Skip to content
TrustedSkillsbeta
Back to all skills

Config Guard

Checked
jzOcb·v1.0.0·agents·MIT

Prevent OpenClaw config changes from crashing the gateway. Auto-backup, schema validation, critical field checks, and auto-rollback. Use before any config.apply, config.patch, or openclaw.json edit.

Repository

Install on your platform

Showing OpenClaw.

  1. 1

    Run this in your terminal

    terminal
    $ openclaw skills install config-guard

What we know about this skill

Publisher

jzOcb

Taken from the source listing. We haven't verified who controls this account.

Install target

Pinned to 3dcfd8d7

Installs fetch a stored snapshot of that commit, so the code can't change after the fact.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Only contacts known or declared hosts: 127.0.0.1.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    127.0.0.1local

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned jzocb/config-guard at 946cdaa03e.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
946cdaa03e
Manifest
SKILL.md
Scanned
7 files, 876 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

Config Guard protects OpenClaw gateways from configuration errors made by AI agents. It performs automated backups, JSON syntax and schema validation, semantic checks for common AI mistakes (like incorrect model names or missing fields), and includes a health check with automatic rollback if the gateway fails to recover after changes. This prevents cascading failures caused by agent-introduced configuration issues.

When to use it

  • Automated Configuration Updates: Use when AI agents are directly modifying openclaw.json.
  • Complex Configurations: Ideal for gateways with many channels, models, or tools where errors are more likely.
  • Remote Management: Essential for scenarios where remote troubleshooting of gateway crashes is difficult.
  • Plugin Development: Crucial when plugins introduce new configuration options that agents might mismanage.

Key capabilities

  • Automatic timestamped backups before config changes
  • JSON syntax validation
  • Schema validation (required fields, types, values)
  • Semantic checks for AI-specific errors (e.g., incorrect model names, missing required fields)
  • Critical field diff warnings (Telegram channels, authentication tokens, tool deny lists)
  • Gateway health check with 30-second polling
  • Automatic rollback to the previous backup if the gateway fails

Example prompts

These are not direct prompts to the skill, but rather scenarios where it protects against errors made by agents:

  • "Update the model configuration to use claude-sonnet-4.5." (Config Guard will correct "claude-sonnet-4.5" to "claude-sonnet-4-5")
  • "Add a new Telegram channel with ID 123." (Config Guard ensures required fields for the channel are present)
  • “Enable authentication using API keys.” (Config Guard will check for placeholder values in sensitive fields.)

Tips & gotchas

The skill requires access to and modification rights of openclaw.json. Consider integrating it as a git hook (pre-config-hook.sh) to automatically validate changes before they are applied.