Multi-agent control plane for coding CLIs (Codex, OpenCode, CommandCode, Hermes) with one tmux session, one .logs/ source of truth, terminal + web frontends.
This repository also configures its own agents. See what endy tells them →
Skill Codex
Use this skill when a task is best handed off to another coding agent in the endy stack — OpenCode (multi-model worker, fast refactors, test writing), CommandCode/cmd (Kimi K2.6 / DeepSeek), Hermes (Nous Research, tool-heavy), Gemini, or Claude. Covers three delivery modes: short blocking calls, long detached tmux…
Skill Codex
Use this skill — it is the primary one — when you need to drive another coding agent interactively through a tmux pane. Open named windows, send prompts, capture output, manage lifecycle, AND switch models / change auth / use slash commands inside the live CLI (claude, cmd, opencode, hermes, gemini, codex). Includes a…
Skill Claude CodeCodex
Use this skill when you need to inspect the endy environment of a running task — handoff lineage (who handed work to whom and why), peers in the same and other endy sessions, and per-agent tier headroom (codex 5h/wk, opencode session cost) so you can pick the next agent to hand off to. The same data is auto-prepended…