nitm-ai-dev-toolkit 3.0.15

package/src/monorepo/.claude/agents-snippets/tdd.md

@@ -0,0 +1,18 @@
+# TDD Coordinator Agent
+
+Implement the following feature using test-driven development. Use subagents to guide each phase of the red-green-refactor cycle.
+
+## Workflow
+
+For each requirement:
+
+1. **Red** — Use the Red agent to write failing tests that define the expected behavior
+2. **Green** — Use the Green agent to write the minimal code needed to pass the tests
+3. **Refactor** — Use the Refactor agent to improve code quality while keeping tests green
+
+## Rules
+
+- Never skip the Red phase — tests must fail first
+- Green phase writes minimal code only — no premature optimization
+- Refactor phase must not change behavior — all tests must remain green
+- Each cycle should be small and focused (one behavior at a time)

package/src/monorepo/.claude/commands/assign-tasks.md

@@ -0,0 +1,13 @@
+---
+description: Create {{ISSUE_TRACKER}} tickets from requirements or task files
+allowed-tools: "Read, Write, Edit, Bash(*)"
+argument-hint: "requirements or task file path"
+---
+
+# Create Tickets from Requirements
+
+## Agent Dispatch
+> **Recommended agent:** `fixer`
+> Task assignment and execution
+
+**CRITICAL: READ:** [.claude/prompt-snippets/assign-tasks.md](../prompt-snippets/assign-tasks.md)

package/src/monorepo/.claude/commands/bootstrap-patch.md

@@ -0,0 +1,15 @@
+---
+description: Patch AI instructions by fetching updates from the toolkit repo and applying new/updated/missing guidance
+allowed-tools: "Read, Write, Edit, Bash(*)"
+argument-hint: optional patch options
+---
+
+# Patch AI Instructions
+
+## Agent Dispatch
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Standard patch — incremental changes to existing config |
+| `planner` | Complex patch — cross-cutting changes needing analysis first |
+
+Follow the prompt defined in [.claude/prompt-snippets/bootstrap-patch.md](../prompt-snippets/bootstrap-patch.md).

package/src/monorepo/.claude/commands/bootstrap-upgrade.md

@@ -0,0 +1,15 @@
+---
+description: Upgrade AI instructions from pre-3.0 inline pattern to 3.0+ snippet architecture
+allowed-tools: "Read, Write, Edit, Bash(*)"
+argument-hint: "no arguments required"
+---
+
+# Bootstrap Upgrade
+
+## Agent Dispatch
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Standard upgrade — version bump and migration |
+| `planner` | Complex upgrade — breaking changes needing dependency analysis |
+
+Follow the prompt defined in [.claude/prompt-snippets/bootstrap-upgrade.md](../prompt-snippets/bootstrap-upgrade.md).

package/src/monorepo/.claude/commands/bootstrap.md

@@ -0,0 +1,15 @@
+---
+description: Bootstrap AI instructions for monorepo by analyzing workspace and customizing templates
+allowed-tools: "Read, Write, Edit, Bash(*)"
+argument-hint: optional bootstrap options
+---
+
+# Bootstrap Monorepo AI Instructions
+
+## Agent Dispatch
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Standard bootstrap — project analysis and template customization |
+| `planner` | Complex bootstrap — needs requirements gathering and architecture decisions first |
+
+Follow the prompt defined in [.claude/prompt-snippets/bootstrap.md](../prompt-snippets/bootstrap.md).

package/src/monorepo/.claude/commands/commit-push.md

@@ -0,0 +1,13 @@
+---
+description: Commit and push changes with conventional commit messages
+allowed-tools: "Bash(git:*)"
+argument-hint: optional commit message or options
+---
+
+# Commit and Push Changes
+
+## Agent Dispatch
+> **Recommended agent:** `fixer`
+> Git operations, execution-focused
+
+Follow the prompt defined in [.claude/prompt-snippets/commit-push.md](../prompt-snippets/commit-push.md).

package/src/monorepo/.claude/commands/constitution.md

@@ -0,0 +1,15 @@
+---
+description: Create or update the project constitution defining core principles and guidelines
+argument-hint: "no arguments required"
+allowed-tools: "Read, Write, Edit, Bash(*)"
+---
+
+# Project Constitution
+
+## Agent Dispatch
+| Agent | When to use |
+|-------|-------------|
+| `oracle` | Project principles and governance — architectural decisions |
+| `planner` | Project conventions and standards — team norms and practices |
+
+Follow the prompt defined in [.claude/prompt-snippets/constitution.md](../prompt-snippets/constitution.md).

package/src/monorepo/.claude/commands/create-skill.md

@@ -0,0 +1,15 @@
+---
+description: Create a new agent skill following VS Code and agentskills.io specifications
+allowed-tools: "Read, Write, Edit, Bash(*)"
+argument-hint: "skill name and requirements"
+tags: [skill-creation, agent-skills, documentation, automation]
+version: 1.0.0
+---
+
+# Create Agent Skill
+
+## Agent Dispatch
+> **Recommended agent:** `fixer`
+> Skill file creation
+
+Follow the prompt defined in [.claude/prompt-snippets/create-skill.md](../prompt-snippets/create-skill.md).

package/src/monorepo/.claude/commands/implement-feature.md

@@ -0,0 +1,15 @@
+---
+description: Implement a feature by completing tasks sequentially
+allowed-tools: "Read, Write, Edit, Bash(*)"
+argument-hint: feature specification or task list
+---
+
+# Implement Feature
+
+## Agent Dispatch
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Bounded feature work — spec is clear, files are known |
+| `feature-builder` | Complex feature — needs research, planning, and coordination |
+
+Follow the prompt defined in [.claude/prompt-snippets/implement-feature.md](../prompt-snippets/implement-feature.md).

package/src/monorepo/.claude/commands/implement-fixes.md

@@ -0,0 +1,15 @@
+---
+description: Implement bug fixes with proper tracking and validation
+allowed-tools: "Read, Write, Edit, Bash(*)"
+argument-hint: "bug description or fix requirements"
+---
+
+# Implement Fixes
+
+## Agent Dispatch
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Bounded fixes — clear root cause, known scope |
+| `oracle` | Ambiguous fixes — root cause unclear, needs investigation first |
+
+Follow the prompt defined in [.claude/prompt-snippets/implement-fixes.md](../prompt-snippets/implement-fixes.md).

package/src/monorepo/.claude/commands/implement.md

@@ -0,0 +1,15 @@
+---
+description: Execute implementation tasks from a task list or specification
+argument-hint: "task list or specification"
+allowed-tools: "Read, Write, Edit, Bash(*)"
+---
+
+# Execute Implementation Tasks
+
+## Agent Dispatch
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Bounded implementation — clear spec, known target |
+| `oracle` | Ambiguous implementation — needs architectural judgment first |
+
+Follow the prompt defined in [.claude/prompt-snippets/implement.md](../prompt-snippets/implement.md).

package/src/monorepo/.claude/commands/plan.md

@@ -0,0 +1,15 @@
+---
+description: Create an implementation plan from a feature specification or requirement
+allowed-tools: "Read, Write, Edit, Bash(*)"
+argument-hint: feature specification or requirement
+---
+
+# Create Implementation Plan
+
+## Agent Dispatch
+| Agent | When to use |
+|-------|-------------|
+| `planner` | Standard implementation plan — breaking work into tasks |
+| `oracle` | Architectural planning — trade-offs, system design, risk analysis |
+
+Follow the prompt defined in [.claude/prompt-snippets/plan.md](../prompt-snippets/plan.md).

package/src/monorepo/.claude/commands/playwright-test.md

@@ -0,0 +1,13 @@
+---
+description: Run or create E2E tests using Playwright
+allowed-tools: "Read, Write, Edit, Bash(*)"
+argument-hint: test file or test description
+---
+
+# Playwright E2E Testing
+
+## Agent Dispatch
+> **Recommended agent:** `fixer`
+> Test generation and execution
+
+Follow the prompt defined in [.claude/prompt-snippets/playwright-test.md](../prompt-snippets/playwright-test.md).

package/src/monorepo/.claude/commands/ponytail-audit.md

@@ -0,0 +1,15 @@
+---
+description: Audit the whole repo for over-engineering and identify what can be deleted
+allowed-tools: "Read, Grep, Bash"
+argument-hint: "no arguments required"
+---
+
+## Agent Dispatch
+
+> **Recommended agent:** `oracle`
+> Whole-repo over-engineering analysis
+
+
+# Ponytail Audit
+
+Follow the prompt defined in [.claude/prompt-snippets/ponytail-audit.md](../prompt-snippets/ponytail-audit.md).

