gemini-cli-runtime

gemini-cli-runtime is a skill for Claude Code from LovelaceLoom/gemini-plugin-cc. It costs 31 tokens per session (1,057 once invoked), scanned A, original, Apache-2.0.

An internal helper contract for forwarding requests from Claude Code to a companion runtime that wraps Google’s Antigravity command-line tool. It is intended for a specific rescue subagent rather than direct use.

In plain words
What is it for?
Use it when the rescue subagent needs another implementation, debugging, planning, research, or diagnosis pass through the companion runtime.
Why use it?
It gives that subagent a defined way to send one request and apply a 15-minute deadline, reducing the risk of unmanaged or incorrectly routed calls.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; mentions Claude Code; mentions Gemini CLI.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the gemini plugin — 3 skills, 9 commands, 1 agent, 3 hooks shipped together

Good fit Use it when the rescue subagent needs another implementation, debugging, planning, research, or diagnosis pass through the companion runtime.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add LovelaceLoom/gemini-plugin-cc
Claude Code
/plugin install gemini

Made for: Claude Code.

Or install gemini, the plugin that ships this one along with the rest of its 3 skills, 9 commands, 1 agent, 3 hooks.

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/lovelaceloom/gemini-plugin-cc/gemini-cli-runtime/github.svg)](https://agentmods.dev/skills/lovelaceloom/gemini-plugin-cc/gemini-cli-runtime)
Your own site
<a href="https://agentmods.dev/skills/lovelaceloom/gemini-plugin-cc/gemini-cli-runtime"><img src="https://agentmods.dev/badge/skills/lovelaceloom/gemini-plugin-cc/gemini-cli-runtime/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gemini-cli-runtime

Your own site · 80×15
<a href="https://agentmods.dev/skills/lovelaceloom/gemini-plugin-cc/gemini-cli-runtime"><img src="https://agentmods.dev/badge/skills/lovelaceloom/gemini-plugin-cc/gemini-cli-runtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,057 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00031 $0.01057
Opus 5.5 $0.00012 $0.00423
Sonnet 5.5 $0.00006 $0.00211
Haiku 4.5 $0.00003 $0.00106

Measured 1mo ago against content hash 410887790909, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agy Companion Runtime

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

Primary helper:

  • GEMINI_RESCUE_MODE=1 node "${CLAUDE_PLUGIN_ROOT}/scripts/companion.mjs" task "<raw arguments>"

The GEMINI_RESCUE_MODE=1 env var asks the companion runtime to apply a finite default timeout (15 min) to the task call. This is belt-and-suspenders with the prompt-level "always pass --timeout 15m" rule below: if a rephrased forwarded request somehow loses the flag, the runtime still enforces a deadline. Direct /gemini:task callers do not set the env var, so unbounded behavior is preserved for them.

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 agy invocations, 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 explicit fix requests.
  • You may use the gemini-prompting skill to rewrite the user's request into a tighter agy 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.
  • Default to read-only agy behavior. Add --write ONLY when the user explicitly asks for code changes.
  • --write is gated by GEMINI_PLUGIN_ALLOW_WRITE=1 in the environment. If the env var is missing the helper will refuse with exit 2 and a message explaining --dangerously-skip-permissions. Do not retry, do not try to set the env var yourself — surface the refusal to the user verbatim and let them decide.
  • Leave --model unset by default. agy 1.0 binds its model internally and ignores --model, but the flag is still accepted on the companion's CLI for back-compat; passing it produces no behavioral change in agy. Only add --model <name> when the user explicitly requests one (purely informational).

Command selection:

  • Use exactly one task invocation per rescue handoff.
  • Run the Bash call in the foreground (do not set run_in_background: true). The rescue contract is synchronous: the parent agent expects agy's real answer, not a "running in background" stub from Claude Code's Bash tool. Issue #3 was caused by the previous "prefer background for long tasks" guidance, which made the wrapper forward a job-ID stub instead of agy's output. For genuinely long tasks, the user can call /gemini:task --background "..." directly from the main thread.
  • 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 --write or --read-only, pass it through to task.
  • Timeout policy for rescue: task's built-in default is unbounded, which is unsafe for rescue because the parent agent blocks on a single foreground call. If the forwarded request includes --timeout <duration>, pass it through verbatim. If it does NOT include --timeout, you MUST add --timeout 15m to the task call. This bounds rescue against a hung agy process indefinitely stranding the parent agent. Forms accepted: 300s, 5m, 1h, 500ms, or 0 to disable. Users who want unbounded rescue must pass --timeout 0 explicitly. On timeout the helper exits 124 — surface that to the user rather than retrying.
  • Never call purge from this subagent. /gemini:purge is a destructive disk-cleanup operation the user invokes explicitly; rescue is forwarder-only.

Safety rules:

  • Default to read-only agy work in gemini:gemini-rescue unless the user explicitly asks for code changes.
  • 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 agy cannot be invoked, return nothing.

Read the full file on GitHub · 41 lines

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. 1mo ago First seen · 41 lines · 31 tokens per session scan A 410887790909

Subscribe to this mod's changes

gemini-cli-runtime is a skill published in the GitHub repository LovelaceLoom/gemini-plugin-cc (4 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 1,057 once invoked, about $0.0001 per session on Opus 5.5. 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

monday-planning

Suggest a weekly training structure from recent load and deliver the plan.

gtapps/hermitd · 18 tokens

vigil-instrument

Instrument a service with OpenTelemetry — RED metrics, structured logs, distributed tracing, and health checks. Outputs actual code and config, not a plan. Use when asked to "add monitoring", "instrument this", "add logging", "set up tracing", or "observability".

tonone-ai/tonone · 61 tokens

pave-env

Set up local development environments — devcontainers, Docker Compose, one-command setup, dev/prod parity. Use when asked to "set up dev environment", "devcontainer", "docker compose for dev", "local development setup", or "one command to run".

tonone-ai/tonone · 57 tokens

design-system-reference

Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.

wigtn/wigtn-plugins · 43 tokens

boss-briefing

Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.

sehoon787/my-claude · 23 tokens

github-pr-creation

Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…

fvadicamo/dev-agent-skills · 75 tokens