Running Claude Code Via Litellm Copilot

Routes Claude Code through a local LiteLLM proxy to hit GitHub Copilot instead of Anthropic's API, cutting direct spend while keeping your existing workflow. Generates the config.yaml with proper github_copilot provider routing, sets up ANTHROPIC_BASE_URL overrides, and walks through GitHub's device auth flow when LiteLLM first connects. Handles the common gotchas like model name mismatches between your ANTHROPIC_MODEL env var and LiteLLM's model_name, plus debugging when requests never reach the proxy or Copilot throws 401s. It's a technical workaround that works but isn't officially blessed by GitHub.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.: 6
skills.sh installs: 520.2K
GitHub stars: 79
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add xixu-me/skills --skill running-claude-code-via-litellm-copilot --agent claude-code

Installs into .claude/skills of the current project.

Files

Overview

Use this skill for the specific workaround where Claude Code keeps its Anthropic-shaped client behavior, but the actual backend traffic is sent to a local LiteLLM proxy and then forwarded to GitHub Copilot.

Treat this as an advanced workaround, not an officially guaranteed GitHub workflow. Help the user succeed technically, but do not promise GitHub support, policy approval, or long-term compatibility.

This skill is guidance-first but execution-aware:

If the user wants explanation only, provide the smallest correct set of files, commands, and checks.
If the user wants real setup work on the current machine, inspect first and adapt commands to the active shell and OS.
Pause before persistent edits such as ~/.claude/settings.json or shell profile files.

Read references/doc-verified-notes.md before answering if you need to justify which parts come from the article and which parts were tightened against current LiteLLM docs.