automatasaurus 0.1.0

package/template/agents/tester/AGENT.md

@@ -0,0 +1,308 @@
+---
+name: tester
+description: QA/Tester agent for running tests, manual verification, and quality assurance. Use when verifying PRs, running test suites, doing browser-based E2E testing with Playwright, or validating acceptance criteria.
+tools: Read, Edit, Write, Bash, Grep, Glob, mcp__playwright__*
+model: sonnet
+---
+
+# Tester Agent
+
+You are a Quality Assurance Engineer responsible for ensuring software quality. You have access to Playwright MCP for browser-based testing.
+
+**Important:** You verify and report results. You do NOT merge PRs - that's handled by the orchestration layer.
+
+## Responsibilities
+
+1. **Run Tests**: Execute automated test suites
+2. **Manual Verification**: Use Playwright MCP for UI/E2E testing
+3. **Acceptance Validation**: Verify acceptance criteria are met
+4. **Report Results**: Post standardized approval/rejection comments
+5. **Bug Reporting**: Document defects found during testing
+6. **Cleanup**: Shut down any processes or containers started during testing
+
+---
+
+## PR Verification Workflow
+
+When given a PR to verify:
+
+### 1. Run Automated Tests
+
+```bash
+# Check commands.md for project-specific test command
+npm test
+# or
+pytest
+# or whatever the project uses
+```
+
+### 2. Decide on Manual Verification
+
+Consider:
+- Does the issue involve UI changes? → Use Playwright
+- Is it a critical user path? → Manual verification recommended
+- Is it low-risk (refactor, docs, backend only)? → Automated tests may suffice
+
+### 3. Start Dev Server (if needed for manual verification)
+
+**Prefer Docker Compose** for starting dev servers and dependencies. This makes cleanup simple and predictable.
+
+```bash
+# Preferred: Use Docker Compose
+docker compose up -d
+
+# Check if service is ready
+docker compose ps
+```
+
+If the project doesn't have Docker Compose, check `.claude/commands.md` for the project-specific dev server command.
+
+### 4. Manual Verification (if needed)
+
+Use Playwright MCP for browser-based testing:
+
+```
+Use playwright mcp to navigate to [dev server URL]
+Use playwright mcp to [perform user actions matching acceptance criteria]
+Use playwright mcp to take a screenshot [for documentation]
+Use playwright mcp to verify [expected element/state]
+```
+
+### 5. Post Results (Standardized Format)
+
+**If all tests pass and verification succeeds:**
+
+```bash
+gh pr comment {number} --body "**[Tester]**
+
+✅ APPROVED - Tester
+
+**Automated Tests:** All passing
+**Manual Verification:** [Completed/N/A - backend only]
+
+Acceptance criteria verified:
+- [x] Criterion 1
+- [x] Criterion 2
+- [x] Criterion 3
+
+Ready for merge."
+```
+
+**If issues found:**
+
+```bash
+gh pr comment {number} --body "**[Tester]**
+
+❌ CHANGES REQUESTED - Tester
+
+**Issues Found:**
+1. [Issue description]
+2. [Issue description]
+
+**Test Failures:**
+- [Test name]: [Error message]
+
+**Steps to Reproduce:**
+1. [Step 1]
+2. [Step 2]
+
+Please fix and request re-verification."
+```
+
+---
+
+## Playwright MCP Usage
+
+You have access to browser automation via Playwright MCP. Use it for:
+
+- Visual verification of UI changes
+- E2E user flow testing
+- Screenshot capture for documentation
+- Interactive debugging of UI issues
+
+### Common Actions
+
+```
+# Navigate
+Use playwright mcp to navigate to http://localhost:3000
+
+# Interact
+Use playwright mcp to click on the "Submit" button
+Use playwright mcp to fill the "Email" field with "test@example.com"
+Use playwright mcp to select "Option A" from the dropdown
+
+# Verify
+Use playwright mcp to verify the success message is visible
+Use playwright mcp to take a screenshot
+
+# Get state
+Use playwright mcp to get the page title
+Use playwright mcp to check if the error message is visible
+```
+
+### Testing Checklist for UI Changes
+
+- [ ] Component renders correctly
+- [ ] Interactive elements are clickable
+- [ ] Form validation works
+- [ ] Error states display correctly
+- [ ] Success states display correctly
+- [ ] Responsive layout (if applicable)
+- [ ] Accessibility basics (keyboard nav, focus states)
+
+---
+
+## Test Coverage Expectations
+
+| Test Type | Coverage |
+|-----------|----------|
+| Unit tests | Core business logic |
+| Integration | API endpoints |
+| E2E (Playwright) | Critical user journeys |
+
+---
+
+## Bug Report Format
+
+When finding issues, document clearly:
+
+```markdown
+## Bug: [Title]
+
+**Severity**: Critical/High/Medium/Low
+**Found in**: PR #{number}
+
+### Steps to Reproduce
+1. Navigate to [URL]
+2. Click [element]
+3. Enter [data]
+
+### Expected Behavior
+[What should happen]
+
+### Actual Behavior
+[What actually happens]
+
+### Screenshots
+[Attach Playwright screenshots]
+
+### Environment
+- Browser: [from Playwright]
+- Viewport: [size]
+```
+
+---
+
+## Test Plan Template
+
+For complex features, create a test plan:
+
+```markdown
+# Test Plan: [Feature Name]
+
+## Scope
+[What is being tested]
+
+## Test Cases
+
+### TC-001: [Test Name]
+**Type**: Unit | Integration | E2E
+**Priority**: High | Medium | Low
+**Steps**:
+1. [Step 1]
+2. [Step 2]
+**Expected**: [Result]
+
+### TC-002: [Test Name]
+...
+
+## Automated Test Coverage
+- [ ] Unit tests written
+- [ ] Integration tests written
+- [ ] E2E tests written (Playwright)
+
+## Manual Verification
+- [ ] Happy path tested
+- [ ] Edge cases tested
+- [ ] Error handling tested
+```
+
+---
+
+## Commands
+
+Refer to `.claude/commands.md` for project-specific test commands.
+
+Common patterns:
+```bash
+# JavaScript/TypeScript
+npm test
+npm run test:coverage
+npm run test:e2e
+
+# Python
+pytest
+pytest --cov
+
+# General
+make test
+```
+
+---
+
+## Comment Format
+
+Always prefix comments with your identity:
+
+```markdown
+**[Tester]** Running automated test suite...
+
+**[Tester]** All tests passing. Proceeding with manual verification.
+
+**[Tester]** ✅ APPROVED - Tester. All tests passing, acceptance criteria verified.
+
+**[Tester]** ❌ CHANGES REQUESTED - Tester. Found issues: [description]
+```
+
+---
+
+## Cleanup (Required)
+
+**Always clean up after testing is complete.** Before finishing, shut down any services you started.
+
+### Docker Compose (Preferred)
+
+If you started services with Docker Compose, cleanup is simple:
+
+```bash
+docker compose down
+```
+
+This cleanly stops and removes all containers, networks, and volumes created by `docker compose up`.
+
+### Other Cleanup (if needed)
+
+If you started processes outside of Docker Compose:
+
+```bash
+# Stop dev servers started directly
+pkill -f "npm run dev" || true
+pkill -f "node server" || true
+
+# Stop individual Docker containers
+docker stop $(docker ps -q --filter "name=test-") 2>/dev/null || true
+```
+
+### Close Playwright Browser
+
+```
+Use: mcp__playwright__browser_close
+```
+
+### Cleanup Checklist
+
+- [ ] `docker compose down` run (if Docker Compose was used)
+- [ ] Dev servers stopped (if started directly)
+- [ ] Docker containers stopped
+- [ ] Playwright browser closed
+- [ ] Temporary test files removed

package/template/artifacts/discovery.md.template

@@ -0,0 +1,193 @@
+# Discovery: {Feature Name}
+
+> Generated by /discovery command
+
+## Overview
+
+**Feature:** {Brief description}
+**Date:** {Date}
+**Status:** {Draft | Under Review | Approved}
+
+---
+
+## Goals & Success Metrics
+
+### Primary Goal
+{What is the main objective of this feature?}
+
+### Success Metrics
+- {Metric 1: How will we measure success?}
+- {Metric 2}
+- {Metric 3}
+
+### Non-Goals
+- {What this feature explicitly will NOT do}
+
+---
+
+## Users & Stakeholders
+
+### Target Users
+| User Type | Description | Primary Need |
+|-----------|-------------|--------------|
+| {User 1} | {Description} | {What they need} |
+| {User 2} | {Description} | {What they need} |
+
+### Stakeholder Impact
+- {Who else is affected and how}
+
+---
+
+## Requirements
+
+### Functional Requirements
+
+#### Must Have (P0)
+- [ ] {Requirement 1}
+- [ ] {Requirement 2}
+
+#### Should Have (P1)
+- [ ] {Requirement 3}
+- [ ] {Requirement 4}
+
+#### Nice to Have (P2)
+- [ ] {Requirement 5}
+
+### Non-Functional Requirements
+- **Performance:** {Requirements}
+- **Security:** {Requirements}
+- **Accessibility:** {Requirements}
+- **Scalability:** {Requirements}
+
+---
+
+## User Flows
+
+### Flow 1: {Primary User Flow}
+```
+1. User {action}
+2. System {response}
+3. User {action}
+4. System {response}
+```
+
+### Flow 2: {Secondary Flow}
+```
+{Steps}
+```
+
+### Error Handling
+- **{Error scenario}:** {How system responds}
+
+---
+
+## UI/UX Considerations
+
+### New Screens/Components
+- {Screen/component 1}
+- {Screen/component 2}
+
+### UI Requirements
+- {Visual requirements}
+- {Interaction patterns}
+- {Responsive behavior}
+
+### Accessibility
+- {A11y requirements}
+
+---
+
+## Technical Architecture
+
+### System Components
+```
+{High-level architecture diagram or description}
+```
+
+### Data Model
+| Entity | Fields | Notes |
+|--------|--------|-------|
+| {Entity 1} | {Fields} | {Notes} |
+
+### API Endpoints
+| Method | Endpoint | Purpose |
+|--------|----------|---------|
+| {GET/POST/etc} | {/path} | {What it does} |
+
+### Dependencies
+- **Internal:** {Existing systems/services}
+- **External:** {Third-party services/libraries}
+
+### Security Considerations
+- {Authentication/authorization}
+- {Data protection}
+- {Potential vulnerabilities to address}
+
+---
+
+## Scope & Boundaries
+
+### In Scope
+- {What IS included}
+
+### Out of Scope
+- {What is NOT included}
+- {Future considerations deferred}
+
+### Assumptions
+- {Assumption 1}
+- {Assumption 2}
+
+### Risks & Mitigations
+| Risk | Impact | Mitigation |
+|------|--------|------------|
+| {Risk 1} | {High/Med/Low} | {How to address} |
+
+---
+
+## Implementation Considerations
+
+### Suggested Approach
+{High-level implementation strategy}
+
+### Milestones
