# Gemini CLI Runtime

> Internal helper contract for calling the Gemini-backed gemini-companion runtime from Claude Code

- Skill: `bytelandtechnology/gemini-cli-runtime` (Agent Skill)
- Install (CLI): `npx skillmds@latest add bytelandtechnology/gemini-cli-runtime`
- Raw SKILL.md: https://api.skillmd.com/api/skills/bytelandtechnology/gemini-cli-runtime/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: bytelandtechnology (https://skillmd.com/u/bytelandtechnology)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/bytelandtechnology/gemini-cli-runtime

---


# Gemini Runtime

Use this skill only inside the `gemini:rescue` subagent.
Do not use it for `--stream`; the parent `/gemini:rescue` command handles streaming directly.

Primary helper:

- `node "${CLAUDE_PLUGIN_ROOT}/scripts/gemini-companion.mjs" task "<raw arguments>"`

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 Gemini CLI strings, or any other Bash activity.
- Do not call `setup`, `review`, `adversarial-review`, `status`, `result`, or `cancel` from `gemini:rescue`.
- Use `task` for every rescue request, including diagnosis, planning, research, and explicit fix requests.
- You may use the `gemini-prompting` skill to rewrite the user's request into a tighter Gemini 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.
- Map `spark` to `--model flash`.
- Default to a write-capable Gemini 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.
- This skill is only for non-stream rescue handoffs. When the user asks for `--stream`, the parent command bypasses the subagent so incremental stdout stays live.
- 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.
- The parent command handles `--stream` directly. Do not try to recreate that path inside this subagent skill.
- If the forwarded request includes `--model`, normalize `spark` to `flash` and pass it through to `task`.
- 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.
- `--effort`: accepted values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`.
- `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 Gemini work in `gemini: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 Gemini cannot be invoked, return nothing.