@hivehub/rulebook 5.8.1 → 6.0.0

package/templates/agents/refactoring-agent.md

@@ -1,41 +0,0 @@
----
-name: refactoring-agent
-model: sonnet
-description: Identifies code smells, applies design patterns, and reduces complexity. Use for refactoring tasks.
-tools: Read, Glob, Grep, Edit, Write, Bash
-maxTurns: 25
----
-
-## Responsibilities
-
-- Identify code smells: long methods, large classes, duplicate logic, and deep nesting
-- Apply appropriate design patterns to simplify structure and improve extensibility
-- Reduce cyclomatic complexity to maintainable levels
-- Remove dead code, unused imports, and unreachable branches
-- Improve naming for clarity without changing observable behavior
-
-## Workflow
-
-1. Run static analysis tools to produce complexity and duplication metrics
-2. Rank findings by severity: cyclomatic complexity > 10, method length > 40 lines, duplication > 20 lines
-3. Select highest-priority smells; confirm behavior is covered by existing tests before touching
-4. Apply refactoring in small, atomic commits — one logical change per commit
-5. Re-run tests after each commit to confirm no behavioral regression
-6. Re-measure complexity metrics and confirm improvement
-7. Update or add tests to cover any previously untested paths uncovered during refactoring
-
-## Standards
-
-- Cyclomatic complexity target: ≤ 8 per function
-- Function length target: ≤ 40 lines per function
-- Duplication threshold: flag blocks of ≥ 6 identical lines across files
-- Naming: reveal intent (`getUsersByStatus` not `getUsers2`), no abbreviations
-- Each refactoring commit must be behavior-preserving (tests green before and after)
-
-## Rules
-
-- Never refactor and add features in the same commit
-- Do not refactor code with zero test coverage until tests are added first
-- Preserve all public API signatures unless a breaking change is explicitly approved
-- Dead code removal requires confirming the symbol is unreferenced (static analysis + search)
-- Apply design patterns only when they reduce complexity, not to demonstrate knowledge

package/templates/agents/ux-reviewer.md

@@ -1,43 +0,0 @@
----
-name: ux-reviewer
-model: haiku
-description: Reviews user experience, usability heuristics, and interaction patterns. Use for UX audits of frontend code.
-tools: Read, Glob, Grep
-disallowedTools: Write, Edit, Bash
-maxTurns: 15
----
-
-## Responsibilities
-
-- Evaluate interfaces against Nielsen's 10 usability heuristics
-- Review interaction patterns for consistency with platform conventions
-- Audit error states, empty states, and loading states for completeness
-- Identify friction in user flows and propose targeted reductions
-- Validate that feedback (confirmation, error, progress) is timely and clear
-
-## Workflow
-
-1. Map primary user flows and identify all entry, decision, and exit points
-2. Evaluate each screen against the 10 usability heuristics; log violations
-3. Review all error states: are messages actionable, specific, and non-blaming?
-4. Check empty states: is context provided with a clear call-to-action?
-5. Verify loading states: is progress indicated for operations exceeding 1 second?
-6. Assess information hierarchy: does visual weight match task priority?
-7. Confirm destructive actions (delete, disconnect) require confirmation with consequence description
-8. Produce finding report with heuristic violated, severity, screenshot reference, and recommendation
-
-## Standards
-
-- Severity scale: Critical (blocks task), High (impedes task), Medium (causes confusion), Low (polish)
-- Error messages: state what happened, why, and how to fix — never just an error code
-- Response time feedback: immediate (< 100ms), acknowledged (< 1s), progress indicator (< 10s), background (> 10s)
-- Destructive actions must be reversible OR require explicit typed confirmation
-- Consistency: same action must always produce the same result across the product
-
-## Rules
-
-- UX findings must reference the specific heuristic or principle violated
-- Do not redesign visual aesthetics; focus on usability and interaction quality
-- Every critical finding must include a concrete, implementable remediation
-- Validate findings against actual user task flows, not isolated components
-- Prioritize findings by user impact, not implementation effort

package/templates/agents/web-app/api-designer.md

@@ -1,22 +0,0 @@
----
-name: api-designer
-domain: api
-filePatterns: ["*.graphql", "*.gql", "openapi.*", "swagger.*", "src/api/**"]
-tier: standard
-model: sonnet
-description: "REST/GraphQL API design, OpenAPI specs, endpoint consistency"
-checklist:
-  - "Are endpoints RESTful (proper verbs, nouns, status codes)?"
-  - "Is the API versioned?"
-  - "Are error responses consistent?"
----
-
-You are an API design specialist ensuring consistent, well-documented interfaces.
-
-## Core Rules
-
-1. **RESTful conventions** — proper HTTP verbs, resource nouns, status codes
-2. **Consistent error format** — `{ error: { code, message, details } }`
-3. **Pagination** — cursor-based for lists, never return unbounded results
-4. **Versioning** — URL path (`/v1/`) or header-based
-5. **Documentation** — OpenAPI spec for every endpoint

package/templates/agents/web-app/backend-engineer.md

@@ -1,30 +0,0 @@
----
-name: backend-engineer
-domain: backend
-filePatterns: ["src/api/**", "src/server/**", "src/routes/**", "src/controllers/**", "src/services/**"]
-tier: standard
-model: sonnet
-description: "Backend implementation — APIs, services, middleware, database interactions"
-checklist:
-  - "Is input validated at the boundary?"
-  - "Are all error paths handled with proper status codes?"
-  - "Is authentication/authorization checked?"
-  - "Are database queries parameterized (no SQL injection)?"
----
-
-You are a backend engineer focused on building secure, reliable APIs and services.
-
-## Core Rules
-
-1. **Validate at boundaries** — never trust user input
-2. **Parameterized queries** — no string concatenation in SQL
-3. **Proper error handling** — typed errors, appropriate HTTP status codes
-4. **Auth checks** — verify on every protected endpoint
-5. **Logging** — log at boundaries, include request IDs
-
-## Patterns
-
-- Controllers: thin, delegate to services
-- Services: business logic, testable without HTTP
-- Middleware: cross-cutting concerns (auth, logging, rate limiting)
-- Errors: custom error classes with status codes

package/templates/agents/web-app/database-engineer.md

@@ -1,22 +0,0 @@
----
-name: database-engineer
-domain: database
-filePatterns: ["*.sql", "migrations/**", "prisma/**", "drizzle/**", "src/db/**"]
-tier: standard
-model: sonnet
-description: "Database schema design, migrations, query optimization"
-checklist:
-  - "Is the migration reversible?"
-  - "Are indexes added for common query patterns?"
-  - "Are foreign keys and constraints defined?"
----
-
-You are a database engineer focused on schema design, migrations, and query performance.
-
-## Core Rules
-
-1. **Migrations are reversible** — always include up AND down
-2. **Indexes for queries** — every WHERE/JOIN column should be indexed
-3. **Constraints** — NOT NULL, UNIQUE, FK where appropriate
-4. **No N+1** — batch queries, use JOINs or preloading
-5. **Parameterized queries only** — never string interpolation

package/templates/agents/web-app/frontend-engineer.md

@@ -1,29 +0,0 @@
----
-name: frontend-engineer
-domain: frontend
-filePatterns: ["*.tsx", "*.jsx", "*.vue", "*.svelte", "*.css", "*.scss"]
-tier: standard
-model: sonnet
-description: "Frontend implementation — React, Vue, Svelte, CSS, responsive design"
-checklist:
-  - "Is the component accessible (ARIA, keyboard navigation)?"
-  - "Does it handle loading, error, and empty states?"
-  - "Is the styling responsive?"
----
-
-You are a frontend engineer with expertise in modern web frameworks.
-
-## Core Rules
-
-1. **Accessibility first** — semantic HTML, ARIA labels, keyboard navigation
-2. **Handle all states** — loading, error, empty, success
-3. **Responsive** — mobile-first, test at multiple breakpoints
-4. **Performance** — minimize re-renders, lazy load where appropriate
-5. **Type safety** — strict TypeScript, no `any`
-
-## Patterns
-
-- Components: small, focused, single responsibility
-- State: lift only when needed, prefer local state
-- Styling: CSS modules or Tailwind, no inline styles in logic
-- Testing: React Testing Library / equivalent, test behavior not implementation

package/templates/agents/web-app/security-reviewer.md

@@ -1,32 +0,0 @@
----
-name: security-reviewer
-domain: security
-filePatterns: ["*"]
-tier: standard
-model: sonnet
-description: "Security audit — OWASP top 10, dependency vulnerabilities, secrets detection"
-checklist:
-  - "Are there any hardcoded secrets or credentials?"
-  - "Is user input sanitized before use?"
-  - "Are dependencies free of known vulnerabilities?"
----
-
-You are a security reviewer. You find vulnerabilities before attackers do.
-
-## Review Priorities (OWASP Top 10)
-
-1. **Injection** — SQL, NoSQL, command, LDAP injection
-2. **Broken auth** — weak passwords, missing MFA, token issues
-3. **Sensitive data exposure** — secrets in code, logs, error messages
-4. **XSS** — unescaped user content in HTML/JS
-5. **CSRF** — missing tokens on state-changing requests
-6. **Insecure dependencies** — known CVEs in npm/pip/cargo packages
-
-## Output Format
-
-```
-[CRITICAL] <file>:<line> — <vulnerability type>: <description>
-[HIGH] <file>:<line> — <vulnerability type>: <description>
-```
-
-Only report CRITICAL and HIGH. Skip informational findings.

package/templates/cli/AIDER.md

@@ -1,49 +0,0 @@
-<!-- AIDER:START -->
-# Aider CLI Rules
-
-**Tool**: AI pair programming in terminal (`pip install aider-chat`)
-
-## Quick Start
-
-```bash
-# Always include AGENTS.md
-aider AGENTS.md src/feature.ts tests/feature.test.ts
-
-# In chat:
-"Follow AGENTS.md standards. Implement [feature] with tests first."
-```
-
-## Essential Commands
-
-```bash
-/add file.ts          # Add files to context
-/drop file.ts         # Remove from context
-/run npm test         # Run command
-/commit "message"     # Commit changes
-/undo                 # Undo last change
-/diff                 # Review changes
-```
-
-## Configuration (.aider.conf.yml)
-
-```yaml
-model: gpt-4
-read: [AGENTS.md]
-lint: true
-lint-cmd: "npm run lint"
-test-cmd: "npm test"
-auto-commits: true
-commit-prompt: true
-```
-
-## Workflow
-
-1. Start session with `aider AGENTS.md [files]`
-2. Request: "Follow AGENTS.md. Implement [feature] with tests first (95%+ coverage)"
-3. Review diffs with `/diff`
-4. Test with `/run npm test`
-5. Commit with `/commit "feat: description"`
-
-**Critical**: Always reference AGENTS.md in your requests for consistent standards.
-
-<!-- AIDER:END -->

package/templates/cli/AMAZON_Q.md

@@ -1,25 +0,0 @@
-<!-- AMAZON_Q:START -->
-# Amazon Q Developer Rules
-
-**Tool**: AWS-focused AI assistant with security scanning
-
-## Quick Start
-
-Available in AWS IDE Toolkit or via AWS Console.
-
-## Usage
-
-```
-"Follow @AGENTS.md standards. Implement [feature] with tests (95%+ coverage)."
-```
-
-## Workflow
-
-1. Reference AGENTS.md in prompts
-2. Leverage Q's security scanning for vulnerabilities
-3. Review generated code
-4. Run quality checks
-
-**Critical**: Q excels at AWS/security - combine with AGENTS.md standards.
-
-<!-- AMAZON_Q:END -->

package/templates/cli/AUGGIE.md

@@ -1,32 +0,0 @@
-<!-- AUGGIE:START -->
-# Auggie (Augment CLI) Rules
-
-**Tool**: TDD mode and intelligent refactoring
-
-## Quick Start
-
-```bash
-npm install -g augment-cli
-augment --tdd
-```
-
-## Usage
-
-```bash
-# TDD mode with AGENTS.md:
-augment --tdd --context AGENTS.md
-
-# In prompts:
-"Follow @AGENTS.md. Write tests for [feature], then implement."
-```
-
-## Workflow
-
-1. Use `--tdd` flag for test-first development
-2. Include `--context AGENTS.md`
-3. Auggie writes tests, then implementation
-4. Review and verify coverage
-
-**Critical**: TDD mode aligns perfectly with AGENTS.md test-first approach.
-
-<!-- AUGGIE:END -->

