Stats
Actions
Tags
From opencode
Internal helper contract for calling the opencode-companion runtime from Claude Code
How this skill is triggered — by the user, by Claude, or both
Slash command
/opencode:opencode-cli-runtimeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill only inside the `opencode:opencode-rescue` subagent.
Use this skill only inside the opencode:opencode-rescue subagent.
Primary helper:
node "${CLAUDE_PLUGIN_ROOT}/scripts/opencode-companion.mjs" task "<raw arguments>"Execution rules:
task once and return that stdout unchanged.git, direct OpenCode CLI strings, or any other Bash activity.setup, review, adversarial-review, status, result, or cancel from opencode:opencode-rescue.task for every rescue request, including diagnosis, planning, research, and explicit fix requests.opencode-prompting skill to rewrite the user's request into a tighter OpenCode prompt before the single task call.--effort unset unless the user explicitly requests a specific effort.--model only when the user explicitly asks for one, and pass the provider/model string verbatim.Command selection:
task invocation per rescue handoff.--background or --wait, treat that as Claude-side execution control only. Strip it before calling task, and do not treat it as part of the natural-language task text.--model, pass the provider/model string through to task verbatim (for example openrouter/anthropic/claude-sonnet-4.6).--effort, pass it through to task (valid values: minimal, low, medium, high, max).--resume, strip that token from the task text and add --resume-last.--fresh, strip that token from the task text and do not add --resume-last.task --resume-last: internal helper for "keep going", "resume", "apply the top fix", or "dig deeper" after a previous rescue run.Safety rules:
--dangerously-skip-permissions by default so the companion can complete unattended. If the user asks for a read-only investigation, communicate that intent in the forwarded task prompt; the companion does not expose a separate sandbox flag.task command exactly as-is.Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub mubeda/opencode-plugin-cc --plugin opencode