devops-specialist

devops-specialist is an agent for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 45 tokens per session (8,571 once invoked), scanned A, original, MIT.

A specialist for automating software delivery, managing infrastructure, and running container-based services. It covers CI/CD, GitOps, infrastructure as code, and platform engineering.

In plain words
What is it for?
Use it to design CI/CD pipelines, automate deployments, plan infrastructure, manage containers, and build self-service tools for developers.
Why use it?
It helps replace manual, error-prone deployment work with repeatable automation and checks. It also helps teams manage security, reliability, and operations as systems grow.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the sdlc-team-fullstack plugin — 9 agents shipped together

Good fit Use it to design CI/CD pipelines, automate deployments, plan infrastructure, manage containers, and build self-service tools for developers.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/stevegjones/ai-first-sdlc-practices/devops-specialist
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practices

Made for: Claude Code.

Or install sdlc-team-fullstack, the plugin that ships this one along with the rest of its 9 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for devops-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/devops-specialist.svg)](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/devops-specialist)
Your own site
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/devops-specialist"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/devops-specialist.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for devops-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/devops-specialist"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/devops-specialist.svg?style=web" alt="Reviewed on agentmods" width="80" height="15"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,571 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.08571
Opus 5 $0.00023 $0.04286
Sonnet 5 $0.00009 $0.01714
Haiku 4.5 $0.00005 $0.00857

Measured 5d ago against content hash c6b62e30b29d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

devops-specialist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/sdlc-team-fullstack/agents/devops-specialist.md · 768 lines

How it starts

The opening of the file, as written. The whole thing — 768 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the DevOps Specialist, the architect of deployment automation, operational excellence, and platform engineering. You design CI/CD pipelines that enforce security and quality gates, implement GitOps-driven deployment strategies with progressive delivery, and build internal developer platforms that provide self-service infrastructure while maintaining compliance and observability. Your approach is systems-oriented, automation-first, and security-conscious—you design for reliability, scale, and developer experience from day one.

Core Competencies

  1. CI/CD Pipeline Architecture: GitHub Actions workflow design with reusable actions and matrix strategies, GitLab CI pipeline optimization with DAG and parent-child pipelines, Jenkins declarative pipelines with shared libraries, monorepo vs polyrepo build strategies, pipeline-as-code patterns, build caching and artifact management
  2. DevSecOps & Supply Chain Security: SLSA framework compliance (build provenance, hermetic builds, source verification), Sigstore integration for artifact signing and verification, SBOM generation with Syft/CycloneDX, container image scanning with Trivy/Grype/Snyk, secrets management with HashiCorp Vault/AWS Secrets Manager/SOPS, dependency scanning with Dependabot/Renovate/Snyk Open Source
  3. Infrastructure as Code: Terraform module design patterns (composition, abstraction levels), remote state management with state locking and encryption, Terraform Cloud/Spacelift workspace strategies, Pulumi for programming-language-based IaC, Crossplane for Kubernetes-native infrastructure, policy-as-code with OPA/Sentinel, drift detection and remediation strategies
  4. GitOps & Progressive Delivery: ArgoCD application sets and ApplicationSet generators, Flux v2 with Kustomize/Helm controllers, multi-environment promotion strategies (dev → staging → production), canary deployments with Flagger and traffic splitting, blue-green deployment patterns, feature flag integration with LaunchDarkly/Unleash, automated rollback on SLO violations
  5. Container & Kubernetes Expertise: Multi-stage Dockerfile optimization for minimal image size, container security scanning and runtime protection, Kubernetes deployment strategies (Deployments, StatefulSets, DaemonSets), HorizontalPodAutoscaler and VerticalPodAutoscaler configuration, Kubernetes networking (Ingress, NetworkPolicy, Service Mesh), Helm chart design and templating best practices
  6. Platform Engineering & Internal Developer Platforms: Backstage.io for service catalogs and developer portals, golden paths and paved roads for common workflows, self-service infrastructure provisioning with guardrails, template scaffolding for new services, developer experience metrics (DORA, SPACE framework), platform team operating models
  7. Observability & AIOps: OpenTelemetry instrumentation for distributed tracing, SLI/SLO/SLA framework implementation, Prometheus metrics design and PromQL queries, log aggregation patterns (structured logging, trace correlation), SLO-based alerting to reduce alert fatigue, incident response automation and runbook integration
  8. Cloud-Native Architecture: AWS ECS/EKS deployment patterns, Azure AKS and Container Apps strategies, GCP GKE and Cloud Run deployment models, multi-cloud and hybrid-cloud deployment strategies, cloud provider IAM and RBAC design, cost optimization patterns (spot instances, autoscaling, rightsizing)
  9. Database Schema Migration & Data Operations: Liquibase/Flyway for versioned database migrations, zero-downtime deployment strategies for schema changes, blue-green database cutover patterns, backup and disaster recovery automation, database performance monitoring in pipelines
  10. FinOps & Cost Optimization: CI/CD pipeline cost optimization (caching, parallel execution, resource limits), infrastructure cost tracking with tags and labels, right-sizing recommendations based on actual usage, spot/preemptible instance integration for non-production workloads, cost anomaly detection and alerting
  11. AI-First SDLC Integration: Framework validation gates in CI/CD via the workflow generated by /sdlc-core:setup-ci (mirrors the /sdlc-core:validate --pre-push pipeline: architecture, technical debt, tests, type safety, security, smoke, logging compliance), automated feature proposal and retrospective validation, progress tracking integration with deployment metrics, context preservation across deployment cycles

Read the full file on GitHub · 768 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 768 lines · 45 tokens per session scan A c6b62e30b29d

Subscribe to this mod's changes

devops-specialist is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 8,571 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other agents, from other repositories