package/src/monorepo/.claude/commands/ponytail-debt.md

@@ -0,0 +1,15 @@
+---
+description: "Harvest ponytail: comments into a tracked debt ledger"
+allowed-tools: "Read, Grep, Bash"
+argument-hint: "no arguments required"
+---
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Debt ledger harvesting
+
+
+# Ponytail Debt
+
+Follow the prompt defined in [.claude/prompt-snippets/ponytail-debt.md](../prompt-snippets/ponytail-debt.md).

package/src/monorepo/.claude/commands/ponytail-gain.md

@@ -0,0 +1,15 @@
+---
+description: Show ponytail's measured impact scoreboard (less code, cost, time)
+allowed-tools: "Read"
+argument-hint: "no arguments required"
+---
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Impact scoreboard display
+
+
+# Ponytail Gain
+
+Follow the prompt defined in [.claude/prompt-snippets/ponytail-gain.md](../prompt-snippets/ponytail-gain.md).

package/src/monorepo/.claude/commands/ponytail-help.md

@@ -0,0 +1,15 @@
+---
+description: Quick reference for ponytail levels, skills, and commands
+allowed-tools: "Read"
+argument-hint: "no arguments required"
+---
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Quick-reference display
+
+
+# Ponytail Help
+
+Follow the prompt defined in [.claude/prompt-snippets/ponytail-help.md](../prompt-snippets/ponytail-help.md).

package/src/monorepo/.claude/commands/ponytail-review.md

@@ -0,0 +1,15 @@
+---
+description: Review changes for over-engineering and identify what can be deleted
+allowed-tools: "Read, Grep"
+argument-hint: "no arguments required"
+---
+
+## Agent Dispatch
+
+> **Recommended agent:** `oracle`
+> Diff-level over-engineering review
+
+
+# Ponytail Review
+
+Follow the prompt defined in [.claude/prompt-snippets/ponytail-review.md](../prompt-snippets/ponytail-review.md).

package/src/monorepo/.claude/commands/ponytail.md

@@ -0,0 +1,15 @@
+---
+description: Switch ponytail intensity level (lite/full/ultra/off)
+allowed-tools: "Read, Grep, Bash, Edit, Write"
+argument-hint: "optional level (lite/full/ultra/off)"
+---
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Apply YAGNI/stdlib discipline
+
+
+# Ponytail
+
+Follow the prompt defined in [.claude/prompt-snippets/ponytail.md](../prompt-snippets/ponytail.md).

package/src/monorepo/.claude/commands/release-notes.md

@@ -0,0 +1,13 @@
+---
+description: Generate release notes from git commits (web, git tag, or documentation)
+allowed-tools: "Read, Write, Edit, Bash(*)"
+argument-hint: version or tag
+---
+
+# Generate Release Notes
+
+## Agent Dispatch
+> **Recommended agent:** `fixer`
+> Release notes generation
+
+Follow the prompt defined in [.claude/prompt-snippets/release-notes.md](../prompt-snippets/release-notes.md).

package/src/monorepo/.claude/commands/review-pr.md

@@ -0,0 +1,15 @@
+---
+description: Conduct comprehensive pull request code review
+allowed-tools: "Read, Grep"
+argument-hint: PR number or branch
+---
+
+# Review Pull Request
+
+## Agent Dispatch
+| Agent | When to use |
+|-------|-------------|
+| `reviewer` | Standard PR review — correctness, test coverage, patterns |
+| `oracle` | Complex PR review — architecture, security, cross-system impact |
+
+Follow the prompt defined in [.claude/prompt-snippets/review-pr.md](../prompt-snippets/review-pr.md).

package/src/monorepo/.claude/commands/review-staged.md

@@ -0,0 +1,15 @@
+---
+description: Review currently staged files before committing
+allowed-tools: "Read, Grep, Bash(git:*)"
+argument-hint: "no arguments required"
+---
+
+# Review Staged Files
+
+## Agent Dispatch
+| Agent | When to use |
+|-------|-------------|
+| `reviewer` | Standard pre-commit review — correctness, style, patterns |
+| `oracle` | Complex staged change — trade-offs, security, scalability |
+
+Follow the prompt defined in [.claude/prompt-snippets/review-staged.md](../prompt-snippets/review-staged.md).

