clavix 3.0.1 → 3.2.0

package/README.md

@@ -1,5 +1,5 @@
 # Clavix
-> Universal prompt intelligence for AI coding. Transform rough ideas into production-ready prompts with automatic quality optimization—no framework to learn.
+> **Clavix Intelligence™** for AI coding. Transform rough ideas into production-ready prompts with automatic quality optimization—no framework to learn.
 
 ## Table of contents
 - [Why Clavix?](#why-clavix)
@@ -8,6 +8,17 @@
 - [Quickstart](#quickstart)
 - [Full documentation](#full-documentation)
 
+## Release Notes
+
+| Version | Highlights | Details |
+| --- | --- | --- |
+| **v3.1.0** (Latest) | Clavix Intelligence™ brand evolution | [Changelog](CHANGELOG.md#310---2025-11-23) |
+| **v3.0.1** | Enhanced intent detection (95%+ accuracy) | [Changelog](CHANGELOG.md#301---2025-11-22) |
+| **v2.8.0** | Pure ESM package (breaking change) | [Changelog](CHANGELOG.md#280---2025-11-17) |
+| **v2.7.0** | Prompt lifecycle management | [Changelog](CHANGELOG.md#270---2025-11-15) |
+
+**Requirements:** Node.js ≥ 16.0.0 (ESM support required)
+
 ## Why Clavix?
 Better prompts lead to better code. Clavix automatically detects what you're trying to do and applies the right optimization patterns—no framework to learn, no methodology to master. Just describe what you want, and Clavix makes it AI-ready.
 
@@ -20,7 +31,7 @@ Better prompts lead to better code. Clavix automatically detects what you're try
 Learn more in [docs/why-clavix.md](docs/why-clavix.md).
 
 ## How It Works
-Clavix uses **Adaptive Prompt Intelligence™** (v3.0+) to automatically:
+Clavix uses **Clavix Intelligence™** (v3.0+) to automatically:
 - **Detect intent** - 95%+ accuracy with weighted scoring, phrase detection, and context analysis
 - **Assess quality** - Evaluates across 5 dimensions: Clarity, Efficiency, Structure, Completeness, Actionability
 - **Apply patterns** - 6 optimization patterns automatically selected and prioritized for your specific need
@@ -40,8 +51,6 @@ Provider paths and argument placeholders are listed in [docs/providers.md](docs/
 
 ## Quickstart
 
-> **⚠️ v2.8.0 Breaking Change**: Clavix is now a pure ESM package. Requires **Node.js ≥ 16.0.0**. See [CHANGELOG.md](CHANGELOG.md#280---2025-11-17) for migration details.
-
 ### For AI Agents (Recommended)
 
 Most Clavix users work through AI coding assistants:
@@ -62,61 +71,18 @@ clavix init
 /clavix:deep "Build an API for user management"
 /clavix:prd  # Full PRD workflow
 
-# 3. Execute saved prompts (v2.7+)
-/clavix:execute  # Interactive selection of saved prompts
+# 3. Manage saved prompts
+/clavix:execute  # Execute saved prompts
 /clavix:prompts  # Manage prompt lifecycle
 
