@claudetools/tools 0.5.0 → 0.5.1

package/dist/templates/claude-md.d.ts

@@ -5,7 +5,7 @@ export declare const PROJECT_SECTION_END = "<!-- CLAUDETOOLS:PROJECT:END -->";
 /**
  * Global CLAUDE.md content - added to ~/.claude/CLAUDE.md
  */
-export declare const GLOBAL_TEMPLATE = "\n<!-- CLAUDETOOLS:START -->\n# ClaudeTools Memory System\n\nYou have access to a persistent memory system via the `claudetools_memory` MCP server. Use it to remember context across sessions.\n\n## Memory Tools\n\n### Searching Memory\n```\nmemory_search(query: \"authentication patterns\")\n```\nSearch for relevant facts, entities, and past context. Use this when:\n- Starting work on a feature to recall past decisions\n- Looking for patterns or conventions used before\n- Finding related code or architectural context\n\n### Storing Facts\n```\nmemory_store_fact(\n  entity1: \"UserService\",\n  relationship: \"USES\",\n  entity2: \"bcrypt\",\n  context: \"Password hashing uses bcrypt with 12 rounds\"\n)\n```\nStore important facts as relationships between entities. Use for:\n- Architectural decisions\n- Code patterns and conventions\n- Dependencies and relationships\n- User preferences learned during conversation\n\n### Context Injection\nContext is automatically injected at the start of each session based on the current project. Check `~/.claudetools/session-context.md` for project-specific context.\n\n## Task Management\n\n### Creating Work Plans with Auto-Dispatch\n```\ntask_plan(\n  goal: \"Add user authentication\",\n  epic_title: \"User Auth System\",\n  tasks: [...]\n)\n```\nBreak down complex work into tracked tasks. **Tasks are automatically set to `ready` status.**\n\nAfter `task_plan` completes, you will receive Task tool invocations to spawn parallel agents.\n**Execute ALL Task tool calls in a SINGLE message** to enable parallel execution.\n\n### Parallel Agent Workflow\n1. User describes work needed\n2. Call `task_plan_draft` to present the plan\n3. User says \"go\" to approve\n4. Call `task_plan` - tasks created in `ready` status\n5. Execute the provided Task tool calls in ONE message\n6. Agents work in parallel, each calling `task_complete` when done\n\n### Manual Task Start (Sequential)\n```\ntask_start(task_id: \"task_xxx\")\n```\nClaim a task before working on it. Use for sequential execution.\n\n### Completing Tasks\n```\ntask_complete(task_id: \"task_xxx\", summary: \"Implemented JWT auth with refresh tokens\")\n```\nMark tasks done with a summary of work completed. **Always call this when a task is finished.**\n\n## Codebase Intelligence\n\n### Finding Code\n```\ncodebase_map()           # Get overview of project structure\ncodebase_find(\"UserService\")  # Find symbols/files\ncodebase_context(\"src/auth.ts\")  # Get file dependencies\n```\n\n### Impact Analysis\n```\nanalyze_impact(function_name: \"validateToken\")\n```\nSee what would be affected by changing a function.\n\n## Best Practices\n\n1. **Search before implementing** - Check memory for existing patterns\n2. **Store decisions** - Save architectural choices as facts\n3. **Use task tracking** - Break complex work into tasks\n4. **Complete tasks** - Always mark tasks done with summaries\n<!-- CLAUDETOOLS:END -->\n";
+export declare const GLOBAL_TEMPLATE = "\n<!-- CLAUDETOOLS:START -->\n# ClaudeTools Memory System\n\nYou have access to a persistent memory system via the `claudetools_memory` MCP server. Use it to remember context across sessions.\n\n## Memory Tools\n\n### Searching Memory\n```\nmemory_search(query: \"authentication patterns\")\n```\nSearch for relevant facts, entities, and past context. Use this when:\n- Starting work on a feature to recall past decisions\n- Looking for patterns or conventions used before\n- Finding related code or architectural context\n\n### Storing Facts\n```\nmemory_store_fact(\n  entity1: \"UserService\",\n  relationship: \"USES\",\n  entity2: \"bcrypt\",\n  context: \"Password hashing uses bcrypt with 12 rounds\"\n)\n```\nStore important facts as relationships between entities. Use for:\n- Architectural decisions\n- Code patterns and conventions\n- Dependencies and relationships\n- User preferences learned during conversation\n\n### Context Injection\nContext is automatically injected at the start of each session based on the current project. Check `~/.claudetools/session-context.md` for project-specific context.