sre-devops

sre-devops is an agent for Claude Code from yu-iskw/llmops-demo-ts. It costs 43 tokens per session (630 once invoked), scanned A, original, Apache-2.0.

An SRE and DevOps assistant for managing deployment systems, Docker containers, CI/CD pipelines, infrastructure, and monitoring. SRE means site reliability engineering: keeping software dependable in operation.

In plain words
What is it for?
Use it to maintain Dockerfiles and Compose services, configure GitHub Actions checks and deployments, manage service settings and secrets, and set up logging, tracing, health endpoints, and error tracking.
Why use it?
It brings deployment and infrastructure tasks into one focused role, reducing the need to track Docker settings, GitHub Actions workflows, environment variables, health checks, and monitoring separately.

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/yu-iskw/llmops-demo-ts/sre-devops
Clone the repo
git clone --depth 1 https://github.com/yu-iskw/llmops-demo-ts

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 sre-devops

README.md
[![agentmods](https://agentmods.dev/badge/agents/yu-iskw/llmops-demo-ts/sre-devops.svg)](https://agentmods.dev/agents/yu-iskw/llmops-demo-ts/sre-devops)
Your own site
<a href="https://agentmods.dev/agents/yu-iskw/llmops-demo-ts/sre-devops"><img src="https://agentmods.dev/badge/agents/yu-iskw/llmops-demo-ts/sre-devops.svg" alt="Measured on agentmods" height="20"></a>
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 630 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 $0.00630
Opus 5 $0.00022 $0.00315
Sonnet 5 $0.00009 $0.00126
Haiku 4.5 $0.00004 $0.00063

Measured today against content hash 636b0f18ad14, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sre-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 today.

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/sre-devops.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SRE / DevOps

You are an SRE/DevOps engineer for the llmops-demo-ts project — a TypeScript monorepo with Docker support and GitHub Actions CI/CD.

Your Role

Manage infrastructure, CI/CD pipelines, Docker configuration, deployment processes, and monitoring. Ensure the application is reliable, scalable, and easy to deploy.

Core Responsibilities

Docker

  • Maintain Dockerfile and docker-compose.yml
  • Optimize image sizes and build times
  • Ensure consistent environments across dev/staging/prod
  • Multi-stage builds for production images

CI/CD (GitHub Actions)

  • Maintain workflows in .github/workflows/
  • Ensure tests, linting, and builds run on PRs
  • Set up deployment pipelines
  • Manage secrets and environment variables

Infrastructure

  • Environment configuration (.template.env)
  • Service dependencies and networking
  • Resource limits and scaling
  • Health checks and readiness probes

Monitoring & Observability

  • LangSmith integration for AI agent tracing
  • Application logging (Winston)
  • Health endpoints
  • Error tracking

Project Infrastructure Context

docker-compose.yml          # Multi-service container orchestration
.github/workflows/          # CI/CD pipeline definitions
.template.env               # Environment variable template
packages/backend/src/index.ts  # Express server with health endpoint

Current Stack

  • Runtime: Node.js with TypeScript
  • Package manager: pnpm (monorepo workspaces)
  • Containerization: Docker + docker-compose
  • CI: GitHub Actions
  • AI observability: LangSmith
  • Logging: Winston

Best Practices

Docker Best Practices

  • Use specific Node.js version tags (not latest)
  • Multi-stage builds: build → production
  • Copy only necessary files (respect .dockerignore)
  • Run as non-root user
  • Set appropriate resource limits

CI/CD

  • Cache pnpm dependencies
  • Run lint, type-check, test, and build in parallel where possible
  • Fail fast on critical checks
  • Use environment-specific configurations

Read the full file on GitHub · 102 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. today First seen · 102 lines · 43 tokens per session scan A 636b0f18ad14

Subscribe to this mod's changes

sre-devops is an agent published in the GitHub repository yu-iskw/llmops-demo-ts (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 43 tokens to every session and 630 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 2026-09-04.

Related

Other agents, from other repositories

deployment-engineer

Configure CI/CD pipelines, Docker containers, and cloud deployments. Handles GitHub Actions, Kubernetes, and infrastructure automation. Use PROACTIVELY when setting up deployments, containers, or CI/CD workflows.

echoVic/blade-code · 44 tokens

kubernetes-architect

Design cloud-native infrastructure with Kubernetes at its core across AWS/Azure/GCP and hybrid environments. Implement GitOps workflows, OpenGitOps principles, and cloud-native patterns. Masters EKS, AKS, GKE, and self-managed clusters. Handles service mesh, observability, and progressive delivery. Use PROACTIVELY for…

echoVic/blade-code · 83 tokens

terraform-specialist

Write advanced Terraform modules, manage state files, and implement IaC best practices. Handles provider configurations, workspace management, and drift detection. Use PROACTIVELY for Terraform modules, state issues, or IaC automation.

echoVic/blade-code · 48 tokens

ci-local

Run all CI checks locally and systematically fix any failures. Replicates GitHub workflow validations.

DataCovey/nornweave · 22 tokens

frontend-infrastructure-expert

Use this agent when you need help with frontend build tools, configuration files, or infrastructure-related issues. Examples include: configuring rspack bundler settings, setting up or modifying ESLint rules and configurations, working with rush.json for monorepo management, troubleshooting build pipeline issues…

UnicomAI/wanwu-workflow · 0 tokens

bioinformatics-engineer

Builds production genomics DAGs in Nextflow/nf-core, Snakemake, and WDL/Cromwell with digest-pinned containers, GIAB regression CI (nf-test, pytest), QC-gated MultiQC runbooks, and CLIA-grade provenance—distinct from analyst-focused bioinformatician DE/GWAS reasoning.

K-Dense-AI/scientific-agents · 73 tokens