gemini-cli-runtime

gemini-cli-runtime is a skill for Claude Code, Codex from madciapka/gemini-claude-plugin. It costs 19 tokens per session (712 once invoked), scanned A, original, MIT.

A helper for sending one request to the Gemini companion runtime from a Claude Code rescue worker.

In plain words
What is it for?
Use it for read-only diagnosis, planning, research, or fix requests that need to be passed to Gemini.
Why use it?
It gives that rescue worker a defined way to forward requests without adding its own investigation or decisions.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the gemini plugin — 3 skills, 9 commands, 3 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/madciapka/gemini-claude-plugin/gemini-cli-runtime
Any agent
npx skills add madciapka/gemini-claude-plugin --skill gemini-cli-runtime
Clone the repo
git clone --depth 1 https://github.com/madciapka/gemini-claude-plugin

Made for: Claude Code, Codex.

Or install gemini, the plugin that ships this one along with the rest of its 3 skills, 9 commands, 3 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for gemini-cli-runtime

README.md
[![agentmods](https://agentmods.dev/badge/skills/madciapka/gemini-claude-plugin/gemini-cli-runtime.svg)](https://agentmods.dev/skills/madciapka/gemini-claude-plugin/gemini-cli-runtime)
Your own site
<a href="https://agentmods.dev/skills/madciapka/gemini-claude-plugin/gemini-cli-runtime"><img src="https://agentmods.dev/badge/skills/madciapka/gemini-claude-plugin/gemini-cli-runtime.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 712 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00712
Opus 5 $0.00010 $0.00356
Sonnet 5 $0.00004 $0.00142
Haiku 4.5 $0.00002 $0.00071

Measured 5d ago against content hash 1e94e5f2ddf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gemini-cli-runtime scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/gemini/skills/gemini-cli-runtime/SKILL.md · 41 lines

What it actually says

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, tail, or cancel from gemini: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 --model unset unless the user explicitly requests a specific model.
  • Default to --read-only (Gemini in plan approval mode, no writes, no sandbox) when the user asked for review, diagnosis, research, or "look at" work without an explicit request to apply fixes.
  • For explicit fix or implementation requests, default to a write-capable run (no --sandbox, no --read-only).
  • If the user asks for --yolo, pass it through. This enables auto-accept of all actions and is mutually exclusive with --read-only; if both are present, --read-only wins.
  • If the user asks for --sandbox, pass it through. This enables sandbox mode and is ignored when --read-only is set.

Command selection:

  • Use exactly one task invocation per rescue handoff.
  • If the forwarded request includes --background, --wait, or --stream, treat them as Claude-side execution controls.
    • --background → run task --background and return the queued-launch payload.
    • --stream → only used by the gemini:rescue-stream flow. Forward --stream through to task.
    • --wait → run foreground (the default). Strip the flag before forwarding the natural-language task text.
  • If the forwarded request includes --model, pass it through to task.

Safety rules:

  • Read-only by default for review/diagnosis/research; write-capable only for explicit fix/implementation requests.
  • 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, tail logs, cancel jobs, summarize output, or do any follow-up work of your own — except inside the streaming forwarder (gemini:gemini-rescue-stream), which is required to attach Monitor to the events file the helper prints.
  • Return the stdout of the task command exactly as-is.
  • If the Bash call fails or Gemini cannot be invoked, return nothing.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 41 lines · 19 tokens per session scan A 1e94e5f2ddf9

Subscribe to this mod's changes

gemini-cli-runtime is a skill published in the GitHub repository madciapka/gemini-claude-plugin (8 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 712 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens