gemini-cli-runtime

An internal contract describing how Claude Code calls Gemini CLI through a companion script.

In plain words
What is it for?
Running read-only code reviews, adversarial reviews, write-capable tasks, background jobs, status and result checks, cancellation, and setup checks.
Why use it?
It gives the agent one defined way to start reviews, delegate tasks, inspect jobs, and cancel work.

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

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 408 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 $0.00014 $0.00408
Opus 5 $0.00007 $0.00204
Sonnet 5 $0.00003 $0.00082
Haiku 4.5 $0.00001 $0.00041

Measured yesterday against content hash 2f66e59b48c7, 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 CLI Runtime Contract

How to call Gemini

All Gemini CLI operations go through gemini-companion.mjs:

node "${CLAUDE_PLUGIN_ROOT}/scripts/gemini-companion.mjs" <subcommand> [args]

Subcommands

Command Mode Description
review read-only Code review (sandbox mode)
adversarial-review read-only Challenge review (sandbox mode)
task "prompt" write-capable Delegate a coding task
status [id] read-only List jobs or show job details
result [id] read-only Show completed job output
cancel [id] read-only Cancel a running job
setup read-only Check CLI, manage review gate

Flags

  • --model <model> — Override Gemini model
  • --base <ref> — Git base ref for diff (default: HEAD)
  • --background — Run as background job
  • --wait — Wait for completion (foreground)
  • --scope <text> — Review scope description

Background jobs

When --background is passed, the companion script:

  1. Creates a job entry in state
  2. Spawns gemini as a detached process
  3. Returns immediately with job ID
  4. Output streams to a log file

Use status to check progress, result to read output, cancel to kill.

Important

  • NEVER run gemini directly — always go through gemini-companion.mjs
  • Review outputs should be shown verbatim, never summarized
  • Task outputs should be reviewed before applying to the codebase
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 · 14 tokens per session scan A 2f66e59b48c7

Subscribe to this mod's changes

gemini-cli-runtime is a skill published in the GitHub repository spyrae/gemini-plugin-cc (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 408 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 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

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens