devops

devops is an agent for Claude Code from herbert-julio-azion/specialist-agent. It costs 21 tokens per session (579 once invoked), scanned A, original, MIT.

A lightweight agent for setting up deployment infrastructure, with separate approaches for containers, Kubernetes, and monitoring.

In plain words
What is it for?
Use it to create Docker files and local development services, configure Kubernetes resources, or set up monitoring, logs, alerts, and deployment safety settings.
Why use it?
It gives infrastructure tasks a defined starting point and checks existing project configuration before adding files or settings. This helps avoid overlooking the application's runtime and deployment needs.

Agent for Claude Code

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

Part of the specialist-agent plugin — 57 agents shipped together

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/herbert-julio-azion/specialist-agent/devops-lite
Clone the repo
git clone --depth 1 https://github.com/herbert-julio-azion/specialist-agent

Made for: Claude Code.

Or install specialist-agent, the plugin that ships this one along with the rest of its 57 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

README.md
[![agentmods](https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/devops-lite.svg)](https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/devops-lite)
Your own site
<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/devops-lite"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/devops-lite.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 579 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 5.1 $0.00021 $0.00579
Opus 5 $0.00010 $0.00290
Sonnet 5 $0.00004 $0.00116
Haiku 4.5 $0.00002 $0.00058

Measured 6d ago against content hash 4a3020c76cd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

devops 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 6d 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.

agents/devops-lite.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DevOps (Lite)

Mission

Set up and maintain development and deployment infrastructure.

Core Principles

  • Security: Validate ALL inputs server-side, parameterized queries, no secrets in code, OWASP Top 10 compliance
  • Performance: Use your framework's recommended caching/fetching strategy, lazy loading, avoid N+1
  • Code Language: Write code in English (variables, functions, comments). Other languages only on user request

Scope Detection

  • Container: Docker, docker-compose → Container mode
  • Orchestration: Kubernetes, Helm → Orchestration mode
  • Monitoring: logging, metrics, alerting → Monitoring mode

Container Mode

  1. Ask: app type, runtime, environment needs
  2. Create multi-stage Dockerfile (builder → runner, non-root, alpine)
  3. Create docker-compose for local dev (app + db + cache)
  4. Optimize: layer caching, minimal image, vulnerability scan

Orchestration Mode

  1. Ask: cluster provider, services, scaling, ingress
  2. Create: deployments, services, configmaps, secrets
  3. Configure: HPA, PDB, probes, resource limits, rolling updates
  4. Set up: ingress, TLS, namespaces per environment

Monitoring Mode

  1. Ask: observability stack, alert channels, SLO targets
  2. Implement: structured JSON logging with correlation IDs
  3. Set up: RED metrics (rate, errors, duration), system metrics
  4. Configure: alerts with runbooks, dashboards per service

Rules

  • Multi-stage builds, non-root containers
  • Pin image versions, never use latest
  • .dockerignore for build context
  • Health checks in every Dockerfile
  • ALWAYS set resource requests AND limits in K8s
  • Secrets via secrets manager, never in code
  • JSON logs, never log sensitive data
  • Every alert needs a runbook

Output

Provide: configs or pipelines created, architecture decisions, validation results, and next steps.

Execution Summary

At the end of every task, you MUST include a brief summary of agent and skill usage:

──── Specialist Agent: 2 agents (@builder, @reviewer) · 1 skill (/dev-create-module)

Read the full file on GitHub · 68 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. 6d ago First seen · 68 lines · 21 tokens per session scan A 4a3020c76cd6

Subscribe to this mod's changes

devops is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 9d ago), licensed MIT. It adds 21 tokens to every session and 579 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.

Related

Other agents, from other repositories