Files
claude-howto/07-plugins/devops-automation
Luong NGUYEN 343d6f0f99 docs: sync to Claude Code v2.1.220
Bumps tutorial coverage from the v2.1.217 baseline (2026-07-22 sync) to
v2.1.220 — three contiguous releases (v2.1.218–v2.1.220).

Critical fixes:

- Nested subagent spawning is on by default again at depth 3 (v2.1.219).
  Five locations across 04-subagents, CATALOG, 10-cli and QUICK_REFERENCE
  stated it was disabled by default — true for v2.1.217–v2.1.218 only.
  CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH=1 now disables rather than enables.
  All five carry an identical three-era history note.
- Claude Opus 5 is the default Opus model (v2.1.219). 10-cli asserted
  "Opus 4.8 remains the default"; Opus 5 was absent from every model table.
  Added to both model tables, 19 Compatible Models footers, and ~20
  effort-level enumerations.

Also fixed: fast-mode model list, auto-mode eligibility self-contradiction
in 09-advanced-features, stale CLAUDE_CODE_ENABLE_AUTO_MODE opt-in in
CATALOG, hook-event count disagreement (29/30 -> 31 across three files),
doc-generator skill name/directory mismatch, stale "May 2026" headings,
and the last three docs.anthropic.com links.

Added: DirectoryAdded hook, /deep-research explicit-invocation note,
/code-review background subagent, context:fork background default, agent
frontmatter hook workspace trust, dynamic workflow size guideline and
workflowSizeGuideline key, sandbox.network.strictAllowlist, MCP error
surfacing, stream-json nested subagent forwarding, frontmatter boolean
values, agent name ':' rejection, auto/plan-mode classifier changes, and
Opus 5 safety-classifier fallback.

Renamed the deep-research skill example to topic-research to stop it
shadowing the built-in; mirrored to vi/ja/uk. doc-generator rename
mirrored to ja/zh/uk.
2026-07-29 15:01:31 +07:00
..
2026-07-29 15:01:31 +07:00

Claude How To

DevOps Automation Plugin

Complete DevOps automation for deployment, monitoring, and incident response.

Features

Automated deployments Rollback procedures System health monitoring Incident response workflows Kubernetes integration

Installation

/plugin install devops-automation

What's Included

Slash Commands

  • /deploy - Deploy to production or staging
  • /rollback - Rollback to previous version
  • /status - Check system health
  • /incident - Handle production incidents

Subagents

  • deployment-specialist - Deployment operations
  • incident-commander - Incident coordination
  • alert-analyzer - System health analysis

MCP Servers

  • Kubernetes integration

Scripts

  • deploy.sh - Deployment automation
  • rollback.sh - Rollback automation
  • health-check.sh - Health check utilities

Hooks

  • pre-deploy.js - Pre-deployment validation
  • post-deploy.js - Post-deployment tasks

Usage

Deploy to Staging

/deploy staging

Deploy to Production

/deploy production

Rollback

/rollback production

Check Status

/status

Handle Incident

/incident

Requirements

  • Claude Code 1.0+
  • Kubernetes CLI (kubectl)
  • Cluster access configured

Configuration

Set up your Kubernetes config:

export KUBECONFIG=~/.kube/config

Example Workflow

User: /deploy production

Claude:
1. Runs pre-deploy hook (validates kubectl, cluster connection)
2. Delegates to deployment-specialist subagent
3. Runs deploy.sh script
4. Monitors deployment progress via Kubernetes MCP
5. Runs post-deploy hook (waits for pods, smoke tests)
6. Provides deployment summary

Result:
✅ Deployment complete
📦 Version: v2.1.0
🚀 Pods: 3/3 ready
⏱️  Time: 2m 34s

Last Updated: July 29, 2026 Claude Code Version: 2.1.220 Sources: