gemini-claude-plugin: Instructions file for Gemini CLI

GEMINI.md

gemini-claude-plugin GEMINI.md is an instructions file for Gemini CLI from madciapka/gemini-claude-plugin. It costs 1,091 tokens per session, scanned A, original, MIT.

Repository instructions for a plugin that lets Claude Code delegate selected tasks to Gemini CLI, Google's command-line AI tool.

In plain words
What is it for?
Use them to set up the plugin, run rescue or execution tasks, review changes, ask adversarial questions, check job status, retrieve results, and cancel jobs.
Why use it?
They help choose the right command for read-only investigation, background monitoring, code review, or autonomous changes, reducing misrouted work.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is madciapka/gemini-claude-plugin's own configuration. It tells Gemini CLI how to work on gemini-claude-plugin itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gemini-claude-plugin configures →

Reuse

Borrowing it

Nothing to install: this file belongs to madciapka/gemini-claude-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/madciapka/gemini-claude-plugin/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/madciapka/gemini-claude-plugin

Made for: Gemini CLI.

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-claude-plugin GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/madciapka/gemini-claude-plugin/gemini-md.svg)](https://agentmods.dev/instructions/madciapka/gemini-claude-plugin/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/madciapka/gemini-claude-plugin/gemini-md"><img src="https://agentmods.dev/badge/instructions/madciapka/gemini-claude-plugin/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,091 This file is loaded in full into every session.
When invoked 1,091 The same file — it is already loaded in full.
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 $0.01091 $0.01091
Opus 5 $0.00545 $0.00545
Sonnet 5 $0.00218 $0.00218
Haiku 4.5 $0.00109 $0.00109

Measured 7d ago against content hash dffe2b44c0b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

gemini-claude-plugin GEMINI.md 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 7d 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.

GEMINI.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini plugin — how to use it

The google-gemini plugin (/gemini:* slash commands) lets you delegate work to Gemini CLI from inside Claude Code. Three entry points cover three distinct shapes of work.

Pick the entry point first

You want… Use
Read-only diagnosis or a single-shot research answer /gemini:rescue
Passive observation of a long-running Gemini job (events stream back) /gemini:rescue-stream
Autonomous execution of a planned subtask, with self-healing + structured handoff /gemini:execute
Plain "review my diff" /gemini:review
Review with steering / adversarial questions /gemini:adversarial-review <focus>
Background job control /gemini:status · /gemini:result · /gemini:cancel
Verify install + auth /gemini:setup

Three rules that prevent misroutes

  1. /gemini:rescue is read-only by default. It runs Gemini under --approval-mode plan. If the user wants Gemini to actually change files, that is /gemini:execute, not rescue --yolo (don't reach for the rescue with a yolo flag — execute is the right shape and carries the executor envelope).
  2. /gemini:execute is write-capable and autonomous by default (--yolo --sandbox, background+stream). Don't use it for review (that's /gemini:review or /gemini:adversarial-review) or research (that's /gemini:rescue). Don't use it without a real plan; vague asks produce vague execution.
  3. Foreground vs background:
    • /gemini:rescue defaults to foreground; add --background for unclear-scope investigations.
    • /gemini:execute defaults to background+stream; add --wait only for tight, bounded tasks.
    • /gemini:rescue-stream is always streamed.

Don't touch unless explicitly asked

  • --model — leave unset. Gemini picks its own default.
  • --yolo (rescue only) — only when the user explicitly wants writes via rescue. Prefer /gemini:execute instead.
  • --no-sandbox (execute only) — only when the task genuinely needs host access (rare).

Read the full file on GitHub · 62 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. 7d ago First seen · 62 lines · 1,091 tokens per session scan A dffe2b44c0b3

Subscribe to this mod's changes

gemini-claude-plugin GEMINI.md is an instructions file published in the GitHub repository madciapka/gemini-claude-plugin (8 stars, last pushed 4mo ago), licensed MIT. It adds 1,091 tokens to every session, about $0.0055 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 instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens