Crawler Summary

gateway-watchdog answer-first brief

Automatically detects and repairs OpenClaw gateway disconnections, unresolvable plugin entries, deprecated or mismatched LLM model strings, and invalid API keys. Use when the gateway is down, agent is disconnected, openclaw.json reports plugin or config errors, or a model is failing to respond. Includes a live CLI dashboard for monitoring repair progress. --- name: gateway-watchdog description: Automatically detects and repairs OpenClaw gateway disconnections, unresolvable plugin entries, deprecated or mismatched LLM model strings, and invalid API keys. Use when the gateway is down, agent is disconnected, openclaw.json reports plugin or config errors, or a model is failing to respond. Includes a live CLI dashboard for monitoring repair progress. user-invocable: true m Published capability contract available. No trust telemetry is available yet. 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

gateway-watchdog 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

Claim this agent
Agent DossierGitHubSafety: 89/100

gateway-watchdog

Automatically detects and repairs OpenClaw gateway disconnections, unresolvable plugin entries, deprecated or mismatched LLM model strings, and invalid API keys. Use when the gateway is down, agent is disconnected, openclaw.json reports plugin or config errors, or a model is failing to respond. Includes a live CLI dashboard for monitoring repair progress. --- name: gateway-watchdog description: Automatically detects and repairs OpenClaw gateway disconnections, unresolvable plugin entries, deprecated or mismatched LLM model strings, and invalid API keys. Use when the gateway is down, agent is disconnected, openclaw.json reports plugin or config errors, or a model is failing to respond. Includes a live CLI dashboard for monitoring repair progress. user-invocable: true m

OpenClawself-declared

Public facts

6

Change events

1

Artifacts

0

Freshness

Mar 1, 2026

Verifiededitorial-contentNo verified compatibility signals

Published capability contract available. No trust telemetry is available yet. Last updated 3/1/2026.

Schema refs publishedTrust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Mar 1, 2026

Vendor

Millerderek

Artifacts

0

Benchmarks

0

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. Last updated 3/1/2026.

Setup snapshot

git clone https://github.com/Millerderek/OpenClaw--Skill-CrashRepairKit.git
  1. 1

    Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.

  2. 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

Millerderek

profilemedium
Observed Mar 1, 2026Source linkProvenance
Compatibility (2)

Protocol compatibility

OpenClaw

contractmedium
Observed Feb 24, 2026Source linkProvenance

Auth modes

api_key

contracthigh
Observed Feb 24, 2026Source linkProvenance
Artifact (1)

Machine-readable schemas

OpenAPI or schema references published

contracthigh
Observed Feb 24, 2026Source linkProvenance
Security (1)

Handshake status

UNKNOWN

trustmedium
Observed unknownSource linkProvenance
Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium
Observed Apr 15, 2026Source linkProvenance

Release & Crawl Timeline

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

Self-declaredagent-index

Artifacts Archive

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

Self-declaredGITHUB OPENCLEW

Extracted files

0

Examples

0

Snippets

0

Languages

typescript

Parameters

Docs & README

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

Self-declaredGITHUB OPENCLEW

Docs source

GITHUB OPENCLEW

Editorial quality

ready

Automatically detects and repairs OpenClaw gateway disconnections, unresolvable plugin entries, deprecated or mismatched LLM model strings, and invalid API keys. Use when the gateway is down, agent is disconnected, openclaw.json reports plugin or config errors, or a model is failing to respond. Includes a live CLI dashboard for monitoring repair progress. --- name: gateway-watchdog description: Automatically detects and repairs OpenClaw gateway disconnections, unresolvable plugin entries, deprecated or mismatched LLM model strings, and invalid API keys. Use when the gateway is down, agent is disconnected, openclaw.json reports plugin or config errors, or a model is failing to respond. Includes a live CLI dashboard for monitoring repair progress. user-invocable: true m

Full README

name: gateway-watchdog description: Automatically detects and repairs OpenClaw gateway disconnections, unresolvable plugin entries, deprecated or mismatched LLM model strings, and invalid API keys. Use when the gateway is down, agent is disconnected, openclaw.json reports plugin or config errors, or a model is failing to respond. Includes a live CLI dashboard for monitoring repair progress. user-invocable: true metadata: {"openclaw": {"emoji": "๐Ÿ”ง", "requires": {"bins": ["jq", "bash"]}, "os": ["linux"]}}

Gateway Watchdog & Auto-Repair Skill

When to Use This Skill

Invoke automatically or on user request when any of the following are true:

  • Gateway service is not running or the agent lost connection
  • Startup reports plugin not found: <name> errors
  • openclaw.json is flagged as invalid on gateway start
  • Agent reconnects after a period of being offline or unreachable
  • A model call is failing, timing out, or returning unexpected errors
  • User reports the agent was disconnected, unresponsive, or not replying
  • User asks about gateway health, model health, or config status

Tools

gateway_health_check

  • Description: Check gateway service state and surface any config errors
  • Usage: systemctl is-active openclaw-gateway.service 2>&1; timeout 10 openclaw doctor 2>&1 </dev/null | grep -v "State dir migration"

fix_plugins

  • Description: Detect and remove unresolvable plugin entries from openclaw.json, restart gateway
  • Usage: bash {baseDir}/fix-plugins.sh

check_models

  • Description: Validate all configured model strings, API keys, provider reachability, and escalation chain integrity
  • Usage: bash {baseDir}/check-models.sh

check_models_fix

  • Description: Same as check_models but automatically rewrites deprecated or invalid model strings
  • Usage: bash {baseDir}/check-models.sh --fix

gateway_watch

  • Description: Launch the live CLI dashboard showing gateway state, model health, and recent events
  • Usage: bash {baseDir}/openclaw-watch.sh --follow

gateway_watch_models

  • Description: Full model health report with per-provider API key and endpoint status
  • Usage: bash {baseDir}/openclaw-watch.sh --models

gateway_repair_watch

  • Description: Run full repair with animated progress bar and return to dashboard
  • Usage: bash {baseDir}/openclaw-watch.sh --repair

startup_fix

  • Description: Run the combined startup fix (plugin + model) as it would run automatically on gateway start
  • Usage: bash /usr/local/bin/openclaw-startup-fix.sh

view_logs

  • Description: Tail the startup fix log and watchdog log for recent repair activity
  • Usage: tail -n 30 /var/log/openclaw-startup-fix.log /var/log/openclaw-watchdog.log

Instructions

On reconnection after downtime

Run gateway_health_check silently. Parse output for:

  • plugin not found: โ†’ run fix_plugins, report result
  • Config invalid โ†’ run fix_plugins, report result
  • inactive / failed โ†’ run fix_plugins (it will restart), report result
  • deprecated / model errors โ†’ run check_models, offer check_models_fix
  • Clean output โ†’ continue normally, do not mention the check

On explicit user request

  1. Run gateway_health_check and report current state
  2. Run check_models and report any model/API key issues
  3. If issues found, offer to fix with fix_plugins and/or check_models_fix
  4. After any fix, confirm recovery with gateway_health_check
  5. Report what was changed, what backup was saved, and any manual steps needed

On model errors

  1. Run check_models to identify the specific failure
  2. Check if the issue is: bad model string, expired API key, provider unreachable, or broken escalation chain
  3. If model string is deprecated โ†’ run check_models_fix
  4. If API key issue โ†’ report the provider and env var name needed, do not auto-fix keys
  5. If provider unreachable โ†’ report as transient, suggest retry
  6. If escalation chain broken โ†’ show the full chain and which link is broken

Reporting to the user

Always include:

  • Which issues were found (plugin names, model names, provider names)
  • What was changed and what backup was saved
  • Current gateway state after fix
  • Any manual steps required (e.g. reinstalling a plugin, updating an API key)

For plugin removals: remind user to reinstall when ready: openclaw plugins install <name> For model fixes: show the old string and the replacement used

Recovery After Disconnection (Silent Mode)

On first turn after the agent comes back online, run gateway_health_check silently. Only surface output if a problem is detected. If everything is healthy, do not mention the check and proceed normally with the conversation.

Examples

  • "The agent was down for a while" โ†’ silent health check, fix if needed, report only if issues found
  • "Gateway won't start" โ†’ fix_plugins, report result
  • "plugin not found: retell-voice" โ†’ fix_plugins, report removed plugins
  • "My model isn't responding" โ†’ check_models, report provider/key status
  • "/gateway-watchdog" โ†’ full health check + model check, fix issues, report summary
  • "Show me the dashboard" โ†’ gateway_watch
  • "Is everything healthy?" โ†’ gateway_health_check + check_models, report summary
  • "What plugins were removed?" โ†’ view_logs, summarise recent repair activity

Contract & API

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

Verifiedcapability-contract

Contract coverage

Status

ready

Auth

api_key

Streaming

No

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/millerderek-openclaw-skill-crashrepairkit/snapshot"
curl -s "https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/contract"
curl -s "https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/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

70

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

Traction

No public download signal

Freshness

Updated 2d ago

OPENCLAW
GITHUB_REPOScherry-studio

Rank

70

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

70

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | ๐ŸŒŸ Star if you like it!

Traction

No public download signal

Freshness

Updated 6d ago

MCPOPENCLAW
GITHUB_REPOSCopilotKit

Rank

70

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/Millerderek/OpenClaw--Skill-CrashRepairKit#input",
  "outputSchemaRef": "https://github.com/Millerderek/OpenClaw--Skill-CrashRepairKit#output",
  "dataRegion": "global",
  "contractUpdatedAt": "2026-02-24T19:41:52.232Z",
  "sourceUpdatedAt": "2026-02-24T19:41:52.232Z",
  "freshnessSeconds": 4427159
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-04-17T01:27:51.747Z"
    }
  },
  "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"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|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": "Millerderek",
    "href": "https://github.com/Millerderek/OpenClaw--Skill-CrashRepairKit",
    "sourceUrl": "https://github.com/Millerderek/OpenClaw--Skill-CrashRepairKit",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-03-01T06:02:53.645Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:41:52.232Z",
    "isPublic": true
  },
  {
    "factKey": "auth_modes",
    "category": "compatibility",
    "label": "Auth modes",
    "value": "api_key",
    "href": "https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:41:52.232Z",
    "isPublic": true
  },
  {
    "factKey": "schema_refs",
    "category": "artifact",
    "label": "Machine-readable schemas",
    "value": "OpenAPI or schema references published",
    "href": "https://github.com/Millerderek/OpenClaw--Skill-CrashRepairKit#input",
    "sourceUrl": "https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:41:52.232Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/millerderek-openclaw-skill-crashrepairkit/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub ยท 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
  }
]

Sponsored

Ads related to gateway-watchdog and adjacent AI workflows.