Post-hoc audit of autopilot execution fidelity. Analyzes OpenCode session traces to evaluate how faithfully the autopilot workflow executed against its contract, surfacing errors, friction, and drift with traceable evidence anchors. Use when the user wants to audit an autopilot run, analyze session quality, check if…
Set up OpenCode permission rules to guard against dangerous git commands (push, reset --hard, clean, branch -D, checkout/restore .) before they execute. Use when user wants to prevent destructive git operations, add git safety guardrails, or block dangerous git commands.
Create OpenCode plugin scaffolding from scratch or fix existing projects to conform to plugin conventions. Supports npm packages (publishable) and local auto-discovered plugins. Use when the user wants to create a new opencode plugin, scaffold a plugin project, fix/align an existing plugin project, or mentions plugin…
Create, modify, and improve agent skills with iterative eval-driven development. Use when user wants to create a new skill from scratch, edit or optimize an existing skill, run evals to test skill performance, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering…