How should config-guard be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this skill.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

Crawler Summary

config-guard answer-first brief

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. --- name: config-guard description: 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. metadata: openclaw: emoji: "🛡️" --- Config Guard 🛡️ **Stop AI agents from killing themselves by editing their own config wrong.** OpenClaw agents have full access to openclaw.json — t Published capability contract available. No trust telemetry is available yet. 7 GitHub stars reported by the source. Last updated 3/1/2026.

Freshness

Last checked 3/1/2026

Best For

Contract is available with explicit auth and schema references.

Not Ideal For

config-guard is not ideal for teams that need stronger public trust telemetry, lower setup complexity, or more explicit contract coverage before production rollout.

Evidence Sources Checked

editorial-content, capability-contract, runtime-metrics, public facts pack

Card Facts Snapshot Contract Trust

Claim this agent

Agent DossierGitHubSafety: 89/100

config-guard

OpenClawself-declared

Public facts

Change events

Artifacts

Freshness

Mar 1, 2026

Verifiededitorial-contentNo verified compatibility signals7 GitHub stars

Published capability contract available. No trust telemetry is available yet. 7 GitHub stars reported by the source. Last updated 3/1/2026.

7 GitHub starsSchema refs publishedTrust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Mar 1, 2026

Vendor

Jzocb

Artifacts

Benchmarks

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Published capability contract available. No trust telemetry is available yet. 7 GitHub stars reported by the source. Last updated 3/1/2026.

View Source

Setup snapshot

git clone https://github.com/jzOcb/config-guard.git

1
Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
2
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content

Vendor (1)

Vendor

Jzocb

profilemedium

Observed Mar 1, 2026Source link Provenance

Compatibility (2)

Protocol compatibility

OpenClaw

contractmedium

Observed Feb 24, 2026Source link Provenance

Auth modes

api_key

contracthigh

Observed Feb 24, 2026Source link Provenance

Artifact (1)

Machine-readable schemas

OpenAPI or schema references published

contracthigh

Observed Feb 24, 2026Source link Provenance

Adoption (1)

Adoption signal

7 GitHub stars

profilemedium

Observed Mar 1, 2026Source link Provenance

Security (1)

Handshake status

UNKNOWN

trustmedium

Observed unknownSource link Provenance

Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium

Observed Apr 15, 2026Source link Provenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB OPENCLEW

Extracted files

Examples

Snippets

Languages

typescript

Parameters

Executable Examples

bash

# Validate current config
bash scripts/config-guard.sh check

# Validate → backup → apply → verify
bash scripts/config-guard.sh apply --restart

# Show what changed vs last backup
bash scripts/config-guard.sh diff

# Emergency rollback
bash scripts/config-guard.sh rollback

bash

# Install the pre-commit hook
cp scripts/pre-config-hook.sh /path/to/repo/.git/hooks/pre-commit
# Or chain it in your existing hook

bash

# ✅ CORRECT: Validates before applying
bash scripts/safe-config-patch.sh '{"agents":{"defaults":{"model":"anthropic/claude-opus-4-5"}}}'

# ❌ WRONG: No validation, will crash on bad input  
gateway config.patch raw='{"agents":{"defaults":{"model":"claude-opus-4.5"}}}'  # dots = crash

bash

bash /path/to/config-guard/scripts/safe-config-patch.sh '<json-patch>'

bash

bash /path/to/config-guard/scripts/config-guard.sh check ~/.openclaw/openclaw.json

bash

bash /path/to/config-guard/scripts/config-guard.sh rollback

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB OPENCLEW

Docs source

GITHUB OPENCLEW

Editorial quality

ready

Full README

name: config-guard description: 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. metadata: openclaw: emoji: "🛡️"

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:

Auto-backup — cp openclaw.json to timestamped backup
JSON syntax check — catches malformed JSON before it hits the gateway
Schema validation — checks required fields, correct types, valid values
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
Critical field diff — warns if Telegram channel, auth tokens, or tool deny lists changed

After config changes (with `--restart`):

Gateway health check — polls gateway for up to 30s
Auto-rollback — if gateway doesn't recover, restores backup automatically

Usage

As a script (recommended):

# Validate current config
bash scripts/config-guard.sh check

# Validate → backup → apply → verify
bash scripts/config-guard.sh apply --restart

# Show what changed vs last backup
bash scripts/config-guard.sh diff

# Emergency rollback
bash scripts/config-guard.sh rollback

As a git hook:

# Install the pre-commit hook
cp scripts/pre-config-hook.sh /path/to/repo/.git/hooks/pre-commit
# Or chain it in your existing hook

For AI agents:

⛔ CRITICAL: DO NOT USE `gateway config.patch` DIRECTLY

The gateway tool's config.patch action bypasses all validation. One wrong model name, one invalid field, and the gateway crashes. You go offline. Nobody can fix you remotely.

Use safe-config-patch.sh instead:

# ✅ CORRECT: Validates before applying
bash scripts/safe-config-patch.sh '{"agents":{"defaults":{"model":"anthropic/claude-opus-4-5"}}}'

# ❌ WRONG: No validation, will crash on bad input  
gateway config.patch raw='{"agents":{"defaults":{"model":"claude-opus-4.5"}}}'  # dots = crash

MANDATORY WORKFLOW

Use the safe wrapper (validates → backs up → applies → verifies):

bash /path/to/config-guard/scripts/safe-config-patch.sh '<json-patch>'

Never guess config field names or values. If unsure:
- Use gateway config.schema to check valid fields
- Use gateway config.get to see current values
- Change ONE field at a time

For complex changes, validate first:

bash /path/to/config-guard/scripts/config-guard.sh check ~/.openclaw/openclaw.json

If gateway dies, rollback:

bash /path/to/config-guard/scripts/config-guard.sh rollback

Why This Matters

On 2026-02-05, the agent used gateway config.patch to upgrade to Claude Opus 4.6. The model ID was wrong (claude-opus-4-6-20260205 doesn't exist yet). Gateway kept crashing and falling back to 4.5. Human had to manually fix.

config-guard existed but was bypassed because the agent used the raw gateway tool instead of the validated wrapper. This is exactly the failure mode this skill was designed to prevent.

Checks Performed

| Check | What it catches | |---|---| | JSON syntax | Malformed JSON, trailing commas, unquoted keys | | Unknown top-level keys | AI inventing fields like fallbacks, auth at wrong level | | Model name format | claude-sonnet-4.5 → should be claude-sonnet-4-5 | | browser.profiles.color | Missing required field, non-hex values | | commands.native | Missing required fields | | Placeholder values | your-token-here, sk-xxx in sensitive fields | | Empty primary model | No model configured = agent can't think | | Telegram channel wipe | Silent removal of channel config | | Auth token removal | Gateway auth accidentally deleted | | Tool deny list changes | Security-critical tools removed from deny |

Philosophy

Prompts are suggestions. Code is law.

This skill doesn't ask the AI to "please validate before changing config." It provides executable scripts that enforce validation. The pre-commit hook blocks bad configs from being committed. The apply script auto-rollbacks on failure.

The AI doesn't need to cooperate. The code runs regardless.

Install

clawdhub install config-guard
# or copy the scripts/ directory to your workspace

Requirements

python3 (for JSON parsing and validation)
curl (for gateway health checks)
bash 4+

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

Verifiedcapability-contract

Endpoints

Dossier API Snapshot API Contract API Trust API

Contract coverage

Status

ready

Auth

api_key

Streaming

Data region

global

Protocol support

OpenClaw: self-declared

Requires: openclew, lang:typescript

Forbidden: none

Guardrails

Operational confidence: medium

Contract is available with explicit auth and schema references.

Trust confidence is not low and verification freshness is acceptable.

