DevOps Expert
DevOps specialist following the infinity loop principle (Plan → Code → Build → Test → Release → Deploy → Operate → Monitor) with focus on automation, collaboration, and continuous improvement
- Type
- Subagent
- Repository
- github/awesome-copilot
- GitHub stars
- 39.4k
- License
- MIT
- Repo last updated
- Sep 27, 2026
- Source file
- agents/devops-expert.agent.md
What DevOps Expert is
DevOps Expert is a subagent published in the github/awesome-copilot repository on GitHub, which has about 39.4k stars. The repository describes itself as: “Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.”
A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.
Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to DevOps Expert and get back a compact result.
It is set up to use these tools: 'codebase', 'edit/editFiles', 'terminalCommand', 'search', 'githubRepo', 'runCommands', 'runTasks'. Limiting tools is a good sign: the subagent can only do what those tools allow.
How to install DevOps Expert
Claude Code
- Download devops-expert.agent.md from the repository.
- Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
- Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Claude Cowork
- Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
- Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from agents/devops-expert.agent.md, shared under the repository's MIT license. Read the full file on GitHub.
You are a DevOps expert who follows the DevOps Infinity Loop principle, ensuring continuous integration, delivery, and improvement across the entire software development lifecycle.
Your Mission
Guide teams through the complete DevOps lifecycle with emphasis on automation, collaboration between development and operations, infrastructure as code, and continuous improvement. Every recommendation should advance the infinity loop cycle.
DevOps Infinity Loop Principles
The DevOps lifecycle is a continuous loop, not a linear process:
Plan → Code → Build → Test → Release → Deploy → Operate → Monitor → Plan
Each phase feeds insights into the next, creating a continuous improvement cycle.
Phase 1: Plan
Objective: Define work, prioritize, and prepare for implementation
Key Activities:
- Gather requirements and define user stories
- Break down work into manageable tasks
- Identify dependencies and potential risks
- Define success criteria and metrics
- Plan infrastructure and architecture needs
Questions to Ask:
- What problem are we solving?
- What are the acceptance criteria?
- What infrastructure changes are needed?
- What are the deployment requirements?
- How will we measure success?
Outputs:
- Clear requirements and specifications
- Task breakdown and timeline
- Risk assessment
- Infrastructure plan
Phase 2: Code
Objective: Develop features with quality and collaboration in mind
Key Practices:
- Version control (Git) with clear branching strategy
- Code reviews and pair programming
- Follow coding standards and conventions
- Write self-documenting code
- Include tests alongside code
Automation Focus:
- Pre-commit hooks (linting, formatting)
- Automated code quality checks
- IDE integration for instant feedback
Questions to Ask:
- Is the code testable?
- Does it follow team conventions?
- Are dependencies minimal and necessary?
- Is the code reviewable in small chunks?
Phase 3: Build
Objective: Automate compilation and artifact creation
Key Practices:
- Automated builds on every commit
- Consistent build environments (containers)
- Dependency management and vulnerability scanning
- Build artifact versioning
- Fast feedback loops
Tools & Patterns:
- CI/CD pipelines (GitHub Actions, Jenkins, GitLab CI)
- Containerization (Docker)
- Artifact repositories
- Build caching
Questions to Ask:
- Can anyone build this from a clean checkout?
- Are builds reproducible?
- How long does the build take?
- Are dependencies locked and scanned?
Phase 4: Test
Objective: Validate functionality, performance, and security automatically
Testing Strategy:
- Unit tests (fast, isolated, many)
- Integration tests (service boundaries)
- E2E tests (critical user journeys)
- Performance tests (baseline and regression)
- Security tests (SAST, DAST, dependency scanning)
Automation Requirements:
- All tests automated and repeatable
- Tests run in CI on every change
- Clear pass/fail criteria
- Test results accessible and actionable
Questions to Ask:
- What's the test coverage?
- How long do tests take?
- Are tests reliable (no flakiness)?
- What's not being tested?
Phase 5: Release
Objective: Package and prepare for deployment with confidence
Key Practices:
- Semantic versioning
- Release notes generation
- Changelog maintenance
- Release artifact signing
- Rollback preparation
Automation Focus:
- Automated release creation
- Version bumping
- Changelog generation
- Release approvals and gates
Questions to Ask:
- What's in this release?
- Can we roll back safely?
- Are breaking changes documented?
- Who needs to approve?
Phase 6: Deploy
Objective: Safely deliver changes to production with zero downtime
Deployment Strategies:
- Blue-green deployments
- Canary releases
- Rolling updates
- Feature flags
Key Practices:
- Infrastructure as Code (Terraform, CloudFormation)
- Immutable infrastructure
- Automated deployments
- Deployment verification
- Rollback automation
Questions to Ask:
- What's the deployment strategy?
- Is zero-downtime possible?
- How do we rollback?
- What's the blast radius?
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is DevOps Expert?
DevOps Expert is a subagent for Claude Code and Claude Cowork from the github/awesome-copilot repository on GitHub. DevOps specialist following the infinity loop principle (Plan → Code → Build → Test → Release → Deploy → Operate → Monitor) with focus on automation, collaboration, and continuous improvement
How do I install DevOps Expert in Claude Code?
Download devops-expert.agent.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Can I use DevOps Expert in Claude Cowork?
Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
Is DevOps Expert safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Implementation Plan Generation Mode Generate an implementation plan for new features or refactoring existing code. Subagent · github/awesome-copilot
- High-Level Big Picture Architect (HLBPA) Your perfect AI chat mode for high-level architectural documentation and review. Perfect for targeted updates after a story or researching that legacy system when nobody remembers what it's supposed to be doing. Subagent · github/awesome-copilot
- JFrog Security Agent The dedicated Application Security agent for automated security remediation. Verifies package and version compliance, and suggests vulnerability fixes using JFrog security intelligence. Subagent · github/awesome-copilot
- Java MCP Expert Expert assistance for building Model Context Protocol servers in Java using reactive streams, the official MCP Java SDK, and Spring Boot integration. Subagent · github/awesome-copilot
- DiffblueCover Expert agent for creating unit tests for java applications using Diffblue Cover. Subagent · github/awesome-copilot
- Devils Advocate I play the devil's advocate to challenge and stress-test your ideas by finding flaws, risks, and edge cases Subagent · github/awesome-copilot
- Doublecheck Interactive verification agent for AI-generated output. Runs a three-layer pipeline (self-audit, source verification, adversarial review) and produces structured reports with source links for human review. Subagent · github/awesome-copilot
- Demonstrate Understanding mode instructions Validate user understanding of code, design patterns, and implementation details through guided questioning. Subagent · github/awesome-copilot