OpenClaw Reference

OpenClaw platform reference - plugin system, extensions, configuration, boot/provisioning, channels, models, CLI. Use when working on openclaw codebase, buil...

This skill is a bundled reference/docs set for OpenClaw and appears internally consistent and low-risk. It does mention local repo/config paths (e.g. ~/Projects/openclaw/, ~/.openclaw/openclaw.json) and describes platform features (BOOT.md, channels, credentials directories). If you allow an agent to act on this guidance, be cautious about any follow-up actions that read or modify your local OpenClaw config or credentials directories — the reference itself is read-only, but agents using it could advise or perform changes. If you don't want the agent accessing local files or secrets, do not grant file-system or credential access when invoking the skill. If you need higher assurance, inspect the included markdown files yourself before use and validate the skill's source (this package has no homepage and an unknown source).

Type: OpenClaw Skill Name: openclaw-reference Version: 2026.4.1 This bundle is a comprehensive technical reference for the OpenClaw platform, intended to provide an AI agent with the necessary context to assist in developing, configuring, and debugging the system. It contains detailed documentation on the plugin architecture, boot sequences (references/boot-provisioning.md), configuration schemas (references/configuration.md), and CLI commands (references/cli-commands.md). While the documentation covers high-risk features like remote command execution and automated provisioning, these are described as core architectural components with associated security policies and command allowlists. The presence of a 'github-context.md' file tracking known bugs and security regressions further supports its role as a legitimate developer tool rather than a malicious payload.