Invocation examples

curl -s "https://xpersona.co/api/v1/agents/jzocb-config-guard/snapshot"

curl -s "https://xpersona.co/api/v1/agents/jzocb-config-guard/contract"

curl -s "https://xpersona.co/api/v1/agents/jzocb-config-guard/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media

No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors

GITHUB_REPOSactivepieces

Rank

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Traction

No public download signal

Freshness

Updated 2d ago

OPENCLAW

GITHUB_REPOScherry-studio

Rank

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

Traction

No public download signal

Freshness

Updated 5d ago

MCPOPENCLAW

GITHUB_REPOSAionUi

Rank

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

Traction

No public download signal

Freshness

Updated 6d ago

MCPOPENCLAW

GITHUB_REPOSCopilotKit

Rank

The Frontend for Agents & Generative UI. React + Angular

Traction

No public download signal

Freshness

Updated 23d ago

OPENCLAW

Machine Appendix

Contract JSON

{
  "contractStatus": "ready",
  "authModes": [
    "api_key"
  ],
  "requires": [
    "openclew",
    "lang:typescript"
  ],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": "https://github.com/jzOcb/config-guard#input",
  "outputSchemaRef": "https://github.com/jzOcb/config-guard#output",
  "dataRegion": "global",
  "contractUpdatedAt": "2026-02-24T19:44:09.392Z",
  "sourceUpdatedAt": "2026-02-24T19:44:09.392Z",
  "freshnessSeconds": 4425086
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/jzocb-config-guard/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/jzocb-config-guard/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/jzocb-config-guard/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/jzocb-config-guard/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/jzocb-config-guard/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/jzocb-config-guard/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-04-17T00:55:35.632Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "fix",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:fix|supported|profile"
}

Facts JSON

[
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Jzocb",
    "href": "https://github.com/jzOcb/config-guard",
    "sourceUrl": "https://github.com/jzOcb/config-guard",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-03-01T06:04:30.416Z",
    "isPublic": true
  },
  {
    "factKey": "traction",
    "category": "adoption",
    "label": "Adoption signal",
    "value": "7 GitHub stars",
    "href": "https://github.com/jzOcb/config-guard",
    "sourceUrl": "https://github.com/jzOcb/config-guard",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-03-01T06:04:30.416Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://xpersona.co/api/v1/agents/jzocb-config-guard/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/jzocb-config-guard/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:44:09.392Z",
    "isPublic": true
  },
  {
    "factKey": "auth_modes",
    "category": "compatibility",
    "label": "Auth modes",
    "value": "api_key",
    "href": "https://xpersona.co/api/v1/agents/jzocb-config-guard/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/jzocb-config-guard/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:44:09.392Z",
    "isPublic": true
  },
  {
    "factKey": "schema_refs",
    "category": "artifact",
    "label": "Machine-readable schemas",
    "value": "OpenAPI or schema references published",
    "href": "https://github.com/jzOcb/config-guard#input",
    "sourceUrl": "https://xpersona.co/api/v1/agents/jzocb-config-guard/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:44:09.392Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/jzocb-config-guard/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/jzocb-config-guard/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

config-guard answer-first brief

Executive Summary

Evidence Ledger

Release & Crawl Timeline

Artifacts Archive

Docs & README

name: config-guard description: 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. metadata: openclaw: emoji: "🛡️"

Config Guard 🛡️

The Problem

What Config Guard Does

Before config changes:

After config changes (with --restart):

Usage

As a script (recommended):

As a git hook:

For AI agents:

⛔ CRITICAL: DO NOT USE gateway config.patch DIRECTLY

MANDATORY WORKFLOW

Why This Matters

Checks Performed

Philosophy

Install

Requirements

Contract & API

Reliability & Benchmarks

Media & Demo

Related Agents

After config changes (with `--restart`):

⛔ CRITICAL: DO NOT USE `gateway config.patch` DIRECTLY