opencode-controller
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local commands for the 'opencode' utility (e.g.,
opencode models openrouter --pure). These commands are used for configuration verification and session management within the user's local environment. - [SAFE]: The skill uses official/expected model aliases and strictly prohibits switching to unverified providers or raw model IDs, enforcing a narrow and predictable execution scope.
- [SAFE]: All instructions focus on workflow management (Plan vs Build modes) and session reuse, adhering to best practices for agent-assisted coding without introducing external dependencies or remote script execution.
Audit Metadata