Openclaw Ops — Security skill for Claude Code
OpenClaw operations skill with health checks, repair scripts, watchdogs, update triage, and security scans.
How to install Openclaw Ops
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open cathrynlavery/openclaw-ops and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Openclaw Ops does
OpenClaw operations skill with health checks, repair scripts, watchdogs, update triage, and security scans.
Alternatives in Security
- Google MCP Security Servers — Security Operations and Threat Intelligence MCP servers 453 ★
- Perplexity Super Skills — Complete collection of 12 Perplexity Computer Super-Skills merging Perplexity + Claude Code capabilities acros 346 ★
- Sovereign Skills — 20 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session man 125 ★
README
openclaw-ops
OpenClaw gateway operations skill for agent environments. Covers health checks, repair workflows, continuous monitoring, session analysis, update-change detection, and security review for a local or self-hosted OpenClaw install.
Tested against OpenClaw `2026.5.4`.
What it does
Skill
/openclaw-ops— full triage and configuration: gateway, auth, exec approvals, cron jobs, channels, sessions, and installation
Scripts
| Script | Purpose |
|---|---|
scripts/heal.sh |
One-shot auto-fix for the most common gateway issues |
scripts/post-update.sh |
Explicit post-update orchestrator: check-update, heal, workspace reconcile, security scan, final health check, policy-guard sentinel trigger |
scripts/watchdog.sh |
Runs every 5 min, restarts gateway if down, escalates after 3 failures |
scripts/watchdog-install.sh |
Installs the watchdog as a macOS LaunchAgent |
scripts/watchdog-uninstall.sh |
Removes the LaunchAgent |
scripts/check-update.sh |
Detects version changes, explains broken config, auto-fix with --fix |
scripts/health-check.sh |
Declarative URL/process health checks; auto-generates targets file on first run |
scripts/security-scan.sh |
Config hardening and credential exposure scan (0–100 score); skips bulky runtime/log/session history unless --include-sessions is passed |
scripts/skill-audit.sh |
Static security audit for third-party skills before installation |
scripts/codex-perf-check.sh |
Check and fix GPT-5.x performance opt-ins that ship disabled by default; --fix to apply |
scripts/workspace-auto-commit.sh |
Local-only git snapshot helper for OpenClaw workspace repos; defaults to ~/.openclaw/workspace, supports --workspace and --all, never pushes |
scripts/workspace-git-audit.sh |
Audits ~/.openclaw/workspace* repos for git status and auto-commit cron coverage; --show-cron prints setup commands for uncovered repos |
scripts/session-monitor.sh |
Related Skills
Openclaw Config Pack
Hardened configuration pack for OpenClaw personal AI assistant — 9-layer security, Telegram topics, plugins, s
Cybersecurity Automation Portfolio 30 n8n Workflows
30 ready-to-import n8n workflows for security operations across three tiers (Basic, Mid, Advanced). They cover
Security Notice Response
Config-driven Claude Code skill: triage a security/malfunction notice for a client website, fix or delegate it
Fake Foreign Health Audit
OpenClaw skill:鉴别药品/保健品是否为「假洋货」(伪造洋品牌身份)。覆盖 9 个法域的官方数据库、工商登记与渠道核查。
Exobrain Audit
Audit the Exobrain harness REPO itself -- scans tracked files for leaked personal data, checks legibility for
Claude Doctor Skill
46 automated checks across 6 layers. Project health audit skill for Claude Code. Security first. Zero dependen
Related Agents
Observability Ops Reviewer
Reviewer for observability and operations — logging, metrics, tracing, alerting, health checks, and incident r
Ops Steward
Operations steward. Use daily (scheduled) or on demand to route the owner's replies to [DevTeam: ...] emails b
QA Release Ops
ADLC Agent 4 — integration/regression tests, eval suite, blocking security gate on stage:qa PRs; drafts the Ga