nitm-ai-dev-toolkit 3.0.15

package/src/repo/.github/instructions/documentation.instructions.md

@@ -0,0 +1,14 @@
+---
+applyTo: "**/*"
+description: "Documentation standards for features and fixes"
+---
+
+# Documentation Guidelines
+
+Follow the rules defined in [.claude/rules-snippets/documentation.md](../../.claude/rules-snippets/documentation.md).
+
+Key points:
+- Features require `docs/features/{{ISSUE_ID}}-FEATURE-NAME/` with `spec.md` and `plan.md`; fixes go in monthly logs (`docs/fixes/{YYYY-MM}.md`) or complex fix folders.
+- Additional doc categories: `docs/integration/` (cross-system guides), `docs/guides/` (developer onboarding), `docs/constitution.md` (project principles).
+- Documentation is a mandatory pre-commit gate — write or update docs before committing code, include doc changes in the same commit/PR.
+- Use [Keep a Changelog](https://keepachangelog.com/) format for changelogs and monthly fix logs; create ADRs in `docs/architecture/` for significant architectural decisions.

package/src/repo/.github/instructions/environment-tooling.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**/*"
+description: "Environment and tooling configuration rules."
+---
+
+# Environment & Tooling
+
+Follow the rules defined in [.claude/rules-snippets/environment-tooling.md](../../.claude/rules-snippets/environment-tooling.md).
+
+Key points:
+- Tailor commands to the user's OS and shell.
+- Use `{{PACKAGE_MANAGER}}` for package management.
+- {{TOOLING_RULE_1}} and {{TOOLING_RULE_2}}.

package/src/repo/.github/instructions/logging-comments.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "src/**"
+description: "Logging identifiers and code comment conventions."
+---
+
+# Logging & Comments
+
+Follow the rules defined in [.claude/rules-snippets/logging-comments.md](../../.claude/rules-snippets/logging-comments.md).
+
+Key points:
+- Comment complex logic and non-obvious implementations.
+- Use bracketed identifiers for logs: `[ModuleName]: message`.
+- Remove debug logs before committing to main branch.

package/src/repo/.github/instructions/logging.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**/*"
+description: "Logging standards and best practices for {{PROJECT_NAME}}"
+---
+
+# Logging Standards
+
+Follow the rules defined in [.claude/rules-snippets/logging.md](../../.claude/rules-snippets/logging.md).
+
+Key points:
+- Use bracketed structured tags: `[ComponentName] [operationContext]: action | details`; match severity to log levels (error, warn, info, debug).
+- Never log sensitive data (passwords, tokens, PII, credit cards); sanitize before logging and use conditional logging in hot paths.
+- Include full error context (stack traces, request IDs, user IDs) and use correlation IDs for request tracing in production.

package/src/repo/.github/instructions/patterns.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**/*"
+description: "Project-specific coding patterns and shared utilities for {{PROJECT_NAME}}."
+---
+
+# Patterns and Conventions
+
+Follow the rules defined in [.claude/rules-snippets/patterns.md](../../.claude/rules-snippets/patterns.md).
+
+Key points:
+- State modules in `{{STATE_DIR}}` with {{STATE_MANAGEMENT}}; API services in `{{SERVICES_DIR}}`; shared utilities in `{{UTILS_DIR}}`.
+- Components follow {{COMPONENT_PATTERN}} pattern; prefer extending existing utilities over creating duplicates.
+- Follow SRP and reuse-first principle: review `{{COMPOSABLES_PATH}}`, `{{UTILS_PATH}}`, and `{{HELPERS_PATH}}` before implementing new functionality.

package/src/repo/.github/instructions/prisma-migrations.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**/*"
+description: "Database migration and schema management rules."
+---
+
+# Database Migrations
+
+Follow the rules defined in [.claude/rules-snippets/prisma-migrations.md](../../.claude/rules-snippets/prisma-migrations.md).
+
+Key points:
+- {{DATABASE_SYNC_RULE}} — create migrations with descriptive names and apply to development database before committing.
+- Maintain corresponding model definitions for database entities and update affected services after schema changes.
+- Run tests after schema modifications to catch regressions early.

package/src/repo/.github/instructions/project-context.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**/*"
+description: "Project architecture and data flow for {{PROJECT_NAME}}."
+---
+
+# {{PROJECT_NAME}} Architecture
+
+Follow the rules defined in [.claude/rules-snippets/project-context.md](../../.claude/rules-snippets/project-context.md).
+
+Key points:
+- Built with {{FRAMEWORK}} ({{LANGUAGE}}), entry point at {{ENTRY_POINT}}; directory structure includes components, pages, services, stores, and types.
+- {{DATA_FLOW_DESCRIPTION}} — {{AUTH_DESCRIPTION}}.
+- {{API_INTEGRATION_DESCRIPTION}}.

package/src/repo/.github/instructions/server-client-separation.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**/*"
+description: "Server/client boundary enforcement and data fetching patterns."
+---
+
+# Server-Client Separation
+
+Follow the rules defined in [.claude/rules-snippets/server-client-separation.md](../../.claude/rules-snippets/server-client-separation.md).
+
+Key points:
+- Never import server-only code in client components; use API endpoints to expose server functionality to clients.
+- Create shared types for cross-boundary use; use appropriate data fetching patterns for the framework.
+- Mark server-only modules clearly (e.g., `.server.{{LANGUAGE_EXTENSION}}`).

package/src/repo/.github/instructions/subagent-workflow.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**/*"
+description: "Subagent workflow patterns and orchestrator-first approach. Loaded when working with multi-step tasks, feature development, or agent delegation."
+---
+
+# Subagent Workflow
+
+Follow the rules defined in [.claude/rules-snippets/subagent-workflow.md](../../.claude/rules-snippets/subagent-workflow.md).
+
+Key points:
+- Default to orchestrator-first for non-trivial work (2+ of research, planning, implementation, testing, review); use single agent only for focused single-file tasks.
+- Run parallelization analysis before dispatching: build dependency graph, apply independence test, group by domain, and dispatch accordingly.
+- Every implementation must pass Reviewer before proceeding; coordinators should not skip review even for "simple" changes.

package/src/repo/.github/instructions/testing-quality.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**/*"
+description: "Testing standards and quality gates."
+---
+
+# Testing & Quality
+
+Follow the rules defined in [.claude/rules-snippets/testing-quality.md](../../.claude/rules-snippets/testing-quality.md).
+
+Key points:
+- Ensure lint, test, and build pass before committing.
+- Use {{TEST_FRAMEWORK}} for unit/component tests and {{E2E_FRAMEWORK}} for E2E tests.
+- Aim for meaningful test coverage of business logic.

package/src/repo/.github/instructions/testing.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**/*"
+description: "Testing standards and conventions for {{PROJECT_NAME}}."
+---
+
+# Testing Standards
+
+Follow the rules defined in [.claude/rules-snippets/testing.md](../../.claude/rules-snippets/testing.md).
+
+Key points:
+- Run tests with `{{TEST_COMMAND}}`, coverage with `{{TEST_COVERAGE_COMMAND}}`, and E2E with `{{E2E_TEST_COMMAND}}`.
+- Unit tests: `{{TEST_FILE_PATTERN}}`, integration: `{{INTEGRATION_TEST_PATTERN}}`, E2E: `{{E2E_TEST_PATTERN}}`.
+- Minimum coverage {{COVERAGE_THRESHOLD}}; critical paths need integration/E2E coverage; new features require tests before merging.

package/src/repo/.github/instructions/ui-accessibility.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**/*"
+description: "UI accessibility standards and responsive design patterns."
+---
+
+# UI & Accessibility
+
+Follow the rules defined in [.claude/rules-snippets/ui-accessibility.md](../../.claude/rules-snippets/ui-accessibility.md).
+
+Key points:
+- Develop with a mobile-first approach; adhere to WCAG 2.1 AA accessibility standards.
+- Use semantic HTML elements with proper keyboard navigation and focus management.
+- Use loading states during async operations.

package/src/repo/.github/instructions/version-control.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**/*"
+description: "Version control conventions and commit message format."
+---
+
+# Version Control
+
+Follow the rules defined in [.claude/rules-snippets/version-control.md](../../.claude/rules-snippets/version-control.md).
+
+Key points:
+- Use conventional commit format: `<type>(<scope>): <description>` with types: feat, fix, docs, refactor, test, chore, style, perf.
+- Include ticket reference when applicable: `feat(auth): add login flow [{{ISSUE_PREFIX}}-123]`.
+- Follow the PR template for pull requests.

