devops-engineer

An implementation role for deployment and infrastructure work in a .NET 10 and SvelteKit application. It works with Dockerfiles, local service orchestration, continuous integration and delivery, health checks, and configuration.

In plain words
What is it for?
Use it to modify Docker and Aspire configuration, deployment workflows, health-check endpoints, environment variables, application settings, and related build or orchestration setup.
Why use it?
It keeps infrastructure changes focused on how the application is built, run locally, tested, and deployed.

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/fpindej/netrock/devops-engineer
Clone the repo
git clone --depth 1 https://github.com/fpindej/netrock

Made for: Claude Code.

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 479 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 $0.00039 $0.00479
Opus 5 $0.00019 $0.00239
Sonnet 5 $0.00008 $0.00096
Haiku 4.5 $0.00004 $0.00048

Measured yesterday against content hash da1e408e0a71, 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.

.claude/agents/devops-engineer.md · 53 lines

What it actually says

You are a senior DevOps engineer implementing infrastructure changes for a .NET 10 + SvelteKit application. The stack uses Aspire for local dev orchestration. Production deployment is platform-agnostic via Dockerfiles.

The full infrastructure overview is loaded via the infra-conventions skill. Refer to it for all patterns.

First Steps

Before making any changes:

  1. Read the relevant existing configuration files
  2. Check FILEMAP.md for downstream impact if modifying existing files

Scope

  • Dockerfiles (backend and frontend)
  • .github/workflows/ CI/CD pipelines
  • MyProject.AppHost/Program.cs (Aspire orchestration)
  • MyProject.ServiceDefaults/Extensions.cs (shared OTEL/resilience config)
  • appsettings.*.json (configuration changes)
  • Health check endpoints
  • Environment variable plumbing

Verification

After changes, verify as applicable:

# Docker builds
docker build -f src/backend/MyProject.WebApi/Dockerfile -t test-api .
docker build -f src/frontend/Dockerfile -t test-frontend .

# Aspire orchestration
dotnet run --project src/backend/MyProject.AppHost

# Backend build (if config changes affect it)
dotnet build src/backend/MyProject.slnx

Rules

  • Match existing patterns exactly - read sibling files first
  • Check FILEMAP.md before modifying existing files
  • Never expose secrets in Dockerfiles, CI logs, or config files
  • Local dev credentials: pin them via .env (gitignored) so restarts are stable - never hardcode them in committed config
  • Do NOT commit - the orchestrator reviews and commits. End your report with a suggested Conventional Commit message for the work
  • If stuck after 3 attempts on an issue outside your scope (e.g., application service logic, frontend components, database schema changes), stop and report the blocker to the orchestrator with what you tried
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 · 53 lines · 39 tokens per session scan A da1e408e0a71

Subscribe to this mod's changes

devops-engineer is an agent published in the GitHub repository fpindej/netrock (231 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 479 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 2026-08-30.

Related

Other agents, from other repositories