package/src/monorepo/.claude/commands/review.md

@@ -0,0 +1,15 @@
+---
+description: Conduct code review for files or features
+allowed-tools: "Read, Grep"
+argument-hint: file path or feature description
+---
+
+# Code Review
+
+## Agent Dispatch
+| Agent | When to use |
+|-------|-------------|
+| `reviewer` | Standard code review — correctness, style, patterns |
+| `oracle` | Complex architectural review — trade-offs, security, scalability |
+
+Follow the prompt defined in [.claude/prompt-snippets/review.md](../prompt-snippets/review.md).

package/src/monorepo/.claude/commands/specify.md

@@ -0,0 +1,15 @@
+---
+description: Create a feature specification from a natural language description
+allowed-tools: "Read, Write, Edit, Bash(*)"
+argument-hint: feature description
+---
+
+# Create Feature Specification
+
+## Agent Dispatch
+| Agent | When to use |
+|-------|-------------|
+| `planner` | Standard feature specification — requirements and acceptance criteria |
+| `oracle` | Complex specification — cross-system design, API contracts, security |
+
+Follow the prompt defined in [.claude/prompt-snippets/specify.md](../prompt-snippets/specify.md).

package/src/monorepo/.claude/commands/tasks.md

@@ -0,0 +1,13 @@
+---
+description: Generate an actionable task list from a specification or plan
+allowed-tools: "Read, Write, Edit, Bash(*)"
+argument-hint: specification or plan file
+---
+
+# Generate Task List
+
+## Agent Dispatch
+> **Recommended agent:** `planner`
+> Task breakdown and management
+
+Follow the prompt defined in [.claude/prompt-snippets/tasks.md](../prompt-snippets/tasks.md).

