gemini

A Claude Code skill that calls Google's Gemini command-line tool so another AI model can participate in the coding workflow.

In plain words
What is it for?
It sends prompts to Gemini, can resume or list sessions, and supports default, automatic-edit, planning, and full-auto approval modes.
Why use it?
It supports a multi-model workflow and defines how edits, read-only plans, approvals, and previous sessions are handled.

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/ggombee/code-forge/gemini
Any agent
npx skills add ggombee/code-forge --skill gemini
Clone the repo
git clone --depth 1 https://github.com/ggombee/code-forge

Made for: Claude Code, Codex.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 431 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 $0.00031 $0.00431
Opus 5 $0.00015 $0.00216
Sonnet 5 $0.00006 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured yesterday against content hash 4fcdd2b5d68c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gemini 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.

archive/skills/gemini/SKILL.md · 65 lines

What it actually says

Gemini Skill

Claude Code에서 Google Gemini CLI를 활용한 AI 협업


설정

  • 기본 모델: gemini-3.1-pro-preview
  • 폴백: gemini-2.5-progemini-2.5-flash
  • 사용자가 요청하지 않으면 모델 선택 묻지 않음

핵심 규칙

항상 -p/--prompt 플래그 사용 (v0.29.0+에서 위치 인자는 인터랙티브 모드 진입)


승인 모드

모드 용도
default 편집 전 확인 필요
auto_edit 사용자가 파일 수정 명시적 요청 시
plan 읽기 전용
yolo 전체 자동 승인 (사전 동의 필요)

세션 관리

  • 이전 세션 재개: -r latest
  • 세션 목록: --list-sessions

평가 원칙

Gemini를 동료로 취급 (권위자 아님):

  • 확신 있으면 자신의 지식 신뢰
  • 불일치 시 독립적 리서치
  • 지식 컷오프 한계 인지

에러 해결

에러 해결
미설치 npm i -g @google/gemini-cli
인증 실패 gemini login
Rate limit 무료 60req/min, 대기 후 재시도
모델 없음 폴백 체인 사용
액세스 거부 프리뷰 기능 비활성화
세션 없음 --list-sessions로 확인
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 · 65 lines · 31 tokens per session scan A 4fcdd2b5d68c

Subscribe to this mod's changes

gemini is a skill published in the GitHub repository ggombee/code-forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 431 once invoked, about $0.0002 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 2026-08-30.