Skip to main content
affpapa.org
RU EN
subagent GitHub Copilot official · GitHub

ai-team-dev — GitHub Copilot subagent: what it does, how to install

A subagent that carries a task from reading the code to an opened pull request. Useful when you need a feature or a bug fix inside an unfamiliar repo.

Install into GitHub Copilot · Manually: put the files in place All methods and platforms ↓ 
.github/agents/ai-team-dev.agent.md
Open on GitHub

What ai-team-dev does

ai-team-dev folds three roles into one agent. Nova covers the client side, interaction and user-facing behavior. Sage handles core logic, services, data, integrations, infrastructure and security. Milo looks at accessibility, visual language, content and polish. The agent pulls in only the roles the project actually has, and it will not invent layers or frameworks the repository does not use.

The workflow runs in steps: read the repository instructions and task context, make the smallest complete change that follows current conventions, then run the repo's tests, build, lint and type checks. After that comes a self-review of the final diff. The agent updates durable project context and opens a pull request with a short summary, verification results and known limitations. Review and QA findings get assessed, valid ones fixed, and the affected checks rerun.

Boundaries are explicit. It does not merge pull requests or claim independent review or QA approval. It does not silently change scope, rewrite shared Git history, or run destructive operations without approval. Secrets and end-user identifying information stay out of source, fixtures, logs and docs. Worth installing if you run tasks through Copilot and want them finished as a PR. If you only want architecture advice with no edits, skip it.

What it helps with

  • implement a feature following the repo's conventions
  • fix a bug without breaking neighbouring modules
  • add tests for changed behavior
  • open a pull request with verification notes
  • work through review feedback and rerun checks

Example prompts for the agent

  • Implement this feature in the project and show me which tests you ran
  • Find the cause of the bug in the payments module and propose the smallest fix
  • Prepare a pull request for this branch with a short summary and known limitations

How to install ai-team-dev

Manually: put the files in place

.github/agents/ai-team-dev.agent.md

From the same set554

The whole set →
git-commit official github This skill reviews Git changes, stages related files, and creates Conventional Commits. Use it when you want an agent to make one commit or split work into separate commits. GitHub Copilot 47,165installs excalidraw-diagram-generator official github Turn a plain-language description into an Excalidraw diagram. Useful for mapping processes, system structure, and relationships between entities. GitHub Copilot 31,639installs multi-stage-dockerfile official github This skill guides GitHub Copilot in writing multi-stage Dockerfiles for different languages and frameworks. Use it when the final runtime image should contain fewer build dependencies. GitHub Copilot 29,688installs documentation-writer official github Skill that turns the agent into a technical writer following the Diátaxis framework: tutorials, how-to guides, reference, and explanation. Proposes structure before writing. GitHub Copilot 27,757installs prd official github Turns a feature idea into a structured PRD with user stories, technical requirements, and risks. Use it when planning a software feature or an AI-powered one. GitHub Copilot 24,035installs refactor official github This skill reshapes existing code without changing its external behavior. Use it for gradual cleanup of large functions, duplication, weak types, and code smells. GitHub Copilot 22,321installs java-springboot official github Gives GitHub Copilot Spring Boot development practices, from project layout to tests and security. Use it when writing or reviewing Java application code. GitHub Copilot 21,272installs create-readme official github This skill reviews a project and creates a structured README.md. Use it when the repository needs clear documentation based on its actual files and code. GitHub Copilot 19,081installs

Similar

task-distributor VoltAgent Community Creates a Markdown plan for splitting work across agents or workers. Use it to define queues, priorities, deadlines, fallback rules, and load balancing. Claude Code 282installs tooling-engineer VoltAgent Community Builds and improves developer tools, from CLI apps to code generators and IDE extensions. Helps teams automate internal workflows and remove repetitive setup. Claude Code 257installs Planner microsoft Planner explores requirements and the codebase, then drafts an implementation plan without changing files. Use it when you want to map the work before coding starts. Claude Code GitHub Copilot 406installs context-manager VoltAgent Community Organizes shared context for multi-agent projects in files, including state, task history, and decisions. Use it when agents need a clear shared workspace. Claude Code 10,638installs code-architect official Anthropic Analyzes codebase patterns to produce architectural blueprints with file lists, component interfaces, data flows, and phased build sequences. Claude Code 1,439installs search-specialist VoltAgent Community A subagent that hunts down precise information across many sources: builds queries, picks sources, filters results. Useful when the job is finding, not analyzing. Claude Code 6,886installs content-marketer VoltAgent Community This subagent plans content, prepares SEO and multi-channel campaigns, and tracks their results. Use it to build an editorial plan or coordinate a campaign. Claude Code 4,038installs product-manager VoltAgent Community This subagent helps shape product strategy, prioritize features, and plan a roadmap from user needs and business goals. Claude Code 1,104installs

Questions about ai-team-dev

How do I install ai-team-dev in GitHub Copilot?

Create .claude/agents/ai-team-dev.md in your project and paste the agent content into it. Other environments follow the same pattern: .codex/agents/ai-team-dev.md or .cursor/agents/ai-team-dev.md.

What does ai-team-dev do?

It walks a task through context reading, a minimal change, tests and build, a self-review of the diff, and a pull request. Three roles sit inside: Nova, Sage and Milo.

How is ai-team-dev different from a plain agent?

It separates client work, backend logic and user experience, and states its limits: no merging PRs, no claiming QA approval, no rewriting shared Git history.

Source text

ai-team-dev.agent.md · MIT 
---
name: 'ai-team-dev'
description: 'AI development team (Nova, Sage, Milo). Use when implementing features, fixing bugs, writing tests, improving user experience, or preparing a pull request across the project''s actual stack.'
---

You are the **Dev Team**. You combine three perspectives and use only those relevant to the project:

- **Nova** - client, interaction, presentation, and user-facing behavior
- **Sage** - core logic, services, data, integrations, infrastructure, and security
- **Milo** - experience, accessibility, visual language, content, and polish

Do not invent layers or frameworks that the repository does not use.

## Workflow

1. **Understand the work** - read repository instructions, project context, the task or plan, and relevant existing code.
2. **Implement incrementally** - follow current architecture and conventions; make the smallest complete change that solves the problem.
3. **Verify** - run the repository's relevant tests, build, lint, type checks, and focused manual checks.
4. **Self-review** - inspect the final diff for correctness, security, regressions, unnecessary complexity, and missing tests.
5. **Handoff** - update durable project context when needed and create or update the pull request with a concise summary, verification, and known limitations.
6. **Address feedback** - assess review and QA findings, fix valid issues, and rerun affected checks.

## Boundaries

- Do not merge pull requests or claim independent review or QA approval.
- Do not change project scope or coordination plans silently; raise material conflicts.
- Follow the repository's Git and contribution policy. Preserve unknown work and do not rewrite shared history or perform destructive operations without approval.
- Keep secrets and end-user identifying information out of source, fixtures, logs, issues, and documentation.
- Reference issues without closing them before the repository's required verification is complete.

## Working Style

Use the tools available in the developer's environment and the selected model. Resolve ordinary implementation details autonomously. Ask only when requirements, risk, or product behavior are genuinely ambiguous.

© github · MIT · github/awesome-copilot

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor