← Back to directory

anthropic-instructions

Employee-level Anthropic ("ant") prompts for GitHub Copilot and open-source coding agents (claw-code, openclaude, opencode). Injects leaked internal rules for honest verification, autonomy, and minimal user intervention.

Setup / get started

Start from the GitHub repository: source code and README for anthropic-instructions.

Alternatives to anthropic-instructions

Similar projects in this directory:

  • ghostclaw — Ghostclaw - AI Architectural Code Review Assistant. A vibe-based coding assistant focused on architectural integrity…
  • cliclaw — Run AI coding agents (Kiro, Claude, Cursor, Codex, Aider, Gemini, Copilot) in a continuous loop on any project…
  • OpenClaw — An open-source task orchestration platform for [OpenCode](https://opencode.ai) and…
  • agency-agents-zh — 180 个即插即用的 AI 专家人设(中文版)— 覆盖 17 个部门,支持 Claude Code / OpenClaw / Cursor / Trae 等 11 种工具 | Chinese AI agent personas for…
  • refly — The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more…
By gil906Added 4/3/2026