package/src/repo/.github/instructions/what-to-avoid.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**/*"
+description: "Deprecated features and anti-patterns to avoid."
+---
+
+# Anti-Patterns (What to Avoid)
+
+Follow the rules defined in [.claude/rules-snippets/what-to-avoid.md](../../.claude/rules-snippets/what-to-avoid.md).
+
+Key points:
+- No deprecated {{FRAMEWORK}} features, global CSS outside {{STYLING}} configuration, or direct DOM manipulation.
+- No custom solutions for problems solved by core libraries.
+- No mixing server and client code inappropriately; use consistent naming for events and handlers.

package/src/repo/.github/instructions/workflows.instructions.md

@@ -0,0 +1,13 @@
+---
+applyTo: "**/*"
+description: "Developer workflows and environment settings for {{PROJECT_NAME}}."
+---
+
+# Workflows
+
+Follow the rules defined in [.claude/rules-snippets/workflows.md](../../.claude/rules-snippets/workflows.md).
+
+Key points:
+- Dev server: `{{PACKAGE_MANAGER}} run dev` (port {{DEV_PORT}}); build: `{{PACKAGE_MANAGER}} run build`; type check: `{{PACKAGE_MANAGER}} run type-check`.
+- Unit tests: `{{PACKAGE_MANAGER}} run test`; coverage: `{{PACKAGE_MANAGER}} run test:coverage`; E2E: `{{PACKAGE_MANAGER}} run test:e2e`.
+- Lint: `{{PACKAGE_MANAGER}} run lint`; format: `{{PACKAGE_MANAGER}} run format`.

package/src/repo/.github/prompts/assign-tasks.prompt.md

@@ -0,0 +1,14 @@
+---
+description: Create {{ISSUE_TRACKER}} tickets from requirements or task files
+tools: ["read", "search", "edit"]
+argument-hint: "path to requirements or task file"
+---
+
+# Create Tickets from Requirements
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Task assignment and execution
+
+**CRITICAL: READ:** [.claude/prompt-snippets/assign-tasks.md](../../.claude/prompt-snippets/assign-tasks.md)

package/src/repo/.github/prompts/bootstrap-patch.prompt.md

@@ -0,0 +1,16 @@
+---
+description: Patch AI instructions by fetching updates from the toolkit repo and applying new/updated/missing guidance
+tools: ["read", "search", "edit", "terminal"]
+argument-hint: "[--dry-run] [--category <category>]"
+---
+
+# Bootstrap Patch
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Standard patch — incremental changes to existing config |
+| `planner` | Complex patch — cross-cutting changes needing analysis first |
+
+**CRITICAL: READ:** [.claude/prompt-snippets/bootstrap-patch.md](../../.claude/prompt-snippets/bootstrap-patch.md).

package/src/repo/.github/prompts/bootstrap-upgrade.prompt.md

@@ -0,0 +1,15 @@
+---
+description: Upgrade AI instructions from pre-3.0 inline pattern to 3.0+ snippet architecture
+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 |
+
+**CRITICAL: READ:** [.claude/prompt-snippets/bootstrap-upgrade.md](../../.claude/prompt-snippets/bootstrap-upgrade.md).

package/src/repo/.github/prompts/bootstrap.prompt.md

@@ -0,0 +1,16 @@
+---
+description: Bootstrap AI instructions by analyzing project and customizing templates
+tools: ["read", "search", "edit", "terminal"]
+argument-hint: "no arguments required"
+---
+
+# Bootstrap 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 |
+
+**CRITICAL: READ:** [.claude/prompt-snippets/bootstrap.md](../../.claude/prompt-snippets/bootstrap.md).

package/src/repo/.github/prompts/commit-push.prompt.md

@@ -0,0 +1,14 @@
+---
+description: Commit and push changes with conventional commit messages
+tools: ["read", "search", "terminal"]
+argument-hint: "no arguments required"
+---
+
+# Commit and Push Changes
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Git operations, execution-focused
+
+**CRITICAL: READ:** [.claude/prompt-snippets/commit-push.md](../../.claude/prompt-snippets/commit-push.md).

package/src/repo/.github/prompts/constitution.prompt.md

@@ -0,0 +1,16 @@
+---
+description: Create or update the project constitution
+tools: ["read", "search", "edit"]
+argument-hint: "no arguments required"
+---
+
+# Create or Update Project Constitution
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `oracle` | Project principles and governance — architectural decisions |
+| `planner` | Project conventions and standards — team norms and practices |
+
+**CRITICAL: READ:** [.claude/prompt-snippets/constitution.md](../../.claude/prompt-snippets/constitution.md).

