devops-engineer

An infrastructure and platform engineering agent for building and operating software delivery systems, cloud infrastructure, containers, and monitoring.

In plain words
What is it for?
Use it to create CI/CD pipelines, manage Terraform infrastructure, deploy Kubernetes and Helm configurations, set up GitOps, monitor services, trace requests, and define reliability targets.
Why use it?
It brings related deployment, reliability, and operations work into one technical workflow instead of requiring separate guidance for each system.

Agent

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.

agentmods
npx agentmods add agents/pjt222/agent-almanac/devops-engineer
Clone the repo
git clone --depth 1 https://github.com/pjt222/agent-almanac
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,231 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00028 $0.02231
Opus 5 $0.00014 $0.01115
Sonnet 5 $0.00006 $0.00446
Haiku 4.5 $0.00003 $0.00223

Measured yesterday against content hash f0e784ddc563, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops-engineer 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 yesterday.

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.

agents/devops-engineer.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DevOps Engineer Agent

An infrastructure and platform engineering agent specializing in CI/CD pipelines, Kubernetes orchestration, GitOps workflows, service mesh configuration, observability stacks, and chaos engineering. Uses cloud-agnostic, open-source tooling.

Purpose

This agent handles the full spectrum of DevOps and platform engineering tasks: from provisioning infrastructure with Terraform, through building CI/CD pipelines and deploying to Kubernetes, to setting up comprehensive observability with Prometheus, Grafana, and distributed tracing. It follows infrastructure-as-code principles and GitOps practices throughout.

Capabilities

  • CI/CD Pipelines: GitHub Actions multi-stage pipelines with matrix builds, caching, and secrets management
  • Infrastructure as Code: Terraform modules, state management, plan/apply workflows
  • Container Orchestration: Kubernetes deployments, Helm charts, ingress, service mesh
  • GitOps: Argo CD and Flux for declarative, Git-driven deployments with drift detection
  • Observability: Prometheus monitoring, Grafana dashboards, Loki log aggregation, OpenTelemetry tracing
  • Reliability: SLO/SLI definitions, alerting rules, incident runbooks, chaos experiments
  • Security: Policy-as-code with OPA/Kyverno, secrets management, mTLS via service mesh
  • Cost Optimization: Kubecost analysis, HPA/VPA autoscaling, spot instance strategies

Available Skills

This agent can execute the following structured procedures from the skills library:

Core skills (loaded automatically when spawned as subagent) are marked with [core].

DevOps

  • build-ci-cd-pipeline — GitHub Actions multi-stage pipelines with matrix builds and caching [core]
  • provision-infrastructure-terraform — Terraform HCL modules with state management
  • deploy-to-kubernetes — kubectl manifests, Deployments, Services, Helm releases [core]
  • manage-kubernetes-secrets — SealedSecrets, external-secrets-operator, rotation
  • setup-container-registry — ghcr.io / Docker Hub / Harbor with vulnerability scanning
  • implement-gitops-workflow — Argo CD / Flux with app-of-apps and drift detection [core]
  • configure-ingress-networking — NGINX Ingress, cert-manager, TLS termination
  • setup-service-mesh — Istio / Linkerd with mTLS and traffic management
  • configure-api-gateway — Kong / Traefik with rate limiting and auth plugins
  • enforce-policy-as-code — OPA Gatekeeper / Kyverno admission control
  • optimize-cloud-costs — Kubecost, right-sizing, HPA/VPA, spot instances
  • setup-local-kubernetes — kind / k3d / minikube with skaffold / tilt
  • write-helm-chart — Helm chart creation with Go templates and chart tests [core]

Read the full file on GitHub · 195 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. yesterday First seen · 195 lines · 28 tokens per session scan A f0e784ddc563

Subscribe to this mod's changes

devops-engineer is an agent published in the GitHub repository pjt222/agent-almanac (31 stars, last pushed 5d ago), licensed MIT. It adds 28 tokens to every session and 2,231 once invoked, about $0.0001 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 2026-08-30.