openclaw-subagent-toolsetProvides predefined constrained tool subsets for spawning sub-agents tailored to task types like Explore, Plan, Verification, Coding, and Secretary.
Install via ClawdBot CLI:
clawdbot install hanxiao-bot/openclaw-subagent-toolsetGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated May 7, 2026
Use the Verification tool subset to run read-only tests and review code changes in a CI/CD pipeline. The sub-agent can execute bash commands for verification and read files to validate output, ensuring code quality without risking writes.
Deploy an Explore-type sub-agent to collect data from multiple sources, such as web pages and file systems. This is ideal for market research or competitive analysis where gathering facts from various documents is needed.
Use the Plan tool subset to create detailed project plans, break down tasks, and write to-do lists. The agent can read existing files and send messages to stakeholders, but cannot execute code or edit files.
Assign a Secretary sub-agent to read documents, summarize content, and generate structured reports. It can write to-do lists for follow-ups and send messages to users, but has limited file access.
Utilize the Coding tool subset for writing and debugging code in a sandboxed environment with full tool access. This enables developers to implement features, fix bugs, and verify changes safely.
Offer basic Explore and Secretary subsets for free, while premium tiers unlock Plan, Verification, and Coding subsets. This encourages adoption and upsells advanced capabilities.
License the entire subagent toolset to enterprises for internal automation tasks. Custom tool restrictions can be configured per department, ensuring security and compliance.
Provide the tool subsets as API endpoints where users pay per sub-agent spawn or per task completed. This suits small businesses needing occasional automation without upfront costs.
💬 Integration Tip
Prepend the tool subset as a system prompt before each sub-agent task to enforce constraints; use different subsets for different phases of a workflow to optimize safety and efficiency.
Scored May 7, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.