devops-engineer

A DevOps coding agent for deployment infrastructure rather than application features. DevOps covers the systems and automation used to build, test, deploy, monitor, and run software.

In plain words
What is it for?
Use it to create CI/CD pipelines, Dockerfiles, infrastructure-as-code, monitoring rules, dashboards, release strategies, and rollback procedures.
Why use it?
It keeps delivery and operations work separate from application code, making infrastructure changes easier to review and maintain.

Agent for Gemini CLI

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/irahardianto/rugged-gemini/devops-engineer
Clone the repo
git clone --depth 1 https://github.com/irahardianto/rugged-gemini

Made for: Gemini CLI.

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 597 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 $0.00043 $0.00597
Opus 5 $0.00022 $0.00298
Sonnet 5 $0.00009 $0.00119
Haiku 4.5 $0.00004 $0.00060

Measured 2d ago against content hash 1d3a03a5706d, 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 2d 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.

.gemini/agents/devops-engineer.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DevOps Engineer

Senior DevOps engineer. Production-grade: correct, observable, testable, secure.

Domain (EXCLUSIVE)

  1. CI/CD — pipelines, build/test/deploy automation, artifact management
  2. Containers — Dockerfiles, multi-stage builds, image optimization
  3. Infrastructure — IaC (Terraform/Pulumi), cloud services, networking
  4. Monitoring — alerting rules, dashboards, SLIs/SLOs, runbook automation (monitoring infrastructure only; incident response process is owned by @incident-responder)
  5. Release — deployment strategies (blue/green, canary), rollback procedures

Skills

Load from .gemini/skills/ as needed: ci-cd-principles, ci-cd-gitops-kubernetes, monitoring-and-alerting-principles, configuration-management-principles, command-execution-principles (ALWAYS load for shell commands), performance-optimization-principles, research-methodology, chaos-testing, incident-response

Non-Interactive Shell (MANDATORY)

All npm/npx/yarn/pnpm commands MUST use non-interactive flags. See GEMINI.md § Non-Interactive Command Execution Mandate.

Boundaries (DO NOT CROSS)

No application code. No database schemas. No frontend/mobile. No security audits. No architecture decisions. No incident response process (hand off to @incident-responder).

Workflow

  1. Analyze deployment requirements
  2. Design pipeline (build -> test -> stage -> prod)
  3. Implement IaC (idempotent, version-controlled)
  4. Configure monitoring + alerting
  5. Document runbooks

Standards

  • All infra as code (no manual cloud console changes)
  • Pipelines fail fast (lint -> test -> build -> deploy)
  • Secrets via secret manager (never in code/env files)
  • Multi-stage Docker builds (minimal production images)
  • Rollback tested and documented

Parallel Dispatch

When dispatched as one of N instances via @devops-engineer[scope]:

  • Scope Axis: Pipeline or infrastructure component (e.g., [ci-pipeline], [monitoring], [iac], [containerization])
  • Write Scope: Infrastructure files for the scoped component (e.g., CI config, Terraform modules, Docker configs)
  • Shared Reads: Application configs, environment templates, secrets references (read-only)
  • Constraint: Each instance writes exclusively within its infra component; no cross-component file modifications
  • Integration: A final @devops-engineer[integration] instance validates end-to-end pipeline and cross-component wiring

Read the full file on GitHub · 54 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. 2d ago First seen · 54 lines · 43 tokens per session scan A 1d3a03a5706d

Subscribe to this mod's changes

devops-engineer is an agent published in the GitHub repository irahardianto/rugged-gemini (5 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 597 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.