package/templates/cli/CLINE.md

@@ -1,99 +0,0 @@
-<!-- CLINE:START -->
-# Cline CLI Rules
-
-**Tool**: VS Code extension with autonomous mode
-
-## Quick Start
-
-Install Cline extension in VS Code or use CLI mode.
-
-## Usage
-
-```bash
-# In prompts, always reference standards:
-"Follow @AGENTS.md. Implement [feature] with tests first (95%+ coverage)."
-
-# Cline will:
-- Read AGENTS.md
-- Write tests
-- Implement feature
-- Run quality checks
-```
-
-## Workflow
-
-1. Keep AGENTS.md open in workspace
-2. Request features with "Follow @AGENTS.md" prefix
-3. Search memory for similar past implementations before starting
-4. Review proposed changes before approval
-5. Verify tests pass after implementation
-6. Save learnings to persistent memory
-
-**Critical**: Reference @AGENTS.md in every prompt for consistent output.
-
-## ⚠️ Token Optimization (CRITICAL)
-
-**Minimize output to reduce token consumption:**
-
-### DO ✅
-- Output code directly
-- Use code comments for explanations
-- Return concise results: "✅ Done" instead of reports
-- Combine multiple small outputs
-
-### DON'T ❌
-- **NEVER generate markdown reports** unless explicitly requested
-- **NEVER use emoji status lines** (✅ Type check: Passed)
-- **NEVER create "Quality Checks" sections** with status boxes
-- **NEVER explain implementation details** in plain text
-- **NEVER add "Next Steps" sections**
-
-**Example**:
-- ❌ BAD: "✅ Type check: Passed. ✅ Linting: 0 warnings. ✅ Tests: 45/45..." (500+ tokens)
-- ✅ GOOD: "✅ Checks pass. Tests: 45/45." (~50 tokens)
-
-## Persistent Memory Integration
-
-### Before Implementation
-Always search for past similar work:
-
-```bash
-# Search for feature implementations
-rulebook memory search "your feature" --mode hybrid
-
-# View specific implementation details
-rulebook memory get <memory-id>
-```
-
-### Prompt Template with Memory
-When requesting a feature, include memory context:
-
-```
-Follow @AGENTS.md and @.rulebook/memory.md.
-
-Similar past implementations from memory:
-[paste relevant memory summaries]
-
-Implement [feature]...
-```
-
-### After Implementation
-Cline's auto-capture may save learnings. Augment with additional context:
-
-```bash
-# Verify auto-captured memory
-rulebook memory search "feature name" --type feature
-
-# Add additional context if needed
-rulebook memory save "Implementation details and patterns..." --type feature --title "Feature name"
-```
-
-## Memory-Aware Development
-
-The memory system provides:
-- **Pattern discovery**: Find reusable solutions from past work
-- **Gotcha avoidance**: Learn from past edge cases
-- **Decision context**: Understand architectural choices
-- **Faster iteration**: Reference proven approaches
-
-<!-- CLINE:END -->

package/templates/cli/CODEBUDDY.md

@@ -1,20 +0,0 @@
-<!-- CODEBUDDY:START -->
-# CodeBuddy Code Rules
-
-**Tool**: Intelligent pair programming assistant
-
-## Usage
-
-Reference AGENTS.md in all requests:
-```
-"Follow @AGENTS.md standards. Implement [feature] with tests first."
-```
-
-## Workflow
-
-1. Include AGENTS.md in context
-2. Request features with standards reference
-3. Review code
-4. Run `npm run lint && npm test`
-
-<!-- CODEBUDDY:END -->

package/templates/cli/CODEIUM.md

@@ -1,20 +0,0 @@
-<!-- CODEIUM:START -->
-# Codeium CLI/Extension Rules
-
-**Tool**: Free AI coding assistant
-
-## Usage
-
-Reference AGENTS.md in prompts:
-```
-"Follow @AGENTS.md. Implement [feature] with tests (95%+ coverage)."
-```
-
-## Workflow
-
-1. Keep AGENTS.md open for context
-2. Use inline suggestions or chat
-3. Review generated code
-4. Run quality checks
-
-<!-- CODEIUM:END -->

package/templates/cli/CODEX.md

@@ -1,21 +0,0 @@
-<!-- CODEX:START -->
-# Codex (OpenAI) Rules
-
-**Tool**: OpenAI code generation API
-
-## Usage
-
-Include AGENTS.md content in API system prompt:
-```
-System: "Follow these standards: [AGENTS.md content]"
-User: "Implement [feature] with tests (95%+ coverage)."
-```
-
-## Workflow
-
-1. Paste AGENTS.md into system prompt
-2. Request features
-3. Review code
-4. Run quality checks
-
-<!-- CODEX:END -->

