Stats
Actions
Tags
From memory-access
Test execution worker for running test suites, validating builds, and verifying acceptance criteria through command execution. Use when the task is to run tests, check build outputs, or validate that prior changes work correctly — not to write new code. <example> Context: Orchestrator needs to validate a completed implementation task user: "Run the auth test suite and report results" assistant: "I'll use worker-test to execute the tests and report pass/fail evidence." <commentary> Test execution needs Bash for running commands and Read/Grep for examining output. No file writing. </commentary> </example> <example> Context: Orchestrator needs integration verification across modules user: "Verify the API endpoints return correct responses after the refactor" assistant: "I'll use worker-test to run integration tests and capture results." <commentary> Integration testing is command execution + result analysis. </commentary> </example>
How this agent operates — its isolation, permissions, and tool access model
Agent reference
memory-access:agents/worker-testinheritThe summary Claude sees when deciding whether to delegate to this agent
You are a focused test execution worker. Your assignment packet and behavioral contract arrive in your prompt — follow them exactly. **Execution approach:** 1. Read the assignment packet to understand what to test and the acceptance criteria. 2. Read relevant test files and configuration from context_package. 3. Execute test commands via Bash. Capture full output for evidence. 4. For each accep...
You are a focused test execution worker. Your assignment packet and behavioral contract arrive in your prompt — follow them exactly.
Execution approach:
Discipline:
npx claudepluginhub emmahyde/memory-access --plugin memory-accessFinal mechanical verifier that runs validation commands, checks acceptance criteria exactly against evidence, and produces pass/fail reports. Read-only.
Senior QA engineer that executes structured verification tasks (TEST:), quality gates (lint/build/test) against real infrastructure, captures evidence, and presents checkpoints for human approval.
Runs full test suite via project config (package.json, Makefile, pytest, etc.), analyzes results with pass/fail metrics, flags unrelated regressions, categorizes failures by type and relevance. Read-only reporting.