recipe-add-integration-tests

Required Skills [LOAD BEFORE EXECUTION]

1. [LOAD IF NOT ACTIVE] testing — repository-aware test execution
2. [LOAD IF NOT ACTIVE] integration-e2e-testing — value-based integration/E2E selection
3. [LOAD IF NOT ACTIVE] subagents-orchestration-guide — review resolution and agent coordination
4. [LOAD IF NOT ACTIVE] llm-friendly-context — task file contract

Spawn rule: every spawn_agent call uses fork_turns="none" so the subagent receives only the task message and explicitly provided context.

Context: Test addition workflow for existing implementations

Orchestrator Definition

Core Identity: Coordinate test addition, perform lightweight evidence collection and routing directly, and invoke specialists for generation, implementation, and review judgment.

Execution Plan: Reuse the active execution plan. When the workflow has multiple dependent actions and no plan exists, create one that tracks them through final verification.

Why Spawn: Orchestrator's context is shared across all steps. Direct implementation consumes context needed for review and quality check phases. Task files create context boundaries. Subagents work in isolated context.

Execution Method:

• Skeleton generation -> Spawn acceptance-test-generator agent
• Task file creation -> Orchestrator creates directly (minimal context usage)
• Test implementation -> Spawn task-executor agent
• Test review -> Spawn integration-test-reviewer agent
• Quality checks -> Spawn quality-fixer agent

Document paths: $ARGUMENTS

Prerequisites

• At least one Design Doc must exist (created manually or via reverse-engineer)
• Existing implementation to test

Execution Flow

Step 0: Prepare Context

Use the llm-friendly-context Task File Contract in Step 3.

Step 1: Discover and Validate Documents

# Verify at least one document path was provided
test -n "$ARGUMENTS" || { echo "ERROR: No document paths provided"; exit 1; }

# Verify provided paths exist
ls $ARGUMENTS