QA Wolf CLI
The CLI runs QA Wolf flows locally and in CI, refreshes cached tests and helps investigate traces from failed attempts.
- 3,459 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- The CLI runs browser flows with environment access and can read traces containing application data.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add cli/qa-wolf-cliDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The CLI runs browser flows with environment access and can read traces containing application data.
This is third-party code. Review the repository files before installing.
What it does
QA Wolf CLI runs browser test flows from the terminal. It accepts a local file or team-environment flows and reuses an on-disk cache that can be refreshed explicitly. After a failure, an agent can inspect a summary, logs, network events and page snapshots. AI test creation and managed team execution belong to the QA Wolf platform; the CLI can also initialize local projects.
Who it is for. QA Wolf test engineers reproducing failures locally and supplying focused evidence to an agent.
Good fit when
- A failed team flow needs local reproduction.
- CI must run prepared browser tests through a CLI.
- A failure needs a specific request, snapshot or log inspected.
- For a separate experiment, you need a local project with your own flow files.
Not a fit when
- You expect the entire hosted platform and AI generation from one npm package.
- Test actions could place a real order in a production account.
- You assume the local cache always matches the team’s latest flows.
Example request
Investigate this failed QA Wolf attempt: show its summary first, then inspect only the relevant log and network request.Limitations
The npm package requires Node.js 24.14.1 or newer; standalone binaries are a separate option. Team flows require a QA Wolf account and environment ID, while local projects use their own initialization command. Environment caches refresh through an explicit pull, so verify freshness before reproducing a failure. Trace and log reads are bounded; incomplete or truncated evidence flags must inform the investigation.
How to disable. Stop active tests and uninstall the CLI. Review the local cache and QA Wolf credentials separately.
FAQ
How do I refresh team flows?
Run `qawolf flows pull --env <env-id>` for the intended environment, then rerun.
Can I work locally without the platform?
Yes. Initialize with `qawolf init` and provide local flow files.
How do I install the browser runtime?
Run `qawolf install` and verify it before the first test.
Can I save a failure screenshot?
Yes. Use a new output path; existing files are not overwritten.
Is there an agent skill?
Yes. Add the qawolf-cli skill separately after installing the CLI; it guides command and failure-evidence selection.
Discussion
No questions or reviews yet.
Related
CLI toolsQlty CLI reports duplicate and complex code before refactoring; automatic formatting runs as a separate action.
QA Agent for the GigaCode CLI: 14 roles and 6 skills for testing
QaAgentGigacodeCli
Requirements-based testing in GigaCode: from analysis and autotest review to a conclusion, with duplicate search before a bug is filed in Jira
Seven QA agents and ten skills for test automation: Playwright in TypeScript, Selenium in Java, API, accessibility and ISTQB.
A skill that tests your agent's code in a real browser: reads your changes, builds a test plan and runs it through Playwright with your own cookies
A CLI from TestMu AI that writes end-to-end tests from requirements and runs them in a browser or on mobile, with a skill for your agent
Playwright CLI
playwright-cli
Microsoft's official Playwright CLI with an agent skill: drive a browser through short commands without heavy MCP schemas
README in short
Platform run commands are separate from local flow execution. A TypeScript SDK supports programmatic runner control.