antigravity-claude-proxy: Instructions file for Claude Code

CLAUDE.md

antigravity-claude-proxy CLAUDE.md is an instructions file for Claude Code from badrisnarayanan/antigravity-claude-proxy. It costs 623 tokens per session, scanned A, original, MIT.

Project instructions for a Node.js proxy that lets the Claude Code command-line tool use Google’s Cloud Code service through an Anthropic-compatible interface. It covers setup, running modes, account management, quotas, and tests.

In plain words
What is it for?
Use it when developing, testing, debugging, or managing Google accounts for this proxy, including quota strategies and alternate-model fallback.
Why use it?
It explains how requests flow through the proxy and records the commands and options needed to run or debug it correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is badrisnarayanan/antigravity-claude-proxy's own configuration. It tells Claude Code how to work on antigravity-claude-proxy 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 antigravity-claude-proxy configures →

About the project

Antigravity Claude Proxy is a server that translates Anthropic-style API requests into calls to Claude and Gemini models through Google's Antigravity Cloud Code service. It is intended for users who want to use those models with Claude Code or OpenClaw, though the project warns that Google accounts connected to it may be restricted or banned.

badrisnarayanan/antigravity-claude-proxy · 3,948 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to badrisnarayanan/antigravity-claude-proxy. 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/badrisnarayanan/antigravity-claude-proxy/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/badrisnarayanan/antigravity-claude-proxy

Made for: Claude Code.

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 antigravity-claude-proxy CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/badrisnarayanan/antigravity-claude-proxy/claude-md.svg)](https://agentmods.dev/instructions/badrisnarayanan/antigravity-claude-proxy/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/badrisnarayanan/antigravity-claude-proxy/claude-md"><img src="https://agentmods.dev/badge/instructions/badrisnarayanan/antigravity-claude-proxy/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 623 This file is loaded in full into every session.
When invoked 623 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 $0.00623 $0.00623
Opus 5 $0.00311 $0.00311
Sonnet 5 $0.00125 $0.00125
Haiku 4.5 $0.00062 $0.00062

Measured 8d ago against content hash 2666fc10eec2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

antigravity-claude-proxy CLAUDE.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 8d 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.

CLAUDE.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Node.js proxy that exposes an Anthropic-compatible API backed by Google's Cloud Code service, letting Claude Code CLI use Gemini (and Claude) models via Google accounts with multi-account quota management.

Request flow: Claude Code CLI → Express (server.js) → CloudCode client → Antigravity Cloud Code API

Commands

npm install          # installs deps and builds CSS (prepare hook)
npm start            # port 8080
npm run dev          # watch server files
npm run dev:full     # watch CSS + server files

npm start -- --strategy=sticky       # cache-optimized (default is hybrid)
npm start -- --strategy=round-robin  # load-balanced
npm start -- --fallback              # fall back to alternate model on quota exhaustion
npm start -- --dev-mode              # enables debug logging + dev tools (--debug is a legacy alias)

npm run build:css    # compile Tailwind once
npm run watch:css    # watch CSS

npm run accounts:add                 # add Google account via OAuth
npm run accounts:add -- --no-browser # headless/manual code input
npm run accounts:list
npm run accounts:verify

npm test                             # requires server running on port 8080
node tests/run-all.cjs <filter>      # run matching tests only
node tests/test-strategies.cjs       # strategy unit tests (no server needed)

Non-obvious things

CSS: Source is public/css/src/input.css (Tailwind + @apply). Compiled output is public/css/style.css — don't edit the compiled file.

Quota thresholds are stored as fractions (0–0.99) but displayed as percentages in the UI. Three-tier resolution: per-model > per-account > global.

cache_control stripping: Claude Code CLI sends cache_control on content blocks; Cloud Code API rejects them. Stripped at the start of convertAnthropicToGoogle() before any other processing.

Cross-model thinking signatures: Claude and Gemini signatures are incompatible. When switching models mid-conversation, mismatched signatures are dropped. Gemini targets: strict (drop unknown). Claude targets: lenient (let Claude validate).

Read the full file on GitHub · 52 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. 8d ago First seen · 52 lines · 623 tokens per session scan A 2666fc10eec2

Subscribe to this mod's changes

antigravity-claude-proxy CLAUDE.md is an instructions file published in the GitHub repository badrisnarayanan/antigravity-claude-proxy (3,948 stars, last pushed 2d ago), licensed MIT. It adds 623 tokens to every session, about $0.0031 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.

Related

Other instructions, from other repositories

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

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 · 5,153 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

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

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

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