package/src/repo/.github/prompts/create-skill.prompt.md

@@ -0,0 +1,16 @@
+---
+description: Create a new agent skill following VS Code and agentskills.io specifications
+tools: ["read", "search", "edit"]
+tags: [skill-creation, agent-skills, documentation, automation]
+version: 1.0.0
+argument-hint: "skill purpose or description"
+---
+
+# Agent Skill Creation Wizard
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Skill file creation
+
+**CRITICAL: READ:** [.claude/prompt-snippets/create-skill.md](../../.claude/prompt-snippets/create-skill.md).

package/src/repo/.github/prompts/implement-feature.prompt.md

@@ -0,0 +1,16 @@
+---
+description: Implement a feature by completing tasks sequentially
+tools: ["read", "search", "edit", "terminal"]
+argument-hint: "issue key or task file path"
+---
+
+# 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 |
+
+**CRITICAL: READ:** [.claude/prompt-snippets/implement-feature.md](../../.claude/prompt-snippets/implement-feature.md).

package/src/repo/.github/prompts/implement-fixes.prompt.md

@@ -0,0 +1,16 @@
+---
+description: Implement bug fixes with proper tracking and validation
+tools: ["read", "search", "edit", "terminal"]
+argument-hint: "issue key or fix description"
+---
+
+# 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 |
+
+**CRITICAL: READ:** [.claude/prompt-snippets/implement-fixes.md](../../.claude/prompt-snippets/implement-fixes.md).

package/src/repo/.github/prompts/implement.prompt.md

@@ -0,0 +1,16 @@
+---
+description: Implement features based on a task list or specification
+tools: ["read", "search", "edit", "runInTerminal", "terminalLastCommand"]
+argument-hint: "task list or specification"
+---
+
+# Implement Features
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `fixer` | Bounded implementation — clear spec, known target |
+| `oracle` | Ambiguous implementation — needs architectural judgment first |
+
+**CRITICAL: READ:** [.claude/prompt-snippets/implement.md](../../.claude/prompt-snippets/implement.md).

package/src/repo/.github/prompts/plan.prompt.md

@@ -0,0 +1,16 @@
+---
+description: Create an implementation plan for a feature
+tools: ["read", "search"]
+argument-hint: "issue key or spec file path"
+---
+
+# Plan Feature Implementation
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `planner` | Standard implementation plan — breaking work into tasks |
+| `oracle` | Architectural planning — trade-offs, system design, risk analysis |
+
+**CRITICAL: READ:** [.claude/prompt-snippets/plan.md](../../.claude/prompt-snippets/plan.md).

package/src/repo/.github/prompts/playwright-test.prompt.md

@@ -0,0 +1,14 @@
+---
+description: Run or create E2E tests using Playwright
+tools: ["read", "search", "edit", "terminal"]
+argument-hint: "test scenario description or test file path"
+---
+
+# Playwright E2E Testing
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Test generation and execution
+
+**CRITICAL: READ:** [.claude/prompt-snippets/playwright-test.md](../../.claude/prompt-snippets/playwright-test.md).

package/src/repo/.github/prompts/ponytail-audit.prompt.md

@@ -0,0 +1,13 @@
+---
+description: Audit the whole repo for over-engineering, what can be deleted
+argument-hint: "no arguments required"
+---
+
+# Ponytail Audit
+
+## Agent Dispatch
+
+> **Recommended agent:** `oracle`
+> Whole-repo over-engineering analysis
+
+**CRITICAL: READ:** [.claude/prompt-snippets/ponytail-audit.md](../../.claude/prompt-snippets/ponytail-audit.md).

package/src/repo/.github/prompts/ponytail-debt.prompt.md

@@ -0,0 +1,13 @@
+---
+description: "Harvest 'ponytail' comments into a tracked debt ledger"
+argument-hint: "no arguments required"
+---
+
+# Ponytail Debt
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Debt ledger harvesting
+
+**CRITICAL: READ:** [.claude/prompt-snippets/ponytail-debt.md](../../.claude/prompt-snippets/ponytail-debt.md).

package/src/repo/.github/prompts/ponytail-gain.prompt.md

@@ -0,0 +1,13 @@
+---
+description: Show ponytail's measured impact scoreboard (less code, cost, time)
+argument-hint: "no arguments required"
+---
+
+# Ponytail Gain
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Impact scoreboard display
+
+**CRITICAL: READ:** [.claude/prompt-snippets/ponytail-gain.md](../../.claude/prompt-snippets/ponytail-gain.md).

