Use this skill to execute repeatable, low-error lifecycle operations for OpenClaw agents.
openclaw status, openclaw agents list)If deleting an agent, always archive first and require explicit confirmation.
AGENT_IDTELEGRAM_TOKENWORKSPACE (default: ~/.openclaw/workspace-)--inherit-auth or INHERIT_AUTH=1) only with explicit user consentAGENT_IDPAIRING_CODE (obtained only after user sends /start to the bot)AGENT_IDAGENT_IDstate/archive// )Read references/openclaw-agent-lifecycle-playbook.md before running uncommon operations.
For deterministic execution, use scripts in this skill:
scripts/create-telegram-agent.shscripts/approve-telegram-pairing.shscripts/archive-agent.shscripts/delete-agent-safe.shscripts/refresh-dashboard.shscripts/lifecycle-log.shopenclaw CLI over ad-hoc file edits.openclaw config get/set (append entry; do not overwrite blindly).openclaw pairing approve --channel telegram .auth-profiles.json from another agent workspace.scripts/delete-agent-safe.sh (archive verification + explicit confirmation + cleanup + logging).Run:
openclaw agents list --json
openclaw status --json
openclaw gateway status --json
Confirm:
共 2 个版本