Redacted excerpt; full evidence withheld.

$ pwd && ls -la && sed -n '1,240p' README.md
exit: 0
erything, written on the first start with a token generated for this machine, relocatable with `MCC_CONFIG_DIR`; a legacy `~/.fcc` moves itself once | `~/.mcc` | [Guide](docs/USAGE.md#3-first-run) |

## How it works

<div align="center">
  <img src="https://raw.githubusercontent.com/FiredMosquito831/my-claude-code/main/assets/how-it-works.svg" alt="Request flow: a coding agent speaks one of four protocols to My Claude Code, which resolves the tier, picks a credential, walks the fallback chain and translates the reply back" width="820">
</div>

Your agent talks to MCC in whichever protocol it already speaks — `POST /v1/messages` for Claude Code, Pi, OpenCode, Crush, Kimi Code, Qwen Code, Droid and Kilo; `POST /v1/responses` for Codex; `POST /v1/chat/completions` for Cline, Goose, Aider and every OpenAI-shaped SDK; `POST /v1beta/models/{model}:generateContent` for Gemini CLI and Antigravity. All four doors reach the same router, which resolves the requested tier to a real model, applies your reasoning and output-budget settings, adapts images, picks a healthy credential, and walks the fallback chain when a provider fails. The reply
[excerpt truncated]