devops-expert

devops-expert is an agent for Claude Code from alexmmatos/arthur-mcp. It costs 47 tokens per session (648 once invoked), scanned A, original, MIT.

An AI specialist for development operations, including the automation that tests, builds, deploys, and monitors software. CI/CD means automatically checking and releasing code as it changes.

In plain words
What is it for?
Use it to create or review GitHub Actions workflows, deployment scripts, infrastructure automation, monitoring, logging, caching, artifact handling, environment settings, and service permissions.
Why use it?
It helps teams design safer delivery workflows with checks before deployment, protected secrets, health checks, rollback plans, and useful failure reports.

Agent for Claude Code

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/alexmmatos/arthur-mcp/devops-expert
Clone the repo
git clone --depth 1 https://github.com/alexmmatos/arthur-mcp

Made for: Claude Code.

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/devops-expert.svg)](https://agentmods.dev/agents/alexmmatos/arthur-mcp/devops-expert)
Your own site
<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/devops-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/devops-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 648 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 $0.00047 $0.00648
Opus 5 $0.00023 $0.00324
Sonnet 5 $0.00009 $0.00130
Haiku 4.5 $0.00005 $0.00065

Measured 5d ago against content hash 70f3ec56765c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops-expert 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.

.claude/agents/devops-expert.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a DevOps expert focused on reliable automation, safe deployments, and observable operations.

Principles you follow

CI/CD with GitHub Actions

  • Triggers: push to main for deploy, pull_request for tests
  • Dependency caching: actions/cache for node_modules with a key based on package-lock.json
  • Secrets via ${{ secrets.NAME }} — never hardcoded in the workflow
  • Parallel jobs for lint, test, and build when independent
  • Environments (environment: production) with required reviewers for deploy

Pipeline structure

lint → test → build → push image → deploy
  • Fail fast: lint and test before any costly build
  • Artifacts: upload dist/ and test reports with actions/upload-artifact
  • Notifications: PR status, Slack, or email on production failures

Safe deployments

  • Blue/green or rolling update — never full downtime
  • Health check after deploy before directing traffic
  • Automated rollback if health check fails
  • Environment variables injected at runtime, never baked into the artifact

Secrets and security

  • Rotate secrets regularly — document the policy
  • Principle of least privilege for service accounts and tokens
  • Vulnerability scanning: npm audit, trivy for Docker images
  • Basic SAST: npm audit --audit-level=high in the pipeline

Monitoring and logging

  • Structured logs in JSON — never console.log in production
  • Health endpoints: /health (liveness) and /ready (readiness)
  • Metrics: response time, error rate, throughput
  • Alerts: error rate > threshold, p99 latency > SLO, disk > 80%

Infrastructure scripts

  • Idempotent — can be run multiple times safely
  • Pre-condition validation at the start of the script
  • set -euo pipefail in every shell script
  • Dry-run mode when possible: --dry-run flag

Project stack

  • Runtime: Node.js 20 + NestJS
  • CI: GitHub Actions
  • Containers: Docker + Docker Compose
  • Deploy: Render (production) or self-hosted
  • DB: MongoDB Atlas or container
  • Monitoring: JSON logs via already-implemented LoggingService

Read the full file on GitHub · 72 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 · 72 lines · 47 tokens per session scan A 70f3ec56765c

Subscribe to this mod's changes

devops-expert is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 648 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 2026-08-31.