gemini-cli-runtime

An internal helper that forwards requests from a specific Claude Code rescue agent to the Gemini command-line runtime. It passes the runtime's output back unchanged.

In plain words
What is it for?
Forwarding diagnosis, planning, research, or analysis requests to Gemini, with optional selection of Gemini Pro or Flash.
Why use it?
It provides one defined path for rescue requests without adding orchestration or separate analysis in the forwarding agent.

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/dysfunc/ai-plugins-cc/gemini-cli-runtime
Any agent
npx skills add dysfunc/ai-plugins-cc --skill gemini-cli-runtime
Clone the repo
git clone --depth 1 https://github.com/dysfunc/ai-plugins-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 711 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 $0.00711
Opus 5 $0.00010 $0.00356
Sonnet 5 $0.00004 $0.00142
Haiku 4.5 $0.00002 $0.00071

Measured 2d ago against content hash de8a57a29ec3, 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 2d 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, 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 (progemini-2.5-pro, flashgemini-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.
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. 2d ago First seen · 41 lines · 19 tokens per session scan A de8a57a29ec3

Subscribe to this mod's changes

gemini-cli-runtime is a skill published in the GitHub repository dysfunc/ai-plugins-cc (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 711 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

ima2

Use the ima2-gen CLI/server to generate, edit, inspect, and manage local AI image generation jobs.

lidge-jun/ima2-gen · 25 tokens

ima2-front

Frontend implementation skill for ima2 users. Use for any frontend, web UI, or visual implementation work — building, styling, or redesigning pages/components, responsive layouts, motion, component architecture, and production-surface polish. Pairs with ima2-uiux: load it first when design direction is vague; this…

lidge-jun/ima2-gen · 149 tokens

ima2-uiux

Design direction discovery and UX judgment for ima2 users. Use for UI/UX direction and design judgment — vague visual briefs, onboarding, empty/error/loading states, layout vocabulary, typography breaks, favicons, logos, and brand identity choices. Pairs with ima2-front: this skill decides the design direction, then…

lidge-jun/ima2-gen · 118 tokens

local-council-execution

Runs a local council when no external AI providers are configured. Spawns N independent Claude subagents (one per role, blind to each other) that each answer the question from a single assigned lens, then synthesizes their perspectives. Invoked by the ask command via --local, or when the user accepts the local-council…

hex/claude-council · 98 tokens

deep-execution

Executes agent-enhanced council queries by spawning parallel Claude subagents that each query a provider, evaluate response quality, ask follow-up questions, and return structured insights with confidence ratings and blind spot analysis. Invoked when the --agents flag is used or when complex architectural decisions…

hex/claude-council · 61 tokens

council-execution

Executes council queries by running the query pipeline across selected AI providers (Gemini, OpenAI, Grok, Perplexity), displaying formatted responses verbatim, and generating a synthesis of consensus, divergence, and recommendations. Invoked by the ask command during standard (non-agent) council queries.

hex/claude-council · 66 tokens