Working memory protocol for multi-step tasks. Use the scratchpad to record intermediate findings without bloating LLM context.
How to schedule one-off and recurring agent tasks, route their delivery to specific Slack/Telegram channels, and use plan enforcement reliably. Load this any time the user asks to remind, schedule, automate, or run something on a cron.
How to add, list, or remove API keys and OAuth integrations through the chat. Load this when the user asks to add/set/configure/connect a key, token, credential, or third-party service (Slack, Telegram, OpenRouter, Anthropic, Google, GitHub, ClickUp, …).
Model string conventions for set_agent_model — how to format names for Gemini, Claude, OpenRouter, and other providers. Load this any time the user asks to change, swap, set, switch, route, or test a model — to avoid building the wrong model string.
How to handle privileged tool calls that require explicit admin approval (ACT-XXXXXX tokens, optional TOTP 2FA). Load this when a tool returns an action token or when the user replies 'Approve ACT-...'.
The mandatory step-by-step procedure for self-evolution: how to plan, stage, verify, and commit code changes. Different paths for parent (native) vs child (Docker sandbox). Load this any time you're about to modify code.
Reference for the A2A v1.0 protocol (Agent-to-Agent). Covers agent discovery, communication with friends and arbitrary agents, and DNA exchange via the Ori-Net.
How to spawn disposable child agents in Docker for sandboxed work — iteration, testing, evolution from a clean slate. Children stage and export DNA back; they cannot commit or reboot. Load this when the user asks to test, sandbox, isolate, spawn, or…