ai-cli-runtime

AI Runtime

Use this skill only inside the ai:rescue subagent.

Primary helper:

• node "${CLAUDE_PLUGIN_ROOT}/scripts/ai-companion.mjs" task "<raw arguments>"
• Use --model provider:model to select a specific provider and model (e.g., --model codex:gpt-5.4, --model copilot:claude-opus-4.5).

Execution rules:

• The rescue subagent is a forwarder, not an orchestrator. Its only job is to invoke task once and return that stdout unchanged.
• Prefer the helper over hand-rolled git, direct CLI strings, or any other Bash activity.
• Do not call setup, review, adversarial-review, council, status, result, or cancel from ai:rescue.
• Use task for every rescue request, including diagnosis, planning, research, and explicit fix requests.
• You may use the gpt-5-4-prompting skill to rewrite the user's request into a tighter prompt before the single task call.
• That prompt drafting is the only Claude-side work allowed. Do not inspect the repo, solve the task yourself, or add independent analysis outside the forwarded prompt text.
• Leave --effort unset unless the user explicitly requests a specific effort.
• Leave model unset by default. Add --model only when the user explicitly asks for one.
• Default to a write-capable run by adding --write unless the user explicitly asks for read-only behavior or only wants review, diagnosis, or research without edits.

Command selection:

• Use exactly one task invocation per rescue handoff.
• If the forwarded request includes --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.
• If the forwarded request includes --model, pass it through to task as-is (provider:model format is resolved by the companion script).
• If the forwarded request includes --effort, pass it through to task.
• If the forwarded request includes --resume, strip that token from the task text and add --resume-last.
• If the forwarded request includes --fresh, strip that token from the task text and do not add --resume-last.
• --resume: always use task --resume-last, even if the request text is ambiguous.
• --fresh: always use a fresh task run, even if the request sounds like a follow-up.
• task --resume-last: internal helper for "keep going", "resume", "apply the top fix", or "dig deeper" after a previous rescue run.

Safety rules:

• Default to write-capable work in ai:rescue unless the user explicitly asks for read-only behavior.
• Preserve the user's task text as-is apart from stripping routing flags.
• Do not inspect the repository, read files, grep, monitor progress, poll status, fetch results, cancel jobs, summarize output, or do any follow-up work of your own.
• Return the stdout of the task command exactly as-is.
• If the Bash call fails or the AI backend cannot be invoked, return nothing.