developing-subagents
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown documentation files providing guidance on subagent design, orchestration, and configuration for various developer-oriented AI platforms.
- [SAFE]: No executable scripts, binaries, or automated tasks are included. The provided examples are static configuration snippets (YAML, TOML, JSON) intended for manual reference by developers.
- [SAFE]: External links in the documentation point exclusively to official documentation for established services, including Anthropic (claude.com), OpenAI (openai.com), and OpenCode (opencode.ai).
- [SAFE]: The skill does not access sensitive local data, hardcode credentials, or attempt to override the parent agent's safety protocols. Discussion of 'bypassPermissions' and similar settings is limited to describing existing platform features.
Audit Metadata