Flaky Test Hunter — Testing & QA agent for Claude Code
Diagnoses a flaky test by making it fail reliably, then fixes the actual nondeterminism.
How to install Flaky Test Hunter
Installs to ~/.claude/agents/agent37-platform-claude-code-subagents-flaky-test-hunter.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/agent37-platform/claude-code-subagents/HEAD/agents/flaky-test-hunter.md -o ~/.claude/agents/agent37-platform-claude-code-subagents-flaky-test-hunter.md Restart Claude Code, or start a new session, for it to be picked up.
What Flaky Test Hunter does
name: flaky-test-hunter description: Diagnoses a flaky test by making it fail reliably, then fixes the actual nondeterminism. Use when a test passes locally but fails in CI, or fails intermittently. Reports the flake class with reproduction evidence. tools: Read, Grep, Glob, Bash, Edit color: yellow
You turn "fails sometimes" into "fails on demand", then fix the real cause. Deleting or retry-wrapping a flaky test is not a fix; it is how real regressions get in unseen.
Method
- **M
Alternatives in Testing & QA
- Grid Tester — Use this agent for test strategy, TDD workflows, integration/e2e coverage, and flaky test hardening 523 ★
- Writ Reviewer — Reviews an implementation diff in two passes (spec-compliance first, then code quality) 187 ★
- Memory Hunter — Memory retrieval lane — given a spec (a consumer's question + task), hunts the wiki for the relevant slices an 94 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Flake Investigator
Establishes why a Playwright case failed intermittently and classifies the cause before anyone changes the tes
Flaky Test Isolator
USE WHEN a test intermittently fails on unchanged code. Runs it N times sequentially, captures pass/fail + std
Flake Detector
Use when a test is suspected to be non-deterministic — passes sometimes, fails sometimes, or fails only in CI.
E2e Selector Drift Reviewer
Use this agent when Playwright E2E spec files under apps//e2e/ (e.g. apps/hospitality/e2e/.spec.ts) are added
Test Maintainer
Fixes failing and flaky tests, and refactors a suite that has grown duplication. Finds the root cause instead
Stagehand Expert
Use this agent when you need executable Stagehand test files for TDD workflow. ALWAYS checks latest Stagehand
Related Skills
Canary Debug Flake
Diagnose a flaky test and propose a deterministic fix from code, CI logs, or a failure description.
Massu CI Fix
When CI fails after push — auto-diagnoses failures, fixes, commits, and re-pushes. 'ci fix', 'fix ci', 'ci fai
Repro Issue
by rzykov - Creates reproducible test cases for GitHub issues, ensuring tests fail reliably and documenting cl