-# 4. Implement with task tracking (v2.8+)
+# 4. Implement with task tracking
 clavix plan              # Generate tasks from PRD
 clavix implement         # Start implementation workflow
 clavix task-complete <taskId>  # Mark tasks done with auto-commit
-
-# Or via CLI
-clavix execute --latest
-clavix prompts list
-clavix prompts clear --executed
 ```
 
 **Supported agents**: Claude Code, Cursor, Windsurf, and [15+ more providers](docs/providers.md)
 
-### Prompt Lifecycle Management (v2.7+)
-
-Clavix now automatically saves prompts from fast/deep optimization, allowing you to:
-- 💾 **Review** saved prompts before execution
-- ⚡ **Execute** prompts when ready
-- 📊 **Track** prompt lifecycle (NEW → EXECUTED → STALE)
-- 🧹 **Clean up** old prompts with safety checks
-
-**Complete workflow:**
-1. **Optimize**: `/clavix:fast` or `/clavix:deep` → Auto-saved to `.clavix/outputs/prompts/`
-2. **Review**: `/clavix:prompts` or `clavix prompts list` → View all saved prompts with status
-3. **Execute**: `/clavix:execute` or `clavix execute --latest` → Implement when ready
-4. **Cleanup**: `clavix prompts clear --executed` → Remove completed prompts
-
-**Prompt Saving Modes (v2.8.1 clarification):**
-
-**CLI Usage (Auto-Save)**:
-```bash
-clavix fast "prompt"     # Automatically saves to .clavix/outputs/prompts/fast/
-clavix deep "prompt"     # Automatically saves to .clavix/outputs/prompts/deep/
-```
-CLI has direct file system access – saving is automatic.
-
-**Slash Command Usage (Agent Manual Save)**:
-```bash
-/clavix:fast "prompt"    # Agent must follow template saving instructions
-/clavix:deep "prompt"    # Agent must follow template saving instructions
-```
-Slash commands run through AI agent that must use tools per template.
-
-**Why the difference?** CLI runs directly in Node.js with file access, while slash commands require agent execution of Write tool.
-
-**Storage hygiene:**
-- Age warnings: >7 days = OLD, >30 days = STALE
-- Safety confirmations before deletion
-- Smart recommendations for cleanup
-- Keep <20 active prompts recommended
-
 Learn more: [Complete prompt lifecycle documentation](docs/commands/execute.md)
 
 ### Direct CLI Usage (Alternative)
@@ -130,32 +96,24 @@ clavix deep "Build an API for user management"
 clavix prd
 ```
 
-**Note**: CLI usage is primarily for initialization and state management. AI agents handle the workflow orchestration via slash commands.
-
 ## Full documentation
-- Overview & navigation: [docs/index.md](docs/index.md)
+- Overview & navigation: [docs/README.md](docs/README.md)
 - Command reference: [docs/commands/](docs/commands/README.md)
 - Providers: [docs/providers.md](docs/providers.md)
-- Prompt Intelligence: [docs/prompt-intelligence.md](docs/prompt-intelligence.md)
+- Clavix Intelligence: [docs/clavix-intelligence.md](docs/clavix-intelligence.md)
 - Guides: [docs/guides/](docs/guides/workflows.md)
 
 ## Requirements
 
 ### For End Users
-- **Node.js ≥ 16.0.0** (required for ESM support)
+- **Node.js ≥ 16.0.0** (ESM support required)
 - npm or yarn package manager
 
 ### For Contributors
-- **Node.js ≥ 16.0.0** (pure ESM package since v2.8.0)
-- Run tests: `npm test` (uses `--experimental-vm-modules` for Jest with ESM)
+- **Node.js ≥ 16.0.0**
+- Run tests: `npm test`
 - Lint: `npm run lint`
-- Build: `npm run build` (TypeScript ES2020 modules)
-
-**ESM Migration (v2.8.0+):**
-- All source code uses ES modules (`import`/`export`)
-- TypeScript configured with `NodeNext` module resolution
-- All imports require `.js` file extensions
-- See [ESM_MIGRATION_NOTES.md](ESM_MIGRATION_NOTES.md) for details
+- Build: `npm run build`
 
 ## License
 MIT

package/dist/cli/commands/init.js

@@ -103,6 +103,10 @@ export default class Init extends Command {
                             name: 'Kilocode (.kilocode/workflows/)',
                             value: 'kilocode',
                         },
+                        {
+                            name: 'LLXPRT (.llxprt/commands/clavix/)',
+                            value: 'llxprt',
+                        },
                         {
                             name: 'Roocode (.roo/commands/)',
                             value: 'roocode',

package/dist/core/adapters/llxprt-adapter.d.ts

@@ -0,0 +1,27 @@
+import { BaseAdapter } from './base-adapter.js';
+import { CommandTemplate } from '../../types/agent.js';
+/**
+ * LLXPRT adapter
+ * Commands stored as TOML files under .llxprt/commands/clavix by default
+ */
+export declare class LlxprtAdapter extends BaseAdapter {
+    private readonly options;
+    readonly name = "llxprt";
+    readonly displayName = "LLXPRT";
+    readonly fileExtension = ".toml";
+    readonly features: {
+        supportsSubdirectories: boolean;
+        supportsFrontmatter: boolean;
+        argumentPlaceholder: string;
+    };
+    constructor(options?: {
+        useNamespace?: boolean;
+    });
+    get directory(): string;
+    detectProject(): Promise<boolean>;
+    getCommandPath(): string;
+    getTargetFilename(name: string): string;
+    protected formatCommand(template: CommandTemplate): string;
+    private getHomeDir;
+}
+//# sourceMappingURL=llxprt-adapter.d.ts.map

