A protective workflow skill designed to safely modify OpenClaw configurations through schema validation and mandatory human-in-the-loop confirmation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install config-safe
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install config-safe using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Config Safe?
Config Safe is an essential utility within the Openclaw Skills ecosystem designed to mitigate the risks associated with modifying system settings. Because OpenClaw enforces strict configuration validation, a single typo or missing field can prevent the Gateway from starting, effectively breaking the communication link between the user and the agent.
This skill implements a rigorous lifecycle for updates: it reads official documentation, performs static and dynamic schema checks, and generates clear visual diffs. By prioritizing stability, Config Safe ensures that your Openclaw Skills environment remains operational even when performing complex adjustments to channels, identities, or security sandboxes.
Config Safe Use Cases
- Safely enabling or disabling communication channels like Telegram without risking a system crash.
- Updating sensitive bot tokens and dmPolicy settings with automatic validation.
- Modifying agent identity metadata, including names and display emojis.
- Adjusting sandbox execution modes and session scopes for improved security.
- Reviewing current configuration hashes to prevent concurrent modification conflicts.
How Config Safe Works
- The skill first reads the latest official documentation to understand the configuration structure and validation rules.
- It retrieves the current active configuration and its associated hash using the config.get method.
- A static schema validation is performed via config.schema to check for type mismatches or missing required fields.
- It generates a detailed preview showing the 'Before' and 'After' states, masking sensitive tokens where necessary.
- Upon explicit user confirmation, it applies the changes using config.patch, which triggers a Gateway reboot only if the configuration is valid.
Config Safe Setup
To use this skill, ensure your OpenClaw environment is active and accessible via the CLI. No additional external dependencies are required beyond the core installation.
# Verify your current OpenClaw status
openclaw status
# Check for existing configuration errors
openclaw doctor
Config Safe Data Schema & Taxonomy
The skill interacts with the standard OpenClaw configuration hierarchy. Key data structures include:
| Section | Description |
|---|---|
channels |
Platform integrations (Telegram, etc.) including status and credentials. |
agents |
Definitions for agent behavior, identity, and sandbox scopes. |
baseHash |
The unique fingerprint of the configuration used to ensure atomic updates. |
schema |
The JSON Schema object used for structural validation. |
Config Safe Advanced Features
- Conflict prevention using baseHash comparison to ensure no settings are overwritten by parallel processes.
- Automated recovery suggestions using the doctor utility if a manual edit goes wrong.
- Dynamic patching via config.patch which allows partial updates without needing to provide the full configuration file.
- Multi-stage validation including both static property checks and dynamic runtime simulation.
SKILL.md
Loading
Related Openclaw Skills
Subagent Watchdog
A reliability tool that monitors AI subagent runs by enforcing completion markers within defined deadlines.
Braingit
A deterministic utility for creating automated git snapshot commits specifically for Markdown files within a repository.
Feishu Agent Relay
A framework for building multi-agent collaboration systems on Feishu by managing cross-bot user identity mapping and task relay.
index1
A persistent AI memory system providing coding agents with hybrid search, code indexing, and cognitive fact recording across sessions.
SafeSkills
A secure execution service that allows AI agents to manage EVM wallets and secrets without ever accessing raw private keys.
Trade Manager
An automated trade execution engine for Polymarket that manages risk through stop-loss, take-profit, and trailing stop rules.
Featured*
