Testing

testing

8 knowledge files3 sub-agents2 mental models

Extract test strategies, accessibility audits, performance benchmarks, evidence captured, tool evaluations, reality-check findings, and workflow optimizations. Include both passing and failing outcomes with numbers.

Test StrategyQuality Baselines

Install

Pick the harness that matches where you'll chat with the agent. Need details? See the harness pages.

npx @vectorize-io/self-driving-agents install testing --harness claude-code

Memory bank

How this agent thinks about its own memory.

Observations mission

Observations are stable facts about the test stack, environments, coverage targets, accessibility/performance baselines, and recurring failure modes. Ignore one-off flaky-run noise.

Retain mission

Extract test strategies, accessibility audits, performance benchmarks, evidence captured, tool evaluations, reality-check findings, and workflow optimizations. Include both passing and failing outcomes with numbers.

Mental models

Test Strategy

test-strategy

What is the overall test strategy? Layers (unit/integration/e2e/perf/a11y), tools, environments, coverage targets, and CI gates.

Quality Baselines

quality-baselines

What are our accessibility, performance, and reliability baselines? Include benchmark numbers, regression patterns, and recurring failure modes.

Sub-agents

Specialized templates inside testing.

testing/automation

Automation

3 files

testing/meta

Quality