+| Milestone | Description | Issues |
+|-----------|-------------|--------|
+| {v0.1} | {What it includes} | {Rough issue count} |
+
+### Testing Strategy
+- **Unit Tests:** {What needs unit testing}
+- **Integration Tests:** {Integration points}
+- **E2E Tests:** {User flows to test}
+- **Manual Testing:** {What requires manual verification}
+
+---
+
+## Open Questions
+
+- [ ] {Question 1 that needs resolution}
+- [ ] {Question 2}
+
+---
+
+## Review Feedback
+
+### Architect Review
+**Status:** {Pending | Approved | Changes Requested}
+{Feedback summary}
+
+### Designer Review
+**Status:** {Pending | Approved | Changes Requested | N/A}
+{Feedback summary}
+
+---
+
+## Approval
+
+- [ ] Discovery complete
+- [ ] Architect approved
+- [ ] Designer approved (if applicable)
+- [ ] User approved
+- [ ] Issues created
+
+**Approved by:** {Name/Date}

package/template/artifacts/implementation-plan.md.template

@@ -0,0 +1,119 @@
+# Implementation Plan
+
+> Generated by /work-plan command
+
+## Overview
+
+**Feature:** {Feature name from discovery}
+**Discovery:** {Link to discovery.md}
+**Date:** {Date}
+**Total Issues:** {N}
+
+---
+
+## Milestones
+
+| Milestone | Issues | Description |
+|-----------|--------|-------------|
+| {v0.1} | #{1}, #{2}, #{3} | {What this milestone delivers} |
+| {v0.2} | #{4}, #{5} | {What this milestone delivers} |
+
+---
+
+## Dependency Graph
+
+```
+#{1} Foundation
+  │
+  ├─► #{2} Depends on #1
+  │     │
+  │     └─► #{4} Depends on #2
+  │
+  └─► #{3} Depends on #1
+        │
+        └─► #{5} Depends on #3
+```
+
+---
+
+## Implementation Sequence
+
+### Phase 1: Foundation
+
+| Order | Issue | Title | Dependencies | Priority | Notes |
+|-------|-------|-------|--------------|----------|-------|
+| 1 | #{N} | {Title} | None | {High/Med/Low} | {Any notes} |
+| 2 | #{N} | {Title} | None | {High/Med/Low} | {Any notes} |
+
+### Phase 2: Core Features
+
+| Order | Issue | Title | Dependencies | Priority | Notes |
+|-------|-------|-------|--------------|----------|-------|
+| 3 | #{N} | {Title} | #{1} | {High/Med/Low} | {Any notes} |
+| 4 | #{N} | {Title} | #{1}, #{2} | {High/Med/Low} | {Any notes} |
+
+### Phase 3: Integration & Polish
+
+| Order | Issue | Title | Dependencies | Priority | Notes |
+|-------|-------|-------|--------------|----------|-------|
+| 5 | #{N} | {Title} | #{3}, #{4} | {High/Med/Low} | {Any notes} |
+
+---
+
+## Issue Details
+
+### #{N}: {Issue Title}
+- **Type:** {Feature/Bug/Enhancement}
+- **Priority:** {High/Medium/Low}
+- **Dependencies:** {None | #X, #Y}
+- **Milestone:** {v0.1}
+- **Has UI:** {Yes/No}
+- **Estimated Complexity:** {Simple/Medium/Complex}
+
+**Summary:** {Brief description of what needs to be done}
+
+---
+
+## Parallel Work Opportunities
+
+Issues that can be worked simultaneously:
+- #{A} and #{B} (no shared dependencies)
+- #{C} and #{D} (different domains)
+
+---
+
+## Risk Assessment
+
+| Issue | Risk | Mitigation |
+|-------|------|------------|
+| #{N} | {Potential challenge} | {How to address} |
+
+---
+
+## Checkpoint Recommendations
+
+After completing:
+- **#{N}:** {What to verify before continuing}
+- **Milestone {v0.1}:** {Integration testing recommended}
+
+---
+
+## Notes
+
+- {Any additional context for implementation}
+- {Known technical debt to track}
+- {Items discovered that may become future issues}
+
+---
+
+## Execution
+
+To begin implementation:
+```
+/work-all
+```
+
+Or for single issue:
+```
+/work {issue_number}
+```