multi-agent-coordinator
AdvisoryAudited by Static analysis on May 6, 2026.
Overview
No suspicious patterns detected.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A broad or ambiguous request could lead the coordinator to involve several agents and pursue a larger plan than the user expected.
The skill may choose and coordinate other agents on the user's behalf. This is the core advertised function, but users should review delegated plans before allowing high-impact actions.
Automatically select the optimal team of agents based on task analysis.
Use the planning checkpoint to review which agents will be used, what each will do, and whether any downstream action should require explicit confirmation.
Information included in the original task may be shared across multiple specialist agents during coordination.
The skill is designed to pass work products among agents and synthesize their results. This is purpose-aligned, but the artifacts do not define detailed context-sharing boundaries.
Combine outputs from multiple agents into coherent, comprehensive solutions.
Avoid including unnecessary sensitive information, and specify any limits on what context may be shared between agents.