What makes OpenClaw Update Runbook notable?

1K downloads. Trust evidence available

How should OpenClaw Update Runbook be evaluated before use?

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

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.

agentCLAWHUBUnverified

OpenClaw Update Runbook

Use when updating OpenClaw or debugging an OpenClaw instance after an update. This skill acts as a structured update runbook with emphasis on gateway startup...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.0.6

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.6release · observed May 28, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s170vkzshxphjazbn77zkncnhx86ge19:claw-update-runbook

Install using `clawhub skill install s170vkzshxphjazbn77zkncnhx86ge19:claw-update-runbook` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/bkf-gitty/claw-update-runbook before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-bkf-gitty-claw-update-runbook/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

142,537 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: openclaw-update-runbook
description: Use when updating OpenClaw or debugging an OpenClaw instance after an update. This skill acts as a structured update runbook with emphasis on gateway startup, service-manager state, plugin registry and install drift, bundled-vs-npm/clawhub plugin confusion, stale config carried across upgrades, channel health, task ledger corruption, and logs that explain why the updated system is slow, disconnected, or half-broken.
version: 1.0.6
metadata:
  openclaw:
    emoji: "🦞"
---

# OpenClaw Update Runbook

Use this skill when an OpenClaw host was just updated, is about to be updated, or is behaving strangely after an update. It is a generic operator runbook, not a release-specific checklist.

This skill is meant to be installed as a folder, not copied as a single file. It expects `references/failure-patterns.md` to exist locally beside `SKILL.md` inside the same skill bundle.

The goal is not only to get it running, but to prove which layer is broken:

- service lifecycle and service-manager state
- host package version
- plugin/package compatibility
- config drift
- model/provider runtime routing
- channel health
- task ledger health
- cron/session isolation and channel-lane ownership
- runtime performance
- command-path and update-channel assumptions
- self-update hazards when an agent updates the gateway that is running it
- supply-chain and package-integrity spot checks after plugin/npm churn

## Quick workflow

1. Establish the real starting state.
   For remote multi-host updates, first prove SSH reachability to each host
   with a short timeout. If a host cannot be reached directly or through an
   available jump host, record it as a transport/access blocker instead of an
   OpenClaw update failure, because no OpenClaw command has executed on that
   host yet.

   If you are connected over non-interactive SSH, do not assume the
   login-shell `PATH` is available. First locate the binary with common install
   paths such as a package-manager prefix and `~/.local/bin/openclaw`, then
   export the correct `PATH` for the audit session.

   If the gateway process is owned by a different OS user than the SSH login
   user, run OpenClaw diagnostics as the gateway service user. The SSH user can
   have no `openclaw` on PATH, or a private package-manager shim can be
   unreadable, while the LaunchAgent/systemd service is healthy under another
   home directory. Derive the service user, state dir, CLI path, and port from
   the live process/service definition before running `doctor` or editing
   config.

   Check:
   - `openclaw --version`
   - `openclaw update status`
   - `openclaw status --deep`
   - `openclaw doctor --non-interactive --no-workspace-suggestions`
   - `openclaw channels status --deep`
   - `openclaw tasks audit`
   - current model routing: agent defaults, agent-level model maps, fallback chains, and cron payload models
   - recent successful sessions for the primary model and runtime, not j

README.md

# OpenClaw Update Runbook

An operator-focused skill and reference pack for updating OpenClaw, debugging post-update regressions, and proving which layer is actually broken before making changes.

This skill turns the update/debug process into a repeatable audit: establish the real host state, inspect service and plugin drift, verify model routing, then apply the smallest repair that makes the system consistent again.

Install or copy the whole folder so `SKILL.md` and `references/failure-patterns.md` stay together. The skill expects those files to exist side by side on disk.

## What it includes

- `SKILL.md`: the main update runbook skill
- `references/failure-patterns.md`: concrete regression patterns seen across multiple hosts
- `agents/openai.yaml`: lightweight agent metadata for skill catalogs that use it

## What it helps with

- confirming the real service state after an update
- separating service-manager issues from detached-process issues
- spotting bundled-vs-global plugin drift
- finding stale config that survives upgrades
- checking whether plugin install records match disk reality
- reading the right logs before changing too much
- cleaning up task ledger problems that keep a host noisy or half-broken

## Who this is for

- operators maintaining one or more OpenClaw hosts
- operators helping a team or another maintainer recover after an update
- anyone who wants a structured checklist for "OpenClaw feels broken after upgrade"

## Install

Place the folder where your agent skills live, or install it through a compatible skill manager.

Do not copy only `SKILL.md`. The skill refers to local companion files under `references/` and `agents/`.

The main entry point is:

- `SKILL.md`

## How to use

Invoke the skill when you are:

- upgrading OpenClaw
- checking health right after an upgrade
- debugging a host that became slow, disconnected, or inconsistent after update

The agent should start with `SKILL.md` and open `references/failure-patterns.md` only when the main workflow points to a known regression pattern or contradictory runtime symptoms.

The runbook is intentionally conservative: verify service reality first, inspect plugin and config drift second, then apply the smallest fix that makes the host consistent again.

## Maintenance model

This runbook is cumulative. New host-specific lessons should usually be added to `references/failure-patterns.md` rather than replacing existing guidance.

Contribution style:

- additive over destructive
- preserve older patterns unless they are clearly wrong
- keep examples generic and free of secrets or personal host details

## Suggested catalog description

Structured OpenClaw update runbook for AI-agent operators: service checks, plugin drift, config regressions, task cleanup, and post-upgrade debugging.

_meta.json

{
  "ownerId": "kn72yh2bfzkawx37gayv80km7186hw0q",
  "slug": "claw-update-runbook",
  "version": "1.0.6",
  "publishedAt": 1779987326552
}

references/failure-patterns.md

# Failure Patterns

Use this file when the main skill identifies a likely upgrade regression and you need concrete examples of what to inspect.

Contribution rule:
- append new patterns or expand existing ones
- do not delete older patterns unless they are proven false
- preserve examples from other hosts even if the current host is healthy

## 1. Update channel drift

Symptom:
- host is intentionally on beta or a newer stable build
- `status --deep` says local version is newer than `npm latest`
- config still says `"update.channel": "stable"` after a beta install

What to inspect:
- `openclaw --version`
- `openclaw status --deep`
- `openclaw.json` update metadata

Why it matters:
- operators get misleading update advice
- handoff notes should call out when install/update channel state is not persisted

## 2. Stale config after upgrade

Symptom:
- `doctor` says provider or plugin is unknown
- runtime falls back to auto-detect or legacy behavior
- helper commands claim to fix config, but warnings remain

Common keys:
- `tools.web.search.provider`
- `plugins.allow`
- `plugins.entries.*`

Typical example:
- `tools.web.search.provider=brave` remains after host/plugin changes and becomes invalid

## 3. Bundled plugin vs global npm plugin shadowing

Symptom:
- bundled capability should work after host upgrade
- `plugins list` shows a global plugin path under `~/.openclaw/npm/node_modules`
- plugin version does not match host version

Example:
- host on `<current-version>`
- global `@openclaw/discord` still at `<previous-version>`
- gateway warns about missing compiled runtime output because the global plugin is source-only

What to inspect:
- `openclaw plugins inspect <id>`
- plugin `source`
- plugin `origin`
- plugin `version`
- presence of `dist/`

## 4. Install records drift from disk reality

Symptom:
- config or install registry says a plugin is installed
- recorded path under `~/.openclaw/npm/node_modules/@openclaw/` or `~/.openclaw/extensions/` does not exist
- plugin not found / phantom allowlist warnings

What to inspect:
- `~/.openclaw/plugins/installs.json`
- actual install path on disk
- `openclaw plugins registry --refresh`

This is the case where reinstalling the plugin is often correct.

## 5. Third-party plugin runtime deps removed

Symptom:
- after `doctor --fix` or cleanup, a third-party plugin fails to load
- error looks like `Cannot find module ...`
- plugin root still exists, but plugin-side `node_modules` is gone

What to inspect:
- plugin package directory
- plugin `package.json`
- whether dependencies are externalized at build time

Why it matters:
- cleanup can be too aggressive for non-bundled plugins

## 6. Context engine not registered after restart

Symptom:
- logs say context engine falls back to legacy
- plugin may still be installed but failed to initialize

Look for:
- plugin load errors
- missing dependencies
- plugin contract warnings
- plugin registry metadata drift

## 7. Event loop degradation after update

Symptom

skill-card.md

## Description:

Use when updating OpenClaw or debugging an OpenClaw instance after an update. This skill acts as a structured update runbook with emphasis on gateway startup, service-manager state, plugin registry and install drift, bundled-vs-npm/clawhub plugin confusion, stale config carried across upgrades, channel health, task ledger corruption, and logs that explain why the updated system is slow, disconnected, or half-broken.

This skill is ready for commercial/non-commercial use.

## Publisher:

[bkf-gitty](https://clawhub.ai/user/bkf-gitty)

### License/Terms of Use:

MIT

## Use Case:

Operators and engineers use this skill to plan OpenClaw updates, diagnose post-update regressions, verify service and plugin state, and choose the smallest repair that returns a host to a healthy state.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Troubleshooting guidance can expose live channel tokens in terminal output, logs, or agent transcripts.

Mitigation: Do not run token-inspection commands that print raw values. If a token appears in a transcript, support ticket, log, or backup, rotate it and remove plaintext fallbacks after recovery.

Risk: Update, restart, or configuration-edit steps can affect a live OpenClaw host.

Mitigation: Use the skill only for explicit OpenClaw maintenance tasks, require confirmation before updates, restarts, or config edits, and verify host state before and after changes.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/bkf-gitty/skills/claw-update-runbook)
- [Failure Patterns](references/failure-patterns.md)
- [README](README.md)

## Skill Output:

**Output Type(s):** [Guidance, Shell commands, Configuration]

**Output Format:** [Markdown with inline shell commands and checklists]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Includes diagnostic sequences, verification criteria, and handoff-note guidance; does not execute commands itself.]

## Skill Version(s):

1.0.6 (source: frontmatter and server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

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!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

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

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.