What is gemini-plugin-cc CLAUDE.md?

A set of Claude Code instructions for a marketplace containing two plugins that use Google's Gemini through the Antigravity command-line tool. One provides commands for code work, and the other describes images before Claude reads them.

It is for understanding, maintaining, or extending the Gemini and Gemini-images plugins, including their marketplace registry, commands, agent definitions, and automatic image-reading hook.

It explains how the plugins, commands, hooks, and shared Google login fit together. It also distinguishes actions that only inspect code from the implementation command that edits files.

gemini-plugin-cc CLAUDE.md — Instructions file for coding agents by haunchen: A set of Claude Code instructions for a marketplace…

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 instructions/haunchen/gemini-plugin-cc/claude-md

Clone the repo

git clone --depth 1 https://github.com/haunchen/gemini-plugin-cc

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/haunchen/gemini-plugin-cc/claude-md.svg)](https://agentmods.dev/instructions/haunchen/gemini-plugin-cc/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/haunchen/gemini-plugin-cc/claude-md"><img src="https://agentmods.dev/badge/instructions/haunchen/gemini-plugin-cc/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 4,992 This file is loaded in full into every session.

When invoked 4,992 The same file — it is already loaded in full.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.04992	$0.04992
Opus 5	$0.02496	$0.02496
Sonnet 5	$0.00998	$0.00998
Haiku 4.5	$0.00499	$0.00499

Measured 4d ago against content hash 60cd9fa4bc37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

gemini-plugin-cc CLAUDE.md scanned grade B with 1 finding 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`/gemini:setup` installs them with `agy plugin install <plugin-root>/agy`, landing in `~/.gemini/config/plugins/gemini-agents/`. The agy-side plugin deliberately ships agents only — including `commands/` would make agy c

CLAUDE.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Is

A Claude Code plugin marketplace that reaches Gemini through the Antigravity CLI (agy). Two plugins share the same Google OAuth credentials:

gemini — slash commands for code review, ask, adversarial review, and implementation. Pure Markdown commands + agent definitions, no JS runtime. Everything is read-only except /gemini:implement, which edits files.
gemini-images — PreToolUse hook that replaces image Read calls with Gemini-generated text descriptions, protecting Anthropic's prompt cache.

Everything user-facing stays in Claude Code. agy is only the backend that runs Gemini — the plugins are not installed into agy as skills.

Architecture

Marketplace registry at /.claude-plugin/marketplace.json points at two plugin sources under /plugins/:

.claude-plugin/marketplace.json          # marketplace registry (2 plugins)
plugins/gemini/
  .claude-plugin/plugin.json             # also registers the SessionStart hook
  commands/                              # /gemini:setup, review, ask, adversarial-review, implement
  hooks/check-agent-version.sh           # warns when agy's agents drift from what the plugin ships
  agy/plugin.json                        # agy-side plugin — agents only, no commands
  agy/agents/<name>/agent.md             # system prompts, installed via `agy plugin install`
  README.md
plugins/gemini-images/
  .claude-plugin/plugin.json             # registers PreToolUse hook on Read
  hooks/intercept-image-read.sh          # entry point
  hooks/image-describe.mjs               # resize + agy describe + parallel tesseract OCR
  agy/agents/gemini-image-describe/agent.md
  scripts/doctor.sh                      # dependency check
  README.md

The agent bodies are the primary quality lever — they define reviewer role, output structure, and severity criteria. Eval: custom prompt 10/10 vs bare model 4/10.

Read the full file on GitHub · 235 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.

4d ago First seen · 235 lines · 4,992 tokens per session scan B 60cd9fa4bc37

Subscribe to this mod's changes

gemini-plugin-cc CLAUDE.md is an instructions file published in the GitHub repository haunchen/gemini-plugin-cc (1 stars, last pushed 21d ago), licensed MIT. It adds 4,992 tokens to every session, about $0.0250 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents claude-code claude-code-plugin gemini gemini-cli prompt-caching

AionUi AGENTS.md

AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.

iOfficeAI/AionUi · 1,663 tokens

ccmanager CLAUDE.md

Instructions for kbwo/ccmanager, covering repository guidelines, project structure & module organization, build, test & development commands, coding style & naming conventions and testing guidelines.

kbwo/ccmanager · 595 tokens

gemini-cli-desktop AGENTS.md

Instructions for Piebald-AI/gemini-cli-desktop, a project described as: Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.

Piebald-AI/gemini-cli-desktop · 6 tokens

gemini-plugin-cc CLAUDE.md