Agent manager

Manage Clawdbot agents: discover, profile, track capabilities, define routing hierarchy, and assign tasks. Use when: (1) Listing available agents, (2) Profiling agent capabilities and communication methods, (3) Defining agent routing (can_assign_to, reports_to, escalation_path), (4) Assigning tasks to appropriate agents, (5) Tracking agent performance and completed work, (6) Updating agent registry after changes.

Install only if you intend to manage agent delegation. Before use, replace the bundled Ilkerkaan/Telegram escalation target, review main agent privileges, require explicit approval for spawned or long-running agents, and do not rely on can_assign.js as a strong authorization boundary without fixing its target validation.

Type: OpenClaw Skill Name: agents-manager Version: 1.0.2 The skill bundle's Node.js scripts primarily handle local file operations for agent configuration. However, the `agent-registry.md` and other documentation (e.g., `task-routing-rules.md`) explicitly declare that the 'main' agent, which this skill manages, possesses extremely broad and powerful capabilities. These include arbitrary shell command execution (`exec, process`), network access (`web_search, web_fetch`), browser control (`browser`), persistence (`cron`), and the ability to spawn and control other agents (`sessions_spawn, sessions_send`). While these capabilities are plausibly required for an agent management skill, their extensive nature introduces significant security risks, even without explicit malicious intent found in the skill's direct instructions or code.