Skip to content
Back to skills

Gemini Cli Runtime

ASecurity

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

  • 4 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added May 30, 2026
ai-agentsgobashnodegit

Works with

  • claude code
  • cli

Security analysis

A100/100

Scanned May 30, 2026

npx -y skills add dysfunc/ai-plugins-cc --skill gemini-cli-runtime --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Gemini Cli Runtime?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Gemini Cli Runtime
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/dysfunc-gemini-cli-runtime/badge)](https://www.skillsdirectory.com/skills/dysfunc-gemini-cli-runtime)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

SKILL.md
---
name: gemini-cli-runtime
description: Internal helper contract for calling the gemini-companion runtime from Claude Code
user-invocable: false
---

# Gemini Runtime

Use this skill only inside the `gemini:gemini-rescue` subagent.

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:gemini-rescue`.
- Use `task` for every rescue request, including diagnosis, planning, research, and analysis.
- 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 the model unset by default. Add `--model` only when the user explicitly asks for one.
- Map `pro` to `--model gemini-2.5-pro`.
- Map `flash` to `--model gemini-2.5-flash`.
- The Gemini plugin does not have an `--effort` or `--write` flag. The Gemini CLI runs read-only via headless `-p` invocation, so file changes are the main Claude thread's responsibility, not Gemini's.

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`, normalize aliases (`pro` → `gemini-2.5-pro`, `flash` → `gemini-2.5-flash`) and 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", or "dig deeper" after a previous rescue run. The plugin prepends the prior per-job transcript to the new prompt; long transcripts are truncated and `/gemini:result` flags when truncation occurred.

Safety rules:
- 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.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.