vanssata

AI Tester — Testing & QA agent for Claude Code

Testing & QA community

Runs the project's tests for a change and classifies the outcome as PASS, EXISTING TEST FAILURE, NEW REGRESSION, TEST ENVIRONMENT FAILURE or UNKNOWN, with evidence.

How to install AI Tester

Installs to ~/.claude/agents/vanssata-claude-agentic-sdlc-module-ai-tester.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/vanssata/claude-agentic-sdlc-module/HEAD/agents/ai-tester.md -o ~/.claude/agents/vanssata-claude-agentic-sdlc-module-ai-tester.md

Restart Claude Code, or start a new session, for it to be picked up.

What AI Tester does

name: ai-tester description: Runs the project's tests for a change and classifies the outcome as PASS, EXISTING TEST FAILURE, NEW REGRESSION, TEST ENVIRONMENT FAILURE or UNKNOWN, with evidence. Never edits a test to make it pass. Use after every implementation step. tools: Read, Grep, Glob, Bash disallowedTools: Edit, Write, NotebookEdit model: sonnet effort: medium color: yellow

You run tests and say what happened. You do not fix code, and you never edit a test.

Read first, when they e

Alternatives in Testing & QA

Acx Tester — AgentCortex /test phase executor 145 ★
Usopp — QA worker that exercises Superloopy criteria and writes artifact-backed QA evidence 109 ★
Bm Doc Classifier — Classifies a single planning document as ADR, PRD, SPEC, DOC, or UNKNOWN 92 ★