QA Explorer — Testing & QA agent for Claude Code
Hands-on exploratory tester that drives the RUNNING application (browser via Playwright MCP / Claude in Chrome, or CLI/API via shell) in time-boxed, charter-based sessions, hunting for real bugs with.
How to install QA Explorer
Installs to ~/.claude/agents/myriambs-argus-qa-qa-explorer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Myriambs/argus-qa/HEAD/agents/qa-explorer.md -o ~/.claude/agents/myriambs-argus-qa-qa-explorer.md Restart Claude Code, or start a new session, for it to be picked up.
What QA Explorer does
name: qa-explorer description: "Hands-on exploratory tester that drives the RUNNING application (browser via Playwright MCP / Claude in Chrome, or CLI/API via shell) in time-boxed, charter-based sessions, hunting for real bugs with heuristics and attack patterns, and capturing evidence (screenshots, console errors, network failures). Use when there is a URL, local dev server, CLI or API to actually test." model: inherit
You are **Argus · Explorer**, an elite exploratory tester in the tr
Alternatives in Testing & QA
- Extension Smoke Test — Pre-reload smoke test for the WXT browser extension 189 ★
- TypeScript Test Explorer — Use this agent when you need comprehensive test case design and exploratory testing for TypeScript code 76 ★
- Figma Executor — Runs an architect's Figma spec — resolves stable names to nodeIds at run time, builds into a named working fra 76 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Migration Validation Explorer
Use this agent for exploratory data-migration validation and QA ideation. Discovers hidden risks, generates va
Automation QA
The automated-test author. Use proactively after a feature or bugfix is implemented, before requesting human r
Tosca Scenario Explorer
Use to explore a test scenario live in the application under test, before Tosca automation is built or fixed.
Dom Auditor
Inspects live application via Chrome MCP to verify which UI elements actually exist. Catches ghost elements th
Loadguard Worker
Default loadguard worker — implement, refactor, debug and test the hook, the CLI and the decision logic. Works
Manual Tester Agent
Use this agent to test the live application under test the way a human QA would - persona-driven exploration (
Related Skills
Ruver QA
QA a GitHub PR (Playwright + browser). Hands potential bugs to ruver_triage.
QA Gate
QA verification for G4 — execute the test plan, build the AC-to-test traceability matrix, run an exploratory c
Dogfood
Exploratory web QA against a target URL — drives a real browser, captures evidence, writes a structured report