E2E Testing

Full-cycle E2E testing orchestration: setup agents, create BDD scenarios, write autotests, quorum review.

Arguments: $ARGUMENTS

Phase 0: Parse Arguments

EXECUTE using Bash tool:

bash "${CLAUDE_SKILL_DIR}/scripts/detect-mode.sh" "$ARGUMENTS" && echo "OK" || echo "FAILED"

Output: MODE:xxx and optionally PROMPT:xxx. Store both.

STOP if FAILED -- fix detect-mode.sh before continuing.

Phase 1: Display Detection

Output detection result:

Mode: {MODE}
Prompt: {PROMPT or "none"}

Phase 2: Load Mode Reference

Read the mode-specific reference file:

Also load core references (always):

• ${CLAUDE_SKILL_DIR}/references/e2e-rules.md -- rules for all agents
• ${CLAUDE_SKILL_DIR}/references/e2e-architecture.md -- architecture reference

STOP if mode reference not found -- report missing file.

Phase 3: Execute Mode Flow

Follow the loaded mode reference step by step. Pass PROMPT as context where indicated.

Common patterns across all modes:

Prerequisite Check (all modes except setup and status)

.claude/agents/e2e-*.md count must be >=3. If not -> "Run /brewcode:e2e setup first." STOP. Status mode reports missing infrastructure instead of blocking.

Review Cycle (create, update modes)

MAX_CYCLES=3. Pattern: execute -> reviewer validates -> different agent re-checks -> fix confirmed -> repeat.

Agent Dispatch

All agent work through Task tool. Spawn parallel agents in ONE message when possible.

User Interaction

AskUserQuestion at every key decision point. PROMPT is initial context, not a replacement for confirmation.

Error Handling

Output Format

# e2e [{MODE}]

## Detection
| Field | Value |
|-------|-------|
| Arguments | `{raw args}` |
| Mode | `{MODE}` |
| Prompt | `{PROMPT or none}` |

## Results
{Mode-specific output}

## Next Steps
- {recommendations based on mode}