OpenClaw Subagent Toolset

Provides predefined constrained tool subsets for spawning sub-agents tailored to task types like Explore, Plan, Verification, Coding, and Secretary.

This skill is largely harmless guidance for choosing tool subsets, but it has issues you should consider before installing: - Inconsistencies: SKILL.md contains contradictions (e.g., Secretary both includes and forbids glob_search). Ask the author to fix these to avoid ambiguous behavior. - Soft constraints: The skill relies on LLM compliance rather than enforcing sandboxing. Confirm your platform enforces tool restrictions at runtime; otherwise sub-agents could ignore the guidance. - 'Skill' invocation risk: Allowed use of the 'Skill' tool lets a sub-agent call other skills (which may have more privileges). If you install this, ensure the platform prevents privilege escalation between skills or disallows chaining that would bypass restrictions. - Unknown provenance: There is no homepage/source and the owner is an ID only. Prefer skills from known sources or ask for more provenance information. - Test in a sandbox: Before using in production, test spawning sub-agents in an isolated environment and verify the platform actually enforces the allowed/forbidden tool lists. If you need strong guarantees, require platform-level enforcement (hard sandboxing) or implement technical checks rather than relying on prompt-based guidance.

Type: OpenClaw Skill Name: openclaw-subagent-toolset Version: 1.0.0 The skill bundle provides a framework for managing sub-agents by defining specific tool subsets (Explore, Plan, Verification, Coding, Secretary) to constrain their behavior based on task requirements. The instructions in SKILL.md and README.md are designed to improve safety by explicitly forbidding high-risk tools like 'exec' or 'write' for low-privilege tasks, and it contains no executable code, data exfiltration logic, or malicious prompt injection.