claude-code-settings copilot-instructions.md

A set of instructions for Claude Code and GitHub Copilot settings, including a proxy-based model setup and reusable skills.

In plain words
What is it for?
Starting the Copilot proxy, managing sessions with tmux, configuring the API connection, and creating or maintaining reusable skills.
Why use it?
It documents the required local services, configuration, environment variables, and skill file format so the setup works consistently.

Instructions file for GitHub Copilot

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/feiskyer/claude-code-settings/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/feiskyer/claude-code-settings

Made for: GitHub Copilot.

Per session 649 This file is loaded in full into every session.
When invoked 649 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.00649 $0.00649
Opus 5 $0.00324 $0.00324
Sonnet 5 $0.00130 $0.00130
Haiku 4.5 $0.00065 $0.00065

Measured 2d ago against content hash fdb114746342, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-settings copilot-instructions.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 2d 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.

.github/copilot-instructions.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 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 and GitHub Copilot when working with code in this repository.

Environment Setup

This repository contains Claude Code settings, configurations and guidance. The default setup uses GitHub Copilot as the model provider through a proxy API.

Required Dependencies

  • copilot-gateway: Run with npx copilot-gateway@latest start --proxy-env to start the proxy and authorize GitHub Copilot account
  • Use tmux for session management: tmux new-session -d -s copilot 'npx copilot-gateway@latest start --proxy-env'

Configuration

  • settings.json: Contains environment variables for API configuration
  • Uses localhost:4141 as the API base URL
  • Telemetry and non-essential traffic are disabled

Skills

Skills are reusable capabilities defined in the skills/ directory. Each skill has a SKILL.md file with YAML frontmatter containing name and description fields. The description serves as both documentation and trigger condition.

Skill File Structure

All skill files must include YAML frontmatter:

---
name: skill-name
description: 'Comprehensive description that also serves as the trigger condition. Include keywords and phrases that should activate this skill.'
---

Directory Structure

skills/
├── translate/           # Tech article translation to Chinese
├── github-fix-issue/    # Fix GitHub issues end-to-end
├── github-review-pr/    # Review GitHub pull requests
├── skill-creator/       # Create and benchmark agent skills
├── codex-skill/         # Handoff tasks to Codex CLI
├── nanobanana-skill/    # Image generation with Gemini
├── deep-research/       # Multi-agent research orchestration
└── youtube-transcribe-skill/  # YouTube transcript extraction

Usage

Skills are invoked via slash syntax or triggered automatically:

/skill-name [arguments]

Examples:

  • /translate [text or file] - Translate to Chinese

Skill Development Principles

When creating or modifying skills:

Read the full file on GitHub · 81 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. 2d ago First seen · 81 lines · 649 tokens per session scan A fdb114746342

Subscribe to this mod's changes

claude-code-settings copilot-instructions.md is an instructions file published in the GitHub repository feiskyer/claude-code-settings (1,644 stars, last pushed 19d ago), licensed MIT. It adds 649 tokens to every session, about $0.0032 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.