package/src/monorepo/.claude/prompt-snippets/assign-tasks.md

@@ -0,0 +1,169 @@
+# Create Tickets from Requirements
+
+Parse requirement documents or task breakdown files and create structured tickets in {{ISSUE_TRACKER}}.
+
+## Usage
+
+```
+/assign-tasks docs/features/requirements.md
+/assign-tasks apps/{{APP_NAME}}/docs/features/{{FEATURE_NAME}}/tasks.md
+```
+
+## Task Consolidation Rules (CRITICAL)
+
+Before creating tickets, consolidate tasks to reduce noise and improve focus:
+
+### Grouping Guidelines
+
+- **Merge related work**: Combine tasks touching the same component or feature area
+- **Bundle by deliverable**: Group by what gets shipped, not individual steps
+- **Collapse small items**: Tasks < 2 story points should be subtasks or merged
+- **Limit hierarchy depth**: Prefer Epic → Story → Task (avoid Subtasks when possible)
+
+### Maximum Ticket Counts
+
+| Feature Size     | Max Stories | Max Tasks/Story | Max Subtasks/Task |
+| ---------------- | ----------- | --------------- | ----------------- |
+| Small (< 8 SP)   | 1-2         | 2-3             | 0                 |
+| Medium (8-21 SP) | 2-4         | 3-4             | 2-4               |
+| Large (21-55 SP) | 4-8         | 4-6             | 4-8               |
+| XL (55+ SP)      | 6-12        | 5-8             | 8-15              |
+
+### Before Creating Tickets, Ask:
+
+1. Can these 2+ tasks be combined into one?
+2. Is this subtask really necessary, or is it just a step?
+3. Would a developer naturally do these together anyway?
+4. Does each ticket represent meaningful, demonstrable progress?
+
+## Issue Tracker Tool Access
+
+> **Full details:** See the `issue-tracker` skill in `.agents/skills/issue-tracker/SKILL.md` for MCP tools reference, CLI fallback strategy, tracker configuration, and epic discovery workflow.
+> For CLI-specific commands, see the matching skill: `.agents/skills/{acli,gh-cli,linear-cli}/SKILL.md`.
+
+When interacting with {{ISSUE_TRACKER}}, use MCP tools first (see the `issue-tracker` skill for the tools table). If MCP is unavailable, fall back to the CLI skill matching your tracker.
+
+## Process
+
+1. **Parse Document**:
+   - Load the specified document (.md, .txt, .json)
+   - Detect document structure (headers, lists, task categories)
+   - Extract task hierarchy: Epic → Story → Task → Subtask
+
+2. **Consolidate & Classify** (do this BEFORE creating tickets):
+   - **Group related items** by component, feature area, or deliverable
+   - **Merge small tasks** (< 2 SP) into related larger tasks
+   - **Eliminate redundant subtasks** that are obvious steps
+   - **Validate counts** against maximum limits above
+
+3. **Classify Consolidated Tasks**:
+   - **Epic**: Large features, 13+ story points
+   - **Story**: User-focused deliverable, 3-13 story points (prefer larger stories)
+   - **Task**: Implementation work, 2-8 story points (avoid < 2 SP tasks)
+   - **Subtask**: Only for complex tasks needing breakdown, 1-3 story points
+
+4. **Estimate Effort**:
+   - 0.5-1 hours → Merge with related task (too small alone)
+   - 2-3 hours → 2 story points
+   - 4-6 hours → 3-5 story points
+   - 7-12 hours → 8 story points
+   - 13+ hours → 13 story points (consider splitting into stories)
+
+5. **Create Tickets**:
+   - Create in proper hierarchy order (Epics first, then Stories, then Tasks)
+   - Link child issues to parents
+   - Set assignees, labels, and story points
+   - Create dependency links where noted
+
+6. **Generate Report**:
+   - List all created tickets with IDs
+   - Show hierarchy and relationships
+   - Report total story points
+   - **Show consolidation summary**: "Merged X items into Y tickets"
+
+## API Rate Limiting & Throttling
+
+**CRITICAL**: {{ISSUE_TRACKER}} APIs have rate limits. When creating multiple tickets:
+
+### Batch Strategy
+
+- **Small batches** (< 5 tickets): Create all tickets immediately
+- **Medium batches** (5-15 tickets): Create in groups of 5 with 2-second delays
+- **Large batches** (15+ tickets): Create in groups of 5 with 3-5 second delays
+
+### Implementation Pattern
+
+```
+1. Create Epic(s) first → Wait 2 seconds
+2. Create Stories (batch of 5) → Wait 2 seconds
+3. Create next Stories (batch of 5) → Wait 2 seconds
+4. Create Tasks (batch of 5) → Wait 3 seconds
+5. Continue batching with delays
+```
+
+### Error Handling
+
+- **429 (Rate Limit)**: Wait 10 seconds, then retry
+- **503 (Service Unavailable)**: Wait 5 seconds, then retry
+- **Max retries**: 3 attempts per ticket
+- **Failed tickets**: Report at end with error details
+
+### Progress Reporting
+
+```
+Creating tickets...
+✓ Epic created: PROJ-123
+  [Waiting 2s to avoid rate limiting...]
+✓ Stories created: PROJ-124, PROJ-125, PROJ-126 (batch 1/3)
+  [Waiting 2s...]
+✓ Stories created: PROJ-127, PROJ-128, PROJ-129 (batch 2/3)
+```
+
+### Best Practices
+
+- ⚠️ **Never create more than 5 tickets without a delay**
+- ⚠️ **Always wait at least 2 seconds between batches**
+- ⚠️ **Increase delays if rate limit errors occur**
+- ✓ **Show progress updates between batches**
+- ✓ **Report any failed tickets with retry instructions**
+
+## Anti-Patterns to Avoid
+
+❌ **Don't create separate tickets for**:
+
+- "Create file X" and "Configure file X" (one ticket)
+- "Write tests" and "Run tests" (one ticket)
+- Each individual file change in a feature
+- Steps that take < 1 hour
+
+✅ **Do combine into single tickets**:
+
+- All database work for an entity (model + migration + seeder)
+- Related API endpoints (CRUD operations for one resource)
+- All configuration and setup for a feature
+- Testing for a component (unit + integration)
+
+## Document Format Support
+
+**Markdown Headers**:
+
+```markdown
+# Epic: Feature Name
+
+## Story: User Story (combines related implementation)
+
+### Task: Implementation Task (only if story needs breakdown)
+```
+
+**Dependency Keywords**:
+
+- "depends on"
+- "after"
+- "requires"
+- "blocks"
+
+## Configuration
+
+- **Project Key**: `{{PROJECT_KEY}}`
+- **Default Assignee**: `{{DEFAULT_ASSIGNEE}}`
+- **Labels**: Based on content categories