The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform local dry-runs and CLI checks to verify model configuration before committing changes to the environment file.- [COMMAND_EXECUTION]: The skill provides documentation for executing a local script located at ~/.claude/skills/pstack/scripts/spawn-codex-worker.sh to facilitate task delegation.- [SAFE]: The skill manages a configuration file within the user's home directory (~/.config/uni-pstack/models.env) to store non-sensitive model selection and reasoning preferences.

setup-pstack