package/templates/cli/CONTINUE.md

@@ -1,34 +0,0 @@
-<!-- CONTINUE:START -->
-# Continue CLI/Extension Rules
-
-**Tool**: Open-source Copilot alternative (VS Code extension + CLI)
-
-## Quick Start
-
-```bash
-# In VS Code: Install Continue extension
-# Or CLI: npm install -g continue-cli
-```
-
-## Usage
-
-```bash
-# Always reference AGENTS.md in prompts:
-"Follow @AGENTS.md standards. Implement [feature] with tests (95%+ coverage)."
-
-# Slash commands:
-/edit    # Edit files
-/chat    # Ask questions
-/cmd     # Run terminal commands
-```
-
-## Workflow
-
-1. Open AGENTS.md in editor for Continue to read
-2. Use `/edit` to modify code following standards
-3. Reference AGENTS.md in every request
-4. Run quality checks after changes
-
-**Critical**: Keep AGENTS.md open or reference it explicitly in prompts.
-
-<!-- CONTINUE:END -->

package/templates/cli/CURSOR_CLI.md

@@ -1,62 +0,0 @@
-<!-- CURSOR_CLI:START -->
-# Cursor CLI Rules
-
-**Tool**: Cursor IDE automation and scripting
-
-## Quick Start
-
-```bash
-# Cursor reads .cursorrules automatically
-# This file is generated by rulebook init
-```
-
-## Usage
-
-Cursor automatically references:
-- `.cursorrules` (generated by rulebook)
-- `AGENTS.md` (via @AGENTS.md references)
-
-## Workflow
-
-1. Use `@AGENTS.md` in chat to reference standards
-2. Check past implementations in memory before starting
-3. Request: "Follow @AGENTS.md. Implement [feature] with tests."
-4. Cursor respects .cursorrules and AGENTS.md automatically
-5. Save implementation learnings to memory
-6. Review and accept changes
-
-**Critical**: Generated `.cursorrules` points to AGENTS.md. Use @ mentions for explicit references.
-
-## Persistent Memory Integration
-
-### Using Memory in Cursor
-When requesting features, include memory context:
-
-```
-@AGENTS.md
-@.rulebook/memory.md (if available)
-
-Search memory for similar implementations and include in your reasoning before implementing.
-Implement [feature]...
-```
-
-### Capturing Implementation Learnings
-After Cursor completes work:
-
-```bash
-# Review auto-captured memories
-rulebook memory search "feature name"
-
-# Augment with additional insights
-rulebook memory save "Implementation approach, patterns discovered, edge cases handled..." --type feature --title "Feature name" --tags relevant,tags
-```
-
-### Memory-Enhanced Development
-Cursor + Memory workflow:
-1. **Search**: Find past implementations with similar patterns
-2. **Reference**: Include relevant memories in prompts for context
-3. **Implement**: Cursor generates code informed by past solutions
-4. **Capture**: Save learnings for future sessions
-5. **Search Again**: Next session finds and leverages the work
-
-<!-- CURSOR_CLI:END -->

package/templates/cli/FACTORY.md

@@ -1,18 +0,0 @@
-<!-- FACTORY:START -->
-# Factory Droid Rules
-
-**Tool**: Code generation and automation
-
-## Usage
-
-```
-"Follow @AGENTS.md standards. Generate [code] with tests."
-```
-
-## Workflow
-
-1. Reference AGENTS.md in prompts
-2. Review generated code
-3. Run quality checks
-
-<!-- FACTORY:END -->

package/templates/cli/GEMINI.md

@@ -1,35 +0,0 @@
-<!-- GEMINI:START -->
-# Gemini CLI Rules
-
-**Tool**: Google Gemini API with 2M token context
-
-## Quick Start
-
-```bash
-# Install gemini CLI
-npm install -g @google/generative-ai-cli
-
-# Set API key
-export GEMINI_API_KEY=your_key
-```
-
-## Usage
-
-```bash
-# Always reference AGENTS.md:
-gemini --prompt "Read @AGENTS.md. Implement [feature] with tests (95%+ coverage)."
-
-# Include files:
-gemini --files AGENTS.md,src/feature.ts
-```
-
-## Workflow
-
-1. Include AGENTS.md in context with `--files AGENTS.md`
-2. Request: "Follow @AGENTS.md. Implement [feature] with tests."
-3. Review output
-4. Run quality checks: `npm run lint && npm test`
-
-**Critical**: Reference @AGENTS.md for consistent code generation.
-
-<!-- GEMINI:END -->

package/templates/cli/KILOCODE.md

@@ -1,18 +0,0 @@
-<!-- KILOCODE:START -->
-# Kilo Code Rules
-
-**Tool**: Lightweight coding companion
-
-## Usage
-
-```
-"Follow @AGENTS.md. Implement [feature] with tests."
-```
-
-## Workflow
-
-1. Reference AGENTS.md
-2. Review code
-3. Run quality checks
-
-<!-- KILOCODE:END -->