Cover

cover authentication flow
cover --model=opus payment processing
cover --tier=unit,integration user service
cover --real-services checkout pipeline

SCOPE = "$ARGUMENTS"  # e.g., "authentication flow"

# Flag parsing
MODEL_OVERRIDE = None
TIERS = ["unit", "integration", "e2e"]  # default: all three
REAL_SERVICES = False

for token in "$ARGUMENTS".split():
    if token.startswith("--model="):
        MODEL_OVERRIDE = token.split("=", 1)[1]
        SCOPE = SCOPE.replace(token, "").strip()
    elif token.startswith("--tier="):
        TIERS = token.split("=", 1)[1].split(",")
        SCOPE = SCOPE.replace(token, "").strip()
    elif token == "--real-services":
        REAL_SERVICES = True
        SCOPE = SCOPE.replace(token, "").strip()

# Probe MCPs (parallel):
# memory is alwaysLoad in .mcp.json (CC 2.1.121+, #1541). Probe below kept as fallback for older CC:
ToolSearch(query="select:mcp__memory__search_nodes")
ToolSearch(query="select:mcp__context7__resolve-library-id")

Write(".claude/chain/capabilities.json", {
  "memory": <true if found>,
  "context7": <true if found>,
  "skill": "cover",
  "timestamp": now()
})

# Resume check:
Read(".claude/chain/state.json")
# If exists and skill == "cover": resume from current_phase
# Otherwise: initialize state

AskUserQuestion(
  questions=[
    {
      "question": "What test tiers should I generate?",
      "header": "Test Tiers",
      "options": [
        {"label": "Full coverage (Recommended)", "description": "Unit + Integration (real services) + E2E"},
        {"label": "Unit + Integration", "description": "Skip E2E, focus on logic and service boundaries"},
        {"label": "Unit only", "description": "Fast isolated tests for business logic"},
        {"label": "E2E only", "description": "Playwright browser tests"}
      ],
      "multiSelect": false
    },
    {
      "question": "Healing strategy for failing tests?",
      "header": "Failure Handling",
      "options": [
        {"label": "Auto-heal (Recommended)", "description": "Fix failing tests up to 3 iterations"},
        {"label": "Generate only", "description": "Write tests, report failures, don't fix"},
        {"label": "Strict", "description": "All tests must pass or abort"}
      ],
      "multiSelect": false
    }
  ]
)

# 1. Create main task IMMEDIATELY
TaskCreate(subject=f"Cover: {SCOPE}", description="Generate comprehensive test suite with real-service testing", activeForm=f"Generating tests for {SCOPE}")

# 2. Create subtasks for each phase
TaskCreate(subject="Discover scope and detect frameworks", activeForm="Discovering test scope")    # id=2
TaskCreate(subject="Analyze coverage gaps", activeForm="Analyzing coverage gaps")                  # id=3
TaskCreate(subject="Generate tests (parallel per tier)", activeForm="Generating tests")            # id=4
TaskCreate(subject="Execute generated tests", activeForm="Running tests")                          # id=5
TaskCreate(subject="Heal failing tests", activeForm="Healing test failures")                       # id=6
TaskCreate(subject="Generate coverage report", activeForm="Generating report")                     # id=7

# 3. Set dependencies for sequential phases
TaskUpdate(taskId="3", addBlockedBy=["2"])  # Analysis needs discovery first
TaskUpdate(taskId="4", addBlockedBy=["3"])  # Generation needs gap map
TaskUpdate(taskId="5", addBlockedBy=["4"])  # Execution needs generated tests
TaskUpdate(taskId="6", addBlockedBy=["5"])  # Healing needs test results
TaskUpdate(taskId="7", addBlockedBy=["6"])  # Report needs healed suite

# 4. Update status as you progress
TaskUpdate(taskId="2", status="in_progress")  # When starting
TaskUpdate(taskId="2", status="completed")    # When done, repeat for each subtask

# PARALLEL, all in ONE message:
# 1. Framework detection (hook handles this, but also scan manually)
Grep(pattern="vitest|jest|mocha|playwright|cypress", glob="package.json", output_mode="content")
Grep(pattern="pytest|unittest|hypothesis", glob="pyproject.toml", output_mode="content")
Grep(pattern="pytest|unittest|hypothesis", glob="requirements*.txt", output_mode="content")

# 2. Real-service infrastructure
Glob(pattern="**/docker-compose*.yml")
Glob(pattern="**/testcontainers*")
Grep(pattern="testcontainers", glob="**/package.json", output_mode="content")
Grep(pattern="testcontainers", glob="**/requirements*.txt", output_mode="content")

# 3. Existing test structure
Glob(pattern="**/tests/**/*.test.*")
Glob(pattern="**/tests/**/*.spec.*")
Glob(pattern="**/__tests__/**/*")
Glob(pattern="**/test_*.py")

# 4. Scope files (what to test)
# If SCOPE specified, find matching source files
Grep(pattern=SCOPE, output_mode="files_with_matches")

# Baseline: npx vitest run --coverage --reporter=json | pytest --cov=<scope> --cov-report=json | go test -coverprofile=coverage.out ./...
# Rank uncovered code by risk and record WHY each target was chosen:
# changed code, complex branches, error paths, security and money paths, past bugs
# gap_map[tier] = [{"target": "src/billing/refund.ts:roundRefund", "why": "money path, fixed in #812"}]

# Unit tests agent (worktree-isolated)
if "unit" in TIERS:
    Agent(
        subagent_type="ork:test-generator",
        isolation="worktree",
        prompt=f"""Generate unit tests for: {SCOPE}
        Risk targets, each with why: {gap_map["unit"]}
        Framework: {detected_framework}
        Existing tests: {existing_test_files}

        Focus on:
        - AAA pattern (Arrange-Act-Assert)
        - Parametrized tests for multiple inputs
        - MSW/VCR for HTTP mocking (never mock fetch directly)
        - Factory-based test data (FactoryBoy/faker-js)
        - Edge cases: empty input, errors, timeouts, boundary values
        - BEHAVIOUR GATE: write a test ONLY if it asserts an observable result. Never write a
          mock-call-only, assertion-free, tautological, or source-reading test (references/behaviour-gate.md)""",
        run_in_background=True,
        max_turns=50,
        model=MODEL_OVERRIDE
    )

# Integration + E2E agents follow the same pattern:
# - subagent_type="ork:test-generator", isolation="worktree", run_in_background=True, same targets + BEHAVIOUR GATE lines
# - Integration focus: API endpoints (Supertest/httpx), real DB, contract tests (Pact), Zod schema validation
# - E2E focus: Playwright, semantic locators, Page Object Model, axe-core a11y, visual regression
#
# Special case: emulate (Vercel Labs stateful API emulation):
# When integration tests need GitHub/Stripe/Resend/Okta/etc. emulated
# (HMAC webhooks, parallel port isolation, full config from scratch),
# spawn emulate-engineer instead of test-generator for that tier:
# - subagent_type="ork:emulate-engineer" (same isolation="worktree" form)
# - Pairs with emulate-seed skill for seed YAML patterns

# Run test commands per tier (PARALLEL if independent):
# Unit: npx vitest run tests/unit/ OR pytest tests/unit/
# Integration: npx vitest run tests/integration/ OR pytest tests/integration/
# E2E: npx playwright test

# Collect: pass count, fail count, error details, coverage delta

Workflow(
  scriptPath="${CLAUDE_SKILL_DIR}/workflows/heal-loop.js",
  args={"testCommand": "<tier test command>", "tier": "unit", "testGlob": "tests/unit/",
        "maxIterations": 3}   # from the effort table above; omitted defaults to 3
)
# One invocation per tier that has failures.