What is cc-copilot-bridge CLAUDE.md?

Project instructions for a wrapper that switches Claude Code between Anthropic’s service, GitHub Copilot, and local Ollama models.

Use them when working on provider switching, Copilot proxy connections, local Ollama support, port checks, MCP profiles, or session tracking in that project.

They explain the project’s scripts, provider setup, health checks, model-specific connections, and session logging so changes can follow the repository’s conventions.

How FlorianBruniaux/cc-copilot-bridge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to FlorianBruniaux/cc-copilot-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/FlorianBruniaux/cc-copilot-bridge/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/FlorianBruniaux/cc-copilot-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/florianbruniaux/cc-copilot-bridge/claude-md.svg)](https://agentmods.dev/instructions/florianbruniaux/cc-copilot-bridge/claude-md)

Your own site

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

Per session 9,436 This file is loaded in full into every session.

When invoked 9,436 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. ✓ AI security review Sonnet 5 · 7 Sept 2026 📄 Read the review

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	$0.09436	$0.09436
Opus 5	$0.04718	$0.04718
Sonnet 5	$0.01887	$0.01887
Haiku 4.5	$0.00944	$0.00944

Measured 8d ago against content hash 0efea76d687d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

cc-copilot-bridge 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 · 898 lines

How it starts

The opening of the file, as written. The whole thing — 898 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.

Project Overview

claude-switch is a multi-provider wrapper for Claude Code CLI that enables seamless switching between:

Anthropic Direct: Official API, best quality
GitHub Copilot: Free with Copilot Pro+ via copilot-api proxy
Ollama Local: 100% private, offline capable

The project consists of 3 main bash scripts and extensive documentation for optimal usage.

Core Scripts

1. claude-switch (Main Script)

Location: ~/bin/claude-switch (installed via install.sh)

Key Functions:

_run_direct(): Anthropic API direct connection
_run_copilot(): GitHub Copilot via copilot-api proxy (localhost:4141)
_run_ollama(): Local Ollama models via localhost:11434
_check_port(): Health checks before launching providers
_get_mcp_flags(): Dynamic MCP profile selection based on model
_session_start()/_session_end(): Session logging with durations

Environment Variables Set:

# Copilot mode
ANTHROPIC_BASE_URL="http://localhost:4141"
ANTHROPIC_AUTH_TOKEN="<PLACEHOLDER>"  # copilot-api ignores this value
ANTHROPIC_MODEL="${COPILOT_MODEL:-claude-sonnet-4-6}"
DISABLE_NON_ESSENTIAL_MODEL_CALLS="1"

# Ollama mode
ANTHROPIC_BASE_URL="http://localhost:11434"
ANTHROPIC_AUTH_TOKEN="<PLACEHOLDER>"  # Ollama ignores this value

Model Switching:

Default Copilot model: claude-sonnet-4-6 (depuis v1.6.0)
Override via COPILOT_MODEL env var (40+ models supported)
Default Ollama model: devstral-small-2 (configurable via OLLAMA_MODEL)
Backup Ollama model: ibm/granite4:small-h (long context, 70% less VRAM)

2. install.sh (Installation)

Auto-installer that:

Creates ~/bin/ directory if needed
Downloads claude-switch script
Adds shell aliases to ~/.zshrc or ~/.bashrc
Creates ~/.claude/ directory for logs

Aliases Created:

30+ aliases for all providers and models (Claude, GPT, Codex, Gemini, Ollama).

Read the full file on GitHub · 898 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.

8d ago First seen · 898 lines · 9,436 tokens per session scan E 0efea76d687d

Subscribe to this mod's changes

cc-copilot-bridge CLAUDE.md is an instructions file published in the GitHub repository FlorianBruniaux/cc-copilot-bridge (58 stars, last pushed 5mo ago), licensed MIT. It adds 9,436 tokens to every session, about $0.0472 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.

Building agents Claude Code Cost Optimization anthropic-api cli-tools copilot-api offline-ai

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

cc-copilot-bridge: Instructions file for Claude Code