\n\n## Task Management\n\n### Creating Work Plans with Auto-Dispatch\n```\ntask_plan(\n  goal: \"Add user authentication\",\n  epic_title: \"User Auth System\",\n  tasks: [...]\n)\n```\nBreak down complex work into tracked tasks. **Tasks are automatically set to `ready` status.**\n\nAfter `task_plan` completes, you will receive Task tool invocations to spawn parallel agents.\n**Execute ALL Task tool calls in a SINGLE message** to enable parallel execution.\n\n### Parallel Agent Workflow\n1. User describes work needed\n2. Call `task_plan_draft` to present the plan\n3. User says \"go\" to approve\n4. Call `task_plan` - tasks created in `ready` status\n5. Execute the provided Task tool calls in ONE message\n6. Agents work in parallel, each calling `task_complete` when done\n\n### Manual Task Start (Sequential)\n```\ntask_start(task_id: \"task_xxx\")\n```\nClaim a task before working on it. Use for sequential execution.\n\n### Completing Tasks\n```\ntask_complete(task_id: \"task_xxx\", summary: \"Implemented JWT auth with refresh tokens\")\n```\nMark tasks done with a summary of work completed. **Always call this when a task is finished.**\n\n## Codebase Intelligence\n\n### Finding Code\n```\ncodebase_map()           # Get overview of project structure\ncodebase_find(\"UserService\")  # Find symbols/files\ncodebase_context(\"src/auth.ts\")  # Get file dependencies\n```\n\n### Impact Analysis\n```\nanalyze_impact(function_name: \"validateToken\")\n```\nSee what would be affected by changing a function.\n\n## CodeDNA: AI Code Generation (95-99% Token Savings)\n\n**CRITICAL: Use CodeDNA for repetitive code generation to save massive tokens.**\n\n### When to Use CodeDNA\n- Creating REST APIs with CRUD operations\n- Generating database models, controllers, routes\n- Building validation middleware\n- Setting up authentication systems\n- Creating test suites\n\n### Available Generators\n```\ncodedna_generate_api(spec, framework, options)\ncodedna_validate_spec(spec)\ncodedna_list_generators()\n```\n\n### Entity DSL Syntax\n```\nEntityName(field:type:constraint, field:type:constraint, ...)\n\nExamples:\nUser(email:string:unique:required, password:string:hashed, age:integer:min(18))\nPost(title:string:required, content:string, author:ref(User))\nProduct(name:string, price:decimal:min(0), stock:integer:default(0))\n```\n\n### Constraints\n- `unique` - Unique constraint\n- `required` - NOT NULL\n- `hashed` - Bcrypt hashing (for passwords)\n- `min(n)` - Minimum value\n- `max(n)` - Maximum value\n- `default(value)` - Default value\n\n### Token Savings Example\n**Traditional approach:**\n- AI writes 1000 lines of code\n- Tokens: ~30,000 (input + output)\n- Cost: ~$0.30\n- Time: 2-3 minutes\n\n**CodeDNA approach:**\n```\ncodedna_generate_api({\n  spec: \"User(email:string:unique, password:string:hashed, role:enum(admin,user))\",\n  framework: \"express\",\n  options: { auth: true, validation: true, tests: true }\n})\n```\n- Tokens: ~200\n- Cost: ~$0.002\n- Time: 5-10 seconds\n- **Savings: 99.3% cost, 90% time**\n\n### Generated Files (Express)\n1. `models/entity.model.ts` - Sequelize ORM model\n2. `controllers/entity.controller.ts` - CRUD controllers\n3. `routes/entity.routes.ts` - Express routes\n4. `validators/entity.validator.ts` - Input validation (optional)\n5. `middleware/auth.middleware.ts` - JWT auth (optional)\n6. `tests/entity.test.ts` - Jest tests (optional)\n\n### Usage Pattern\n1. User asks: \"Create a User API with authentication\"\n2. **YOU MUST** call `codedna_generate_api` instead of writing code\n3. Receive 6 production-ready files\n4. Save 99% tokens and time\n\n**DO NOT write boilerplate code manually when CodeDNA can generate it.**\n\n## Best Practices\n\n1. **Search before implementing** - Check memory for existing patterns\n2. **Store decisions** - Save architectural choices as facts\n3. **Use task tracking** - Break complex work into tasks\n4. **Complete tasks** - Always mark tasks done with summaries\n5. **Use CodeDNA for APIs** - Save 95-99% tokens on boilerplate generation\n<!-- CLAUDETOOLS:END -->\n";
 /**
  * Project-level CLAUDE.md content - added to .claude/CLAUDE.md
  */

