name: 'step-02-load-context' description: 'Load documents, configuration, and knowledge fragments for the chosen mode' nextStepFile: './step-03-risk-and-testability.md' knowledgeIndex: '{project-root}/_bmad/tea/testarch/tea-index.csv'
Load the required documents, config flags, and knowledge fragments needed to produce accurate test design outputs.
{communication_language}CRITICAL: Follow this sequence exactly. Do not skip, reorder, or improvise.
From {config_source}:
tea_use_playwright_utilstea_browser_automationtest_artifactsLoad:
Extract:
Load:
Extract:
If epic-level:
tests/, spec, e2e, api folders)tea_browser_automation is cli or auto)Fallback: If CLI is not installed, fall back to MCP (if available) or skip browser exploration and rely on code/doc analysis.
CLI Exploration Steps: All commands use the same named session to target the correct browser:
playwright-cli -s=tea-explore open <target_url>playwright-cli -s=tea-explore snapshot → capture page structure and element refsplaywright-cli -s=tea-explore screenshot --filename={test_artifacts}/exploration/explore-<page>.pngplaywright-cli -s=tea-explore closeStore artifacts under {test_artifacts}/exploration/
Session Hygiene: Always close sessions using
playwright-cli -s=tea-explore close. Do NOT useclose-all— it kills every session on the machine and breaks parallel execution.
Use {knowledgeIndex} to select and load only relevant fragments.
adr-quality-readiness-checklist.mdtest-levels-framework.mdrisk-governance.mdtest-quality.mdrisk-governance.mdprobability-impact.mdtest-levels-framework.mdtest-priorities-matrix.mdPlaywright CLI (if tea_browser_automation is "cli" or "auto"):
playwright-cli.mdMCP Patterns (if tea_browser_automation is "mcp" or "auto"):
Summarize what was loaded and confirm with the user if anything is missing.
Save this step's accumulated work to {outputFile}.
If {outputFile} does not exist (first save), create it with YAML frontmatter:
---
stepsCompleted: ['step-02-load-context']
lastStep: 'step-02-load-context'
lastSaved: '{date}'
---
Then write this step's output below the frontmatter.
{outputFile} already exists, update:
'step-02-load-context' to stepsCompleted array (only if not already present)lastStep: 'step-02-load-context'lastSaved: '{date}'Load next step: {nextStepFile}