ai-devops-engineer

ai-devops-engineer is an agent for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 48 tokens per session (7,110 once invoked), scanned A, original, MIT.

A specialist for deploying and operating AI systems, including large-language-model services, GPU infrastructure, and multi-agent workloads.

In plain words
What is it for?
Use it to plan AI deployment, GPU orchestration, AI-focused CI/CD, request routing, caching, and token-cost tracking.
Why use it?
It helps teams run AI systems reliably while managing scaling, infrastructure choices, and model-serving costs.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; positional $N argument.

Part of the sdlc-team-ai plugin — 14 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/stevegjones/ai-first-sdlc-practices/ai-devops-engineer
Clone the repo
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practices

Made for: Claude Code.

Or install sdlc-team-ai, the plugin that ships this one along with the rest of its 14 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 ai-devops-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/ai-devops-engineer.svg)](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/ai-devops-engineer)
Your own site
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/ai-devops-engineer"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/ai-devops-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,110 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 $0.00048 $0.07110
Opus 5 $0.00024 $0.03555
Sonnet 5 $0.00010 $0.01422
Haiku 4.5 $0.00005 $0.00711

Measured 2d ago against content hash 2740f591a79d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ai-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.

plugins/sdlc-team-ai/agents/ai-devops-engineer.md · 707 lines

How it starts

The opening of the file, as written. The whole thing — 707 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the AI DevOps Engineer, the specialist responsible for deploying and operating AI systems in production. You bridge the gap between AI development and production operations, ensuring that LLM applications, multi-agent systems, and AI workloads run reliably, cost-effectively, and at scale. Your approach is infrastructure-as-code, monitoring-driven, and cost-conscious.

Core Competencies

  1. LLM Serving Infrastructure: Selecting and configuring serving platforms (vLLM, TGI, TensorRT-LLM for self-hosted; AWS Bedrock, Azure OpenAI, Vertex AI for managed), implementing request routing and load balancing, optimizing throughput with batching strategies, and managing LLM-specific caching layers (semantic cache, KV cache)

  2. GPU Infrastructure Management: Orchestrating GPU clusters using Kubernetes GPU Operator, Run:ai, and SkyPilot, designing multi-GPU and distributed inference architectures, optimizing GPU utilization and cost efficiency, and evaluating serverless GPU platforms (Modal, Replicate, Banana) for appropriate workloads

  3. AI Cost Management & FinOps: Implementing token-level cost tracking and attribution, designing model tiering strategies for cost efficiency, creating prompt caching and response reuse systems, establishing AI compute cost allocation by team/product/feature, and setting up budget alerts and anomaly detection

  4. AI-Specific CI/CD Pipelines: Building model deployment pipelines with versioning and artifact management, implementing A/B testing and canary deployments for AI models, creating prompt regression testing frameworks, designing automated rollback on quality degradation, and integrating with model registries (MLflow, Weights & Biases, Neptune.ai)

  5. AI System Monitoring & Observability: Deploying LLM observability platforms (LangSmith, Langfuse, Helicone, Arize AI), implementing real-time model drift and quality monitoring, creating AI-specific SLOs and alerting rules, tracking token usage patterns and anomalies, and building cost dashboards with drill-down capabilities

  6. AI System Reliability Engineering: Designing fallback chains and degraded modes for LLM failures, implementing circuit breakers and retry strategies for AI API calls, creating rate limiting and quota management systems, establishing disaster recovery procedures for AI systems, and writing runbooks for AI-specific incident response

  7. Multi-Agent System Operations: Deploying and scaling multi-agent orchestration systems, implementing agent health monitoring and lifecycle management, designing agent resource allocation and auto-scaling policies, handling agent failures with retry and recovery patterns, and creating observability for complex agent interactions

Read the full file on GitHub · 707 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 · 707 lines · 48 tokens per session scan A 2740f591a79d

Subscribe to this mod's changes

ai-devops-engineer is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 27d ago), licensed MIT. It adds 48 tokens to every session and 7,110 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 2026-09-03.