package/dist/templates/claude-md.js

@@ -95,12 +95,85 @@ analyze_impact(function_name: "validateToken")
 \`\`\`
 See what would be affected by changing a function.
 
+## CodeDNA: AI Code Generation (95-99% Token Savings)
+
+**CRITICAL: Use CodeDNA for repetitive code generation to save massive tokens.**
+
+### When to Use CodeDNA
+- Creating REST APIs with CRUD operations
+- Generating database models, controllers, routes
+- Building validation middleware
+- Setting up authentication systems
+- Creating test suites
+
+### Available Generators
+\`\`\`
+codedna_generate_api(spec, framework, options)
+codedna_validate_spec(spec)
+codedna_list_generators()
+\`\`\`
+
+### Entity DSL Syntax
+\`\`\`
+EntityName(field:type:constraint, field:type:constraint, ...)
+
+Examples:
+User(email:string:unique:required, password:string:hashed, age:integer:min(18))
+Post(title:string:required, content:string, author:ref(User))
+Product(name:string, price:decimal:min(0), stock:integer:default(0))
+\`\`\`
+
+### Constraints
+- \`unique\` - Unique constraint
+- \`required\` - NOT NULL
+- \`hashed\` - Bcrypt hashing (for passwords)
+- \`min(n)\` - Minimum value
+- \`max(n)\` - Maximum value
+- \`default(value)\` - Default value
+
+### Token Savings Example
+**Traditional approach:**
+- AI writes 1000 lines of code
+- Tokens: ~30,000 (input + output)
+- Cost: ~$0.30
+- Time: 2-3 minutes
+
+**CodeDNA approach:**
+\`\`\`
+codedna_generate_api({
+  spec: "User(email:string:unique, password:string:hashed, role:enum(admin,user))",
+  framework: "express",
+  options: { auth: true, validation: true, tests: true }
+})
+\`\`\`
+- Tokens: ~200
+- Cost: ~$0.002
+- Time: 5-10 seconds
+- **Savings: 99.3% cost, 90% time**
+
+### Generated Files (Express)
+1. \`models/entity.model.ts\` - Sequelize ORM model
+2. \`controllers/entity.controller.ts\` - CRUD controllers
+3. \`routes/entity.routes.ts\` - Express routes
+4. \`validators/entity.validator.ts\` - Input validation (optional)
+5. \`middleware/auth.middleware.ts\` - JWT auth (optional)
+6. \`tests/entity.test.ts\` - Jest tests (optional)
+
+### Usage Pattern
+1. User asks: "Create a User API with authentication"
+2. **YOU MUST** call \`codedna_generate_api\` instead of writing code
+3. Receive 6 production-ready files
+4. Save 99% tokens and time
+
+**DO NOT write boilerplate code manually when CodeDNA can generate it.**
+
 ## Best Practices
 
 1. **Search before implementing** - Check memory for existing patterns
 2. **Store decisions** - Save architectural choices as facts
 3. **Use task tracking** - Break complex work into tasks
 4. **Complete tasks** - Always mark tasks done with summaries
+5. **Use CodeDNA for APIs** - Save 95-99% tokens on boilerplate generation
 ${SECTION_END}
 `;
 /**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@claudetools/tools",
-  "version": "0.5.0",
+  "version": "0.5.1",
   "description": "Persistent AI memory, task management, and codebase intelligence for Claude Code",
   "type": "module",
   "main": "dist/index.js",