← 返回 Skills 市场
260
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install sub-agents
功能描述
Spawn and coordinate sub-agent sessions for parallel work. Use when delegating tasks (research, code, analysis), routing to appropriate models, or managing m...
安全使用建议
This skill is coherent for delegating work to sub-agents, but be careful what you hand to child sessions. Never attach secrets (API keys, private keys, passwords, or full database dumps) or sensitive files as attachments or explicit file paths unless you're certain the child should have them. Be cautious using ANNOUNCE_SKIP — it suppresses chat-level notices and can hide a sub-agent's outputs. Prefer sandbox=require or restrict tools for children where possible, limit agentId usage to trusted allowlisted agents, enable auditing/logging of spawned sessions, and test with harmless, non-sensitive tasks first.
功能分析
Type: OpenClaw Skill
Name: sub-agents
Version: 1.0.0
The 'sub-agents' skill bundle provides a structured framework for an AI agent to delegate tasks to parallel sub-sessions. It includes comprehensive documentation on model routing (referencing futuristic GPT-5 and Claude models), task specification protocols, and session management tools like `sessions_spawn` and `subagents`. While it includes a mechanism to suppress status updates (`ANNOUNCE_SKIP`), this is presented as a legitimate way to reduce chat noise during parallel processing rather than a stealth tactic. No indicators of data exfiltration, malicious execution, or unauthorized access were found in SKILL.md or the associated reference files.
能力评估
Purpose & Capability
The name/description (spawn and coordinate sub-agents) matches the SKILL.md content. There are no unrelated required binaries, env vars, or installs — everything in the instructions is about session spawning, model routing, and handoff templates, which is coherent for this purpose.
Instruction Scope
Instructions clearly limit sub-agents to the `task` string, explicit file paths, and attachments — which is good — but the skill explicitly instructs how to pass file contents/attachments to sub-agents and how to suppress announcements with ANNOUNCE_SKIP. That gives the user full control over what data the child sees; if a user includes sensitive files/attachments the sub-agent will receive them. ANNOUNCE_SKIP can be used to keep a child session from posting results to chat, which could hide outputs if misused.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes disk/remote install risk.
Credentials
The skill requests no environment variables or credentials. It references provider/model names and subscription concepts, but it does not ask for keys or unrelated secrets in its metadata. Note: actual model/API credentials are expected to be handled by the platform, not the skill.
Persistence & Privilege
always:false and normal autonomous invocation are used. The skill does not request persistent privileges or attempt to modify other skills' configs. It does allow spawning under another agent via `agentId` (requires allowlist), which depends on platform allowlist correctness.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install sub-agents - 安装完成后，直接呼叫该 Skill 的名称或使用
/sub-agents触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release: enables spawning and managing sub-agent sessions for parallel work.
- Sub-agents operate with strict context isolation; they see only supplied tasks, referenced files, and attachments.
- Comprehensive guidance on when to use sub-agents, recommended models, and session parameters.
- Implements structured task handoff protocol for reliable, testable sub-agent delegation.
- Announce mechanism clarifies how sub-agent results are reported or suppressed.
- Provides orchestration, monitoring, and management tools for sub-agent lifecycle.
元数据
常见问题
sub-agents 是什么？
Spawn and coordinate sub-agent sessions for parallel work. Use when delegating tasks (research, code, analysis), routing to appropriate models, or managing m... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 260 次。
如何安装 sub-agents？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install sub-agents」即可一键安装，无需额外配置。
sub-agents 是免费的吗？
是的，sub-agents 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
sub-agents 支持哪些平台？
sub-agents 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 sub-agents？
由 bill492（@bill492）开发并维护，当前版本 v1.0.0。
推荐 Skills