package/dist/core/adapters/llxprt-adapter.js

@@ -0,0 +1,54 @@
+import * as os from 'os';
+import * as path from 'path';
+import { BaseAdapter } from './base-adapter.js';
+import { FileSystem } from '../../utils/file-system.js';
+/**
+ * LLXPRT adapter
+ * Commands stored as TOML files under .llxprt/commands/clavix by default
+ */
+export class LlxprtAdapter extends BaseAdapter {
+    options;
+    name = 'llxprt';
+    displayName = 'LLXPRT';
+    fileExtension = '.toml';
+    features = {
+        supportsSubdirectories: true,
+        supportsFrontmatter: false,
+        argumentPlaceholder: '{{args}}',
+    };
+    constructor(options = {}) {
+        super();
+        this.options = options;
+    }
+    get directory() {
+        const useNamespace = this.options.useNamespace ?? true;
+        return useNamespace ? path.join('.llxprt', 'commands', 'clavix') : path.join('.llxprt', 'commands');
+    }
+    async detectProject() {
+        if (await FileSystem.exists('.llxprt')) {
+            return true;
+        }
+        const homePath = path.join(this.getHomeDir(), '.llxprt');
+        return await FileSystem.exists(homePath);
+    }
+    getCommandPath() {
+        return this.directory;
+    }
+    getTargetFilename(name) {
+        const commandPath = this.getCommandPath();
+        const namespaced = commandPath.endsWith(path.join('commands', 'clavix'));
+        const baseName = namespaced ? name : `clavix-${name}`;
+        return `${baseName}${this.fileExtension}`;
+    }
+    formatCommand(template) {
+        const description = template.description.trim().length > 0
+            ? `description = ${JSON.stringify(template.description)}\n\n`
+            : '';
+        const content = template.content.replace(/\{\{ARGS\}\}/g, '{{args}}');
+        return `${description}prompt = """\n${content}\n"""\n`;
+    }
+    getHomeDir() {
+        return process.env.CLAVIX_HOME_OVERRIDE || os.homedir();
+    }
+}
+//# sourceMappingURL=llxprt-adapter.js.map

package/dist/core/agent-manager.js

@@ -14,6 +14,7 @@ import { GeminiAdapter } from './adapters/gemini-adapter.js';
 import { QwenAdapter } from './adapters/qwen-adapter.js';
 import { CodexAdapter } from './adapters/codex-adapter.js';
 import { AugmentAdapter } from './adapters/augment-adapter.js';
+import { LlxprtAdapter } from './adapters/llxprt-adapter.js';
 /**
  * Agent Manager - handles agent detection and registration
  */
@@ -29,6 +30,7 @@ export class AgentManager {
         this.registerAdapter(new CrushAdapter());
         this.registerAdapter(new WindsurfAdapter());
         this.registerAdapter(new KilocodeAdapter());
+        this.registerAdapter(new LlxprtAdapter());
         this.registerAdapter(new ClineAdapter());
         this.registerAdapter(new RoocodeAdapter());
         this.registerAdapter(new AugmentAdapter());

package/dist/core/intelligence/index.js

@@ -1,4 +1,4 @@
-// Main exports for the universal prompt intelligence system
+// Main exports for the Clavix Intelligence system
 export { UniversalOptimizer } from './universal-optimizer.js';
 export { IntentDetector } from './intent-detector.js';
 export { PatternLibrary } from './pattern-library.js';

package/dist/core/intelligence/types.js

@@ -1,3 +1,3 @@
-// Core types for the universal prompt intelligence system
+// Core types for the Clavix Intelligence system
 export {};
 //# sourceMappingURL=types.js.map

