gemini-cli-runtime

An internal helper for sending requests from Claude Code to the Gemini runtime, a separate system that performs tasks.

In plain words
What is it for?
It is for forwarding diagnosis, planning, research, or fix requests to Gemini through a single command.
Why use it?
It keeps the rescue agent focused on forwarding one request and returning the result instead of inspecting or solving the task itself.

Skill for Claude CodeCodex

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/arcobaleno64/agy-plugin-cc/gemini-cli-runtime
Any agent
npx skills add arcobaleno64/agy-plugin-cc --skill gemini-cli-runtime
Clone the repo
git clone --depth 1 https://github.com/arcobaleno64/agy-plugin-cc

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 929 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 $0.00929
Opus 5 $0.00010 $0.00464
Sonnet 5 $0.00004 $0.00186
Haiku 4.5 $0.00002 $0.00093

Measured yesterday against content hash f21f77f520e5, 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 yesterday.

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 · 52 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 CLI strings, git operations, or any other Bash activity.
  • Do not call 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 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.
  • Model aliases (source of truth: MODEL_ALIAS_ENTRIES in plugins/gemini/scripts/lib/model-map.mjs): flash / flash3gemini-3-flash-preview, pro / pro3gemini-3.1-pro-preview, lite3gemini-3.1-flash-lite, flash25gemini-2.5-flash, pro25gemini-2.5-pro, lite / fastgemini-2.5-flash-lite.
  • Read-only is the default; add --write only when the user explicitly asked for 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.
  • If the forwarded request includes --model, normalize aliases and pass it through.
  • If the forwarded request includes --effort, pass it through to task.
  • If the forwarded request includes --timeout <seconds>, pass it through to task. Whole seconds, 30 to 3600. It bounds both the run's duration and the amount of output it can emit before being killed.
  • --effort accepted values: Gemini engine accepts none, minimal, low, medium, high, xhigh; AGY engine accepts only low, medium, high.
  • --resume: add --resume-last, even if the request text is ambiguous.
  • --fresh: use a fresh task run, do not add --resume-last.
  • task --resume-last: for "keep going", "resume", "apply the top fix", or "dig deeper".

Engine routing:

  • Gemini CLI and AGY are both first-class supported engines; only the selected engine's CLI is required.
  • Default engine: credential-gated auto-detection (selects Gemini if installed and authenticated with valid credentials, otherwise AGY).
  • Force AGY: add --engine agy.
  • Force Gemini CLI: add --engine gemini.
  • Note for AGY engine: --model takes an exact model ID from agy models or --effort accepts low, medium, or high; the two cannot be combined, and Gemini model aliases are rejected for AGY.

Safety rules:

  • Read-only is the default in gemini:gemini-rescue; add --write only when the user explicitly asked for edits.
  • 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 engine 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. yesterday First seen · 52 lines · 19 tokens per session scan A f21f77f520e5

Subscribe to this mod's changes

gemini-cli-runtime is a skill published in the GitHub repository arcobaleno64/agy-plugin-cc (10 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 929 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