Best Claude Code Testing & QA agents
1,208Ranked by quality score. Browse all 1,208 Testing & QA agents
Testing & QA agents are subagents whose job is to check work rather than produce it: senior code reviewers, driver-test writers, CI verifiers that ask whether changed behaviour is covered, spec validators that run the tests and compare against the plan, and agents that find where specification and implementation have drifted apart. Several come from real engineering organisations and encode how those teams review.
The pattern that works is delegation after the change: the main session implements, then hands the diff to a reviewer or verifier agent that has not seen the reasoning and cannot be talked into agreeing with it. That separation is the whole point. A test-writing agent is useful when the suite is thin and you want cases generated in bulk in a context that does not crowd out the feature work.
Install by saving the markdown file to ~/.claude/agents/<name>.md; the entry page has the command. Give reviewer agents read tools only where the definition allows it, so a review cannot quietly become an edit. Verifiers that run the suite need Bash, and will. Check /agents after installing to confirm the name Claude will use.
Top 20 Testing & QA agents
Claude Code Flow
66This mode serves as a code-first orchestration layer, enabling Claude to write, edit, test, and optimize code autonomously across recursive agent cycles.
Senior Code Reviewer
57Testing & QA
Fullstack code reviewer with 15+ years experience analyzing security vulnerabilities, performance bottlenecks, and architectural decisions
Testing Architecture
57This directory contains comprehensive test coverage for CUI services.
Gitnexus Test Ci Verifier
56GitNexus test and CI reviewer. Use to verify whether changed behavior is covered by targeted tests, whether CI actually runs those tests, and whether…
Rivetkit Driver Test Writer
52Use this agent when the user needs to write, modify, or debug driver tests for RivetKit.
Weed
49Weed the Allium garden. Find where Allium specifications and implementation code have diverged, and help resolve the divergences. Use when the user wants to…
Track Plan
48Track ID: {{TRACK_ID}} Spec: spec.md Estimated Effort: {{EFFORT_ESTIMATE}}...
Track Spec
48Track ID: {{TRACK_ID}} Type: {{TRACK_TYPE}} (feature · bug · chore · refactor) Priority:...
Workflow
481. plan.md is the source of truth - All task status and progress tracked in the plan 2. Test-D... · - · wshobson/agents ·
Test Generate
48You are a test automation expert specializing in generating comprehensive, maintainable unit tests a...
Test Architect Agent
47You are a testing expert who designs comprehensive test strategies and writes effective tests.
Ad Onboard Reviewer
46Independent reviewer for AutoDeploy model onboarding.
Perf Test Sync
46Use this agent when the user needs to synchronize performance test cases between development (dev) and QA directories, compare test configurations, update…
Test Wiring Auditor
46変更差分に対してテスト網が追随しているかを fresh-context で監査する read-only auditor
Arbiter
45You are a specialized validation agent. Your job is to run unit and integration tests, analyze failures, and generate comprehensive test reports. You judge…
Kraken
45You are a specialized implementation agent.
Pencil Ui Designer
44Use this agent when you need Pencil-based design workflows: atomic designer actions, MCP tools, and spec-driven UI plans.
Visual Testing Agent (Playwright MCP)
44You are the TESTER - the visual QA specialist who SEES and VERIFIES implementations using Playwright MCP.
Civitai Test Review
42Reviews the tests in a feature segment of the main Civitai Next.js app (src/) for whether they would actually fail if the code broke — vacuous assertions,…
Qa Manual Tester
41Use this agent when you need to perform manual quality assurance testing through browser interactions.
These are 20 of 1,208. See every Testing & QA agent, searchable and sortable by stars or name.