package/dist/core/intelligence/universal-optimizer.d.ts

@@ -8,7 +8,7 @@ export declare class UniversalOptimizer {
     private qualityAssessor;
     constructor(intentDetector?: IntentDetector, patternLibrary?: PatternLibrary, qualityAssessor?: QualityAssessor);
     /**
-     * Optimize a prompt using the universal intelligence system
+     * Optimize a prompt using Clavix Intelligence
      */
     optimize(prompt: string, mode: OptimizationMode): Promise<OptimizationResult>;
     /**

package/dist/core/intelligence/universal-optimizer.js

@@ -11,7 +11,7 @@ export class UniversalOptimizer {
         this.qualityAssessor = qualityAssessor || new QualityAssessor();
     }
     /**
-     * Optimize a prompt using the universal intelligence system
+     * Optimize a prompt using Clavix Intelligence
      */
     async optimize(prompt, mode) {
         const startTime = Date.now();

package/dist/templates/agents/agents.md

@@ -1,4 +1,4 @@
-# Clavix Workflows (Universal)
+# Clavix Workflows
 
 Use these instructions when your agent can only read documentation (no slash-command support).
 

package/dist/templates/agents/copilot-instructions.md

@@ -1,10 +1,10 @@
 # Clavix Workflows for GitHub Copilot
 
-These instructions enhance GitHub Copilot's understanding of the Clavix universal prompt intelligence toolkit and workflow commands available in this project.
+These instructions enhance GitHub Copilot's understanding of Clavix Intelligence™ and workflow commands available in this project.
 
 ## About Clavix
 
-Clavix is a universal prompt intelligence toolkit that helps improve prompts, generate PRDs, and manage implementation workflows. It automatically detects intent and applies quality-based optimization patterns without requiring users to learn any specific framework.
+Clavix provides **Clavix Intelligence™** that helps improve prompts, generate PRDs, and manage implementation workflows. It automatically detects intent and applies quality-based optimization patterns without requiring users to learn any specific framework.
 
 ## Available Commands
 

package/dist/templates/agents/octo.md

@@ -358,7 +358,7 @@ When starting implementation with `clavix implement`:
 
 Your goal is to help users:
 - Create clear, comprehensive PRDs through guided questioning
-- Improve prompts using universal prompt intelligence principles
+- Improve prompts using Clavix Intelligence™ principles
 - Think through requirements systematically
 - Execute implementation plans efficiently
 - Archive completed work properly

package/dist/templates/slash-commands/_canonical/deep.md

@@ -3,13 +3,13 @@ name: "Clavix: Deep"
 description: Comprehensive analysis with alternatives, edge cases, and validation
 ---
 
-# Clavix Deep Mode - Comprehensive Prompt Intelligence
+# Clavix Deep Mode - Clavix Intelligence™
 
-You are helping the user perform comprehensive deep analysis using Clavix's universal prompt intelligence with full exploration features (alternatives, edge cases, validation checklists).
+You are helping the user perform comprehensive deep analysis using Clavix Intelligence™ with full exploration features (alternatives, edge cases, validation checklists).
 
 ## What is Deep Mode?
 
-Deep mode provides **comprehensive prompt intelligence** that goes beyond quick optimization:
+Deep mode provides **Clavix Intelligence™** with comprehensive analysis that goes beyond quick optimization:
 
 **Deep Mode Features:**
 - **Intent Detection**: Identifies what you're trying to achieve

package/dist/templates/slash-commands/_canonical/fast.md

@@ -3,13 +3,13 @@ name: "Clavix: Fast"
 description: Quick prompt improvements with smart quality assessment and triage
 ---
 
-# Clavix Fast Mode - Universal Prompt Intelligence
+# Clavix Fast Mode - Clavix Intelligence™
 
-You are helping the user improve their prompt using Clavix's fast mode, which applies universal prompt intelligence with smart quality assessment and triage.
+You are helping the user improve their prompt using Clavix's fast mode, which applies Clavix Intelligence™ with smart quality assessment and triage.
 
 ## What is Clavix?
 
-Clavix provides **universal prompt intelligence** that automatically detects intent and applies the right optimization patterns. No frameworks to learn—just better prompts, instantly.
+Clavix provides **Clavix Intelligence™** that automatically detects intent and applies the right optimization patterns. No frameworks to learn—just better prompts, instantly.
 
 **Fast