Coding Agent Token Economics Standard
CATES is a vendor-neutral analyzer for measuring coding-agent configurations against token-efficiency, security, and conformance rules. Teams use its command-line tools or Docker image to inspect instructions, prompts, MCP settings, hooks, and editor configuration, and to apply selected lossless optimizations.
5 files for GitHub Copilot and Claude Code: cates copilot-instructions.md, CATES SDLC, sdlc-implement, sdlc-plan and 1 more — 526 tokens loaded in every session.
.github/copilot-instructions.md A 526 tok .github/prompts/sdlc-implement.prompt.md A 10 tok .github/prompts/sdlc-plan.prompt.md A 11 tok .github/prompts/sdlc-review.prompt.md A 11 tok .github/agents/sdlc.agent.md A 24 tok These files are microsoft/cates's own configuration — they tell GitHub Copilot and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.