package/src/repo/.github/prompts/ponytail-help.prompt.md

@@ -0,0 +1,13 @@
+---
+description: Quick reference for ponytail levels, skills, and commands
+argument-hint: "no arguments required"
+---
+
+# Ponytail Help
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Quick-reference display
+
+**CRITICAL: READ:** [.claude/prompt-snippets/ponytail-help.md](../../.claude/prompt-snippets/ponytail-help.md).

package/src/repo/.github/prompts/ponytail-review.prompt.md

@@ -0,0 +1,13 @@
+---
+description: Review changes for over-engineering, what can be deleted
+argument-hint: "no arguments required"
+---
+
+# Ponytail Review
+
+## Agent Dispatch
+
+> **Recommended agent:** `oracle`
+> Diff-level over-engineering review
+
+**CRITICAL: READ:** [.claude/prompt-snippets/ponytail-review.md](../../.claude/prompt-snippets/ponytail-review.md).

package/src/repo/.github/prompts/ponytail.prompt.md

@@ -0,0 +1,13 @@
+---
+description: Switch ponytail intensity level (lite/full/ultra/off)
+argument-hint: "ponytail level (lite/full/ultra/off)"
+---
+
+# Ponytail
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Apply YAGNI/stdlib discipline
+
+**CRITICAL: READ:** [.claude/prompt-snippets/ponytail.md](../../.claude/prompt-snippets/ponytail.md).

package/src/repo/.github/prompts/release-notes.prompt.md

@@ -0,0 +1,14 @@
+---
+description: Generate release notes from git commits (web, git tag, or documentation)
+tools: ["read", "search", "edit"]
+argument-hint: "format: web, tag, or docs"
+---
+
+# Generate Release Notes
+
+## Agent Dispatch
+
+> **Recommended agent:** `fixer`
+> Release notes generation
+
+**CRITICAL: READ:** [.claude/prompt-snippets/release-notes.md](../../.claude/prompt-snippets/release-notes.md).

package/src/repo/.github/prompts/review-pr.prompt.md

@@ -0,0 +1,16 @@
+---
+description: Conduct comprehensive pull request code review
+tools: ["read", "search", "edit", "terminal"]
+argument-hint: "PR number or URL"
+---
+
+# 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 |
+
+**CRITICAL: READ:** [.claude/prompt-snippets/review-pr.md](../../.claude/prompt-snippets/review-pr.md).

package/src/repo/.github/prompts/review-staged.prompt.md

@@ -0,0 +1,16 @@
+---
+description: Review staged files with detailed code review
+tools: ["read", "search"]
+argument-hint: "no arguments required"
+---
+
+# Review Staged Files
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `reviewer` | Standard staged review — correctness, style, patterns |
+| `oracle` | Complex staged review — architecture, security, cross-system impact |
+
+**CRITICAL: READ:** [.claude/prompt-snippets/review-staged.md](../../.claude/prompt-snippets/review-staged.md).

package/src/repo/.github/prompts/review.prompt.md

@@ -0,0 +1,16 @@
+---
+description: Conduct code review for files or features
+tools: ["read", "search"]
+argument-hint: "file path or feature name"
+---
+
+# Code Review
+
+## Agent Dispatch
+
+| Agent | When to use |
+|-------|-------------|
+| `reviewer` | Standard code review — correctness, style, patterns |
+| `oracle` | Complex architectural review — trade-offs, security, scalability |
+
+**CRITICAL: READ:** [.claude/prompt-snippets/review.md](../../.claude/prompt-snippets/review.md).

package/src/repo/.github/prompts/specify.prompt.md

@@ -0,0 +1,16 @@
+---
+description: Create a feature specification from a description
+tools: ["read", "search"]
+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 |
+
+**CRITICAL: READ:** [.claude/prompt-snippets/specify.md](../../.claude/prompt-snippets/specify.md).

package/src/repo/.github/prompts/tasks.prompt.md

@@ -0,0 +1,14 @@
+---
+description: Break down a plan into executable tasks
+tools: ["read", "search"]
+argument-hint: "issue key or plan file path"
+---
+
+# Generate Task Breakdown
+
+## Agent Dispatch
+
+> **Recommended agent:** `planner`
+> Task breakdown and management
+
+**CRITICAL: READ:** [.claude/prompt-snippets/tasks.md](../../.claude/prompt-snippets/tasks.md).