DevOps & Deployment for Claude Code

Use when working on infrastructure as code, multi-cloud provisioning, and modular architecture, including Terraform best practices, state management, and enterprise patterns, with emphasis on reusability, security, and automation.

Use when building robust test frameworks, CI/CD integration, and comprehensive test coverage, including multiple automation tools and frameworks, with emphasis on maintainable, scalable, and efficient automated testing solutions.

Use when working on full-stack development, performance optimization, and enterprise solutions, including custom theme/plugin development, multisite management, security hardening, and scaling WordPress from small sites to enterprise platforms handling millions of visitors.

Adversarial post-deploy verifier. Use IMMEDIATELY after any systemctl restart or service redeploy. Catches silent skip when config was edited but daemon wasn't reloaded; catches accidental cascade restarts of untouched services. Snapshots pre/post timestamps, verifies a config-drift gate logged in the journal, validates expected config keys loaded in-memory (not just on disk), confirms sibling services weren't bumped. Optionally auto-rolls back if a backup_path is provided.

Agent that receives a specific TASK within a WORK and implements the actual code. Automatically invoked by the scheduler. Performs all implementation work including file creation, modification, and configuration changes.

Manages the ops background daemon — start, stop, restart services, check health

The Watcher of the dev team. The SRE/security mind with a twist. Thinks about second-order effects, failure modes nobody plans for, and what happens when things go sideways at 3am.

Diagnoses and auto-fixes ops plugin configuration errors, manifest issues, broken permissions, invalid JSON, and stale cache copies.

Developer and Software Architect agent for architecture decisions, full-stack implementation, code writing, testing, infrastructure, CI/CD, and technical documentation. Use for any coding, implementation, architecture, refactoring, or technical task.

Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.

Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.

Multi-service infrastructure health checker. Probes every AWS service the caller has IAM access to (ECS, EC2, RDS, Lambda, S3, CloudFront, ALB/NLB, API Gateway, SQS, SNS, DynamoDB, ElastiCache, Route 53, ACM, CloudWatch, Budgets, IAM) plus Vercel and GitHub Actions. Returns structured JSON with service health, accessible/inaccessible service lists, and severity-ranked anomaly flags. Used by ops-fires and ops-deploy.

Lightweight APM and metrics probe agent. Queries Datadog, New Relic, and OpenTelemetry backends for active alerts, error traces, and entity health. Returns structured JSON. Read-only — used by ops-monitor skill.

Git, PR, and CI status scanner across all registered repos. Returns structured JSON with branch state, uncommitted files, open PRs, and CI status for each project.

Mechanical scp-and-spawn for autonomous Claude Code agents on a remote host. Use when a task exceeds Claude Code's interactive timeout, when work needs to run on a different machine than the human, or when delegating to a long-running agent. Captures the actual claude binary PID (not the bash wrapper PID — load-bearing detail), saves to a PID file, and returns DISPATCHED or BLOCKED with structured evidence. Does not interpret the spec, modify it, or make strategic decisions — purely a launch pri

Agent that manages the TASK dependency DAG for a specific WORK and executes the pipeline. Must be used for requests like "run WORK-XX", "execute pipeline", "next task". Reads the WORK's PLAN.md and dispatches builder → verifier → committer sequentially according to dependency order.

Use this agent to autonomously build, test, and deploy complete applications from plain-English descriptions. Runs a 9-phase pipeline across 4 stacks with enterprise-grade safety hooks.

Technical health agent. Analyzes architecture, tech debt, production risks, scalability limits, and cut corners. Brutally honest about what will break.

Implements A2A JSON-RPC protocol for communicating between Claude Code and Vertex AI ADK agents, including AgentCard discovery, session management, async polling, and multi-agent orchestration patterns. Use when integrating with deployed ADK agents on Agent Engine or setting up inter-agent workflows. Trigger with \"set up A2A client\", \"connect to an ADK agent\".

Engineering lead that translates product briefs into scoped work, dispatches specialists, and delivers unified output. Use when you need technical architecture decisions or multi-specialist coordination. Trigger with "scope this feature", "dispatch the engineering team".

Use this agent for bd/Dolt incident response — a dolt-server that won't start or has orphaned, server sprawl, suspected lost writes after rapid bd updates, JSONL that lags the database, or migrating a workspace between embedded and server mode. It knows the rapid-write race is already fixed in bd 1.0.4 and that residual lag is only the JSONL export throttle.

Design API benchmarks, profile p50/p95/p99 latency, set up throughput tests, and detect performance regressions with k6/wrk. Use when establishing baselines or catching latency regressions in CI. Trigger with "benchmark this API", "set up a performance test".

Design MITRE ATT&CK-mapped detection rules, CIS-benchmarked hardening playbooks, and SOC triage procedures to reduce attacker dwell time. Use when building defensive security controls or auditing detection coverage. Trigger with "design detection rules", "write a hardening playbook".

Design application-layer caching strategies covering Redis/Memcached patterns, key namespacing, TTL, eviction policies, and thundering-herd prevention. Use when adding or auditing caching to reduce database load. Trigger with "design a caching strategy", "audit Redis usage".

Secures the software supply chain via SBOM generation, dependency scanning, and license compliance. Use when you need to audit transitive dependencies, detect CVEs in CI, or assess third-party vendor risk. Trigger with \"scan my dependencies\", \"generate an SBOM\".

Designs controlled failure experiments to expose resilience gaps before production incidents do. Use when you need a chaos experiment hypothesis, a game day plan, or a blast-radius-limited resilience audit. Trigger with \"design a chaos experiment\", \"plan a game day\".

Designs and executes controlled chaos experiments — failure injection, latency simulation, resource exhaustion — following the scientific method with defined abort conditions and recovery validation. Use when hardening a system against cascading failures or preparing for GameDays. Trigger with "design chaos experiment", "test system resilience".

Designs, optimizes, and troubleshoots CI/CD pipelines across GitHub Actions, GitLab CI, CircleCI, and Jenkins with production-ready YAML and setup instructions. Use when building or fixing a pipeline. Trigger with \"set up ci/cd\", \"optimize my pipeline\".

Designs and maintains CI/CD pipelines (GitHub Actions, GitLab CI, CircleCI) including builds, tests, quality gates, secrets management, and deployment strategies, then reports conformity with sprint specs. Use when setting up or fixing CI/CD for a project. Trigger with "set up CI/CD", "fix pipeline".

Triage a failed or slow Databricks cluster by fanning out parallel root-cause threads — one per cause class (provisioning, network/NPIP, init-script, driver, spot/shuffle) — over the cluster's live event stream, then aggregate to the single most-likely cause with its evidence. Use when a cluster failed to start, died mid-run, or is inexplicably slow. Trigger with "why did this cluster fail", "investigate cluster", "triage cluster start".

Designs model serving infrastructure, blue/green rollouts, and canary release plans with explicit rollback triggers. Use when you need inference API configuration, a traffic-splitting strategy, or a deployment topology audit. Trigger with \"design the model serving setup\", \"plan a canary release\".

Deployment strategy and release management expert covering blue/green, canary, rolling, and recreate patterns across Kubernetes, AWS ECS, GCP, and Azure. Use when planning a production rollout, choosing a deployment strategy, or designing rollback procedures. Trigger with \"deployment strategy\", \"zero-downtime deploy\".

Use when reviewing CI/CD pipelines, infrastructure-as-code, container/build config, deployment, or observability changes — verifies operational safety against the devops persona standards.

Analyzes Dockerfiles and produces optimized multi-stage builds, .dockerignore files, and docker-compose configs that shrink image size by 80-90% and enforce security best practices. Use when optimizing container builds or starting a new Dockerfile. Trigger with \"optimize my dockerfile\", \"reduce docker image size\".

Use this agent when bead work is not visible on DoltHub, when configuring or repairing a bd Dolt remote, when deciding between bd backup and bd dolt push, when taming sprawled per-project dolt servers by reaping idle ones, or when diagnosing Dolt-remote drift. It knows the #1 root cause (no remote configured) and that a DoltHub repo must already exist before a push.

Designs CDN configurations, cache strategies, and edge function deployments to minimize latency globally. Use when you need to optimize cache hit ratios, design edge routing, or deploy Cloudflare Workers/Lambda@Edge. Trigger with \"design CDN config\", \"optimize cache strategy\".

Automate FairDB PostgreSQL-as-a-Service operations — proactive monitoring, incident response, customer onboarding, backup verification, query optimization, and capacity planning with a human-escalation decision framework. Use when handling routine maintenance, investigating performance incidents, or provisioning a new database customer. Trigger with \"fairdb operations\", \"run health check\".

Triages and resolves FairDB PostgreSQL production incidents using a P0–P3 severity protocol — diagnosing disk, connection, and performance failures, then generating incident reports and stakeholder communications. Use when a FairDB database is down or degraded. Trigger with "database is down", "FairDB incident".

Audits FairDB VPS instances at three depth levels against SOP-001 (security), SOP-002 (PostgreSQL config), and SOP-003 (backup integrity), producing a scored compliance report with remediation steps. Use when validating a server's configuration or preparing for a compliance review. Trigger with "audit this FairDB server", "run a compliance check".