What is claude-gemini-bridge CLAUDE.md?

Documentation and working instructions for Claude-Gemini Bridge, a hook system that connects Claude Code with Google Gemini for large code-analysis tasks. It describes how tool calls are intercepted, evaluated, delegated, cached, and logged.

Use it when developing, reviewing, or maintaining the Claude-Gemini Bridge repository and its hooks, delegation logic, path conversion, caching, or debugging systems.

It explains how the bridge decides when to send complex analysis to Gemini while Claude Code continues managing the conversation. This helps developers understand the project’s architecture and troubleshoot its behavior.

How tkaufmann/claude-gemini-bridge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tkaufmann/claude-gemini-bridge. 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/tkaufmann/claude-gemini-bridge/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tkaufmann/claude-gemini-bridge

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tkaufmann/claude-gemini-bridge/claude-md/github.svg)](https://agentmods.dev/instructions/tkaufmann/claude-gemini-bridge/claude-md)

Your own site

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

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tkaufmann/claude-gemini-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/tkaufmann/claude-gemini-bridge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,298 This file is loaded in full into every session.

When invoked 1,298 The same file — it is already loaded in full.

Security scan D 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.01298	$0.01298
Opus 5.5	$0.00519	$0.00519
Sonnet 5.5	$0.00260	$0.00260
Haiku 4.5	$0.00130	$0.00130

Measured 2mo ago against content hash 5025483bec29, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

claude-gemini-bridge CLAUDE.md scanned grade D with 2 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 2mo 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.

- **Hook not executing**: Check `~/.claude/settings.json` configuration

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Cache issues**: Clear cache with `rm -rf cache/gemini/*`

CLAUDE.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 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 the Claude-Gemini Bridge repository.

Project Overview

The Claude-Gemini Bridge is an intelligent hook system that seamlessly integrates Claude Code with Google Gemini for large-scale code analysis tasks. When Claude Code encounters complex analysis requests, the bridge automatically delegates appropriate tasks to Gemini while maintaining Claude's control over the conversation flow.

Architecture

Core Components

Hook System: Uses Claude Code's PreToolUse hooks to intercept tool calls
Path Converter: Translates Claude's @ notation to absolute file paths
Decision Engine: Intelligently determines when to delegate tasks to Gemini
Caching Layer: Avoids redundant API calls with content-aware caching
Debug System: Comprehensive logging and performance monitoring

How It Works

Interception: Hook catches Claude's tool calls (Read, Glob, Grep, Task)
Analysis: Decision engine evaluates file count, size, and task complexity
Delegation: Large or complex tasks are sent to Gemini for processing
Integration: Gemini's analysis is seamlessly returned to Claude
Fallback: Failed delegations continue with normal Claude execution

Usage Patterns

Automatic Delegation Triggers

The bridge delegates to Gemini when:

Token Limit: Content exceeds ~50k tokens (~200KB, optimized for Claude's 200k context)
Multi-File Tasks: ≥3 files for Task operations (configurable)
Safety Limits: Content must be ≤10MB and ≤800k tokens for Gemini processing
File Exclusions: Automatically excludes sensitive files (*.secret, *.key, *.env, etc.)

Configuration

Key settings in hooks/config/debug.conf:

# Delegation thresholds (optimized for Claude 200k context)
MIN_FILES_FOR_GEMINI=3          # Delegate Task operations with ≥3 files
MIN_FILE_SIZE_FOR_GEMINI=5120   # Minimum 5KB total size
MAX_TOTAL_SIZE_FOR_GEMINI=10485760  # Maximum 10MB total size

# Debug and performance
DEBUG_LEVEL=2                   # 0=off, 1=basic, 2=verbose, 3=trace
DRY_RUN=false                   # Test mode without Gemini calls

Read the full file on GitHub · 175 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.

2mo ago First seen · 175 lines · 1,298 tokens per session scan D 5025483bec29

Subscribe to this mod's changes

claude-gemini-bridge CLAUDE.md is an instructions file published in the GitHub repository tkaufmann/claude-gemini-bridge (406 stars, last pushed 1y ago), licensed MIT. It adds 1,298 tokens to every session, about $0.0052 per session on Opus 5.5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents

claude-gemini-bridge CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-gemini-bridge CLAUDE.mdtkaufmann/claude-gemini-bridge	Instructions file	406	1y ago	MIT	D	1,298	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-gemini-bridge: Instructions file for Claude Code