Flake Investigator — Testing & QA agent for Claude Code
Establishes why a Playwright case failed intermittently and classifies the cause before anyone changes the test.
How to install Flake Investigator
Installs to ~/.claude/agents/artemcherbaev-agentic-playwright-suite-flake-investigator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ArtemCherbaev/agentic-playwright-suite/HEAD/.claude/agents/flake-investigator.md -o ~/.claude/agents/artemcherbaev-agentic-playwright-suite-flake-investigator.md Restart Claude Code, or start a new session, for it to be picked up.
What Flake Investigator does
name: flake-investigator description: Establishes why a Playwright case failed intermittently and classifies the cause before anyone changes the test. Use when a case passes on one run and fails on the next, or when a failure is about to be dismissed as "just flaky". tools: Read, Grep, Glob, Bash, mcp__playwright__browser_navigate, mcp__playwright__browser_snapshot, mcp__playwright__browser_click, mcp__playwright__browser_evaluate, mcp__playwright__browser_console_messages, mcp__playwright__
Alternatives in Testing & QA
- Civitai Test Review — Reviews the tests in a feature segment of the main Civitai Next.js app (src/) for whether they would actually 7.2k ★
- Knowledge Base Builder — Phase 3 project model construction agent that classifies project type, maps attacker-controlled inputs and tru 125 ★
- Bm Doc Classifier — Classifies a single planning document as ADR, PRD, SPEC, DOC, or UNKNOWN 92 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Flaky Test Hunter
Diagnoses a flaky test by making it fail reliably, then fixes the actual nondeterminism. Use when a test passe
Test Healer
Repairs a failing Playwright case once flake-investigator has established the cause. Use only after the cause
Bug Hypothesis Investigator
Use when one candidate cause of a defect needs a falsifiable test before anyone believes it. Give it the sympt
Result Checker
Use this agent right after test-runner executes a group of test cases, to decide per case whether each genuine
Flake Detector
Use when a test is suspected to be non-deterministic — passes sometimes, fails sometimes, or fails only in CI.
Diagnostician
Finds the cause of a failing check, test or CI run in a devflow task and reports it with evidence, without cha
Related Skills
Triage Flake
Investigate an intermittent failure and classify its cause without repairing it
Recon Dispute Agent
AI agentic workflow (Claude + tool-calling) that consumes reconciliation discrepancies, investigates each case
Analyze Test Report
Phân tích test report — automation (Playwright/Allure/JUnit/TestNG) hoặc manual (execution_report.md / retest_