config-guardlisted

# Config Guard 🛡️ **Stop AI agents from killing themselves by editing their own config wrong.** OpenClaw agents have full access to `openclaw.json` — the file that controls the gateway, channels, models, and tools. One bad edit and the gateway crashes. The agent goes offline. Nobody can fix it remotely. This skill prevents that. ## The Problem Real incidents (all from 2026-02-04, same day): | What happened | Root cause | |---|---| | Gateway crashed after update | AI added unknown config fields (`auth`, `fallbacks`) | | Model not found | AI wrote `claude-sonnet-4.5` (dots) instead of `claude-sonnet-4-5` (hyphens) | | Telegram stopped working | Config change silently wiped the channel section | | browser.profiles error | AI forgot the required `color` field (must be hex) | | Plugin SDK missing | Update broke module paths, no validation caught it | **Core truth: AI doesn't know correct config formats. It guesses. Wrong guesses crash systems.** ## What Config Guard Does ### Before config changes: 1. **Auto-backup** — `cp openclaw.json` to timestamped backup 2. **JSON syntax check** — catches malformed JSON before it hits the gateway 3. **Schema validation** — checks required fields, correct types, valid values 4. **Semantic checks** — catches AI-specific mistakes: - Model names with dots instead of hyphens - Missing required fields (browser.profiles.color) - Unknown top-level keys - Placeholder values in sensitive fields 5. **Critical field diff** — warns if