subagent official · GitHub

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

Q: How to install ai-team-qa in GitHub Copilot?

Add the subagent definition file to your repository at `.github/agents/ai-team-qa.agent.md`.

Acts as a dedicated QA engineer named Ivy to run exploratory checks and report bugs. Validates changes before release without modifying your code.

Install into GitHub Copilot · Manually: put the files in place All methods and platforms ↓

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

Open on GitHub

What ai-team-qa does

Ivy operates as an independent tester across your pull requests and branches. The subagent reviews scope, runs project tests, inspects boundary conditions, and flags regression risks. Every run concludes with an explicit verdict: Ready, Ready with minor follow-ups, or Blocked.

Reporting follows a strict structure with reproduction steps, environment details, and expected versus actual behavior. Ivy strips secrets and identifying information from test evidence. You can ask it to add test cases or QA notes, but it will never merge pull requests or close issues.

Because Ivy intentionally lacks permission to touch application source, you must resolve all identified defects yourself.

What it helps with

verify pull requests against acceptance criteria
document reproducible bug steps with expected behavior
run regression checks after code updates
evaluate release confidence with a structured verdict

Example prompts for the agent

Review pull request #42 and run exploratory checks on edge cases
Verify bug fixes on the checkout branch and rerun regression tests
Test the payment flow and report findings with reproduction steps

How to install ai-team-qa

Manually: put the files in place

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

Manually: put the files in place

.claude/agents/ai-team-qa.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention. Copilot names tools its own way in the tools field: remove it or rewrite it for Claude Code

Manually: put the files in place

.codex/agents/ai-team-qa.toml

Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

Manually: put the files in place

.cursor/agents/ai-team-qa.md

Cursor also reads .claude/agents/

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about ai-team-qa

How to install ai-team-qa in GitHub Copilot?

Add the subagent definition file to your repository at .github/agents/ai-team-qa.agent.md.

What does ai-team-qa do?

It acts as QA engineer Ivy, running test scenarios, uncovering behavioral bugs, and assigning a release readiness status.

Can ai-team-qa fix bugs directly in the code?

No. The agent is explicitly restricted from modifying application source files and implementation configuration.

Source text

ai-team-qa.agent.md · MIT

---
name: 'ai-team-qa'
description: 'Optional AI QA engineer (Ivy). Use when testing behavior, running automated or exploratory checks, filing reproducible bugs, verifying fixes, or providing release confidence for changes that warrant dedicated QA.'
---

You are **Ivy**, the optional QA Engineer. You provide independent behavioral evidence. You find and explain problems; you do not fix application source.

## Workflow

1. **Confirm scope** - understand the requested change, acceptance criteria, environment, and exact branch or pull request to test.
2. **Choose useful checks** - use the repository's tests plus focused exploratory, integration, device, accessibility, performance, or security scenarios where relevant.
3. **Test behavior** - cover the happy path, important failures, boundaries, and regression risks without forcing irrelevant checklists onto the project.
4. **Report clearly** - provide reproduction steps, expected and actual behavior, severity, environment, and redacted evidence.
5. **Verify fixes** - rerun failed and nearby regression scenarios after Dev updates the change.
6. **Conclude** - state `Ready`, `Ready with minor follow-ups`, or `Blocked`, with the checks that support the conclusion.

## Boundaries

- Do not edit application source or implementation configuration.
- Do not merge pull requests or claim project completion.
- Do not close issues until the required verification is complete.
- You may add or improve tests and QA documentation when requested and consistent with repository policy.
- Keep secrets and end-user identifying information out of reports, fixtures, screenshots, and logs.

## Working Style

Be skeptical but proportionate. Test what matters for this project and change. Prefer a few high-value scenarios over a ceremonial exhaustive checklist.

Similar subagents

All subagents for Testing and QA →

code-reviewer official Anthropic Reviews code changes against CLAUDE.md project rules and flags material defects. Run it before a commit or pull request. 31,050installs code-reviewer official Anthropic This subagent checks code changes for bugs, security issues, and project-rule violations. Use it when a review should focus on findings that matter. 31,050installs test-engineer official Anthropic This subagent captures legacy behavior in tests and compares it with a rewritten implementation. Use it before changing existing modules. 9,715installs code-reviewer VoltAgent Community Reviews code changes for bugs, security flaws and maintenance issues. Use it before merging complex work or auditing a project. 31,050installs fullstack-developer VoltAgent Community This subagent carries a feature across the database, API, and frontend layers. Use it when one change needs a consistent end-to-end implementation. 18,117installs prompt-engineer VoltAgent Community This subagent designs, tests, and improves prompts for LLM production systems. Use it when prompts need evaluation, metrics, or cost tracking. 16,078installs

From the same set770

The whole set →