and output capture.

Trust Model

This skill runs Claude Code with --dangerously-skip-permissions and dispatches commands into tmux via send-keys. These are required capabilities, not bugs — the whole point is fire-and-forget execution with no human in the loop to approve prompts. Read this section before installing so you understand exactly what you are enabling.

What this skill can do at runtime:

• Execute Claude Code without any permission prompts. Claude will read, write, and run bash commands in the project directory without asking. If a coding agent with full filesystem and shell access inside your project is not acceptable, do not install this skill.
• Create and kill tmux sessions whose names match claude-<task-name>. If you run other tmux sessions with that prefix, the monitor's cleanup path could terminate them.
• Dispatch bash commands into tmux via send-keys. The orchestrator controls what gets dispatched, so a compromised or buggy orchestrator can use this skill to run arbitrary bash in the project directory.
• Write files to a secure temp directory (mktemp -d, chmod 700) and to the project directory via Claude Code.
• Fire openclaw system event notifications (fire-and-forget, failures swallowed).

What this skill does NOT do: