songsid/AgEnD

model-discovery

Choose and discover models — when to omit, per-backend defaults, pass-through

cross-instance-messaging

Fire-and-queue cross-instance tools — send once, never resend on queued

session-management

Session stores, forking, and auth-pause recovery

tui-effort

在 Kiro CLI TUI instance 中，透過 tmux 查看或設定模型的 reasoning effort

Source text: Chinese

backend-providers

Configure custom model providers when creating or editing AgEnD Codex or OpenCode instances. Use for local, OpenAI-compatible, GLM, or other non-default provider endpoints and for backend_options provider selection.

delegation-playbook

Delegation protocol, loop prevention, parallel vs sequential execution, result/failure handling, team management, and instance configuration tips for the fleet coordinator

development-workflow

The fleet-wide code-change policy the coordinator enforces when delegating code tasks — stages, review pairing, merge conditions

fleet-config

fleet.yaml and classicBot.yaml structure, validation, common mistakes

fleet-health

Check instance health and what an agent is doing; recover a stuck instance

fleet-restart

Fleet restart types, recovery from tmux crash, rate limit handling, safe update

instance-lifecycle

restart vs replace vs pause/wake; when to use each

multi-channel

Setting up multiple platforms (Telegram + Discord) with proper general routing

scheduling

Cron, one-shot, and silent schedules via the schedule MCP tools

worker-collaboration

Complete assigned fleet work as a worker, report the result to the assigning instance, and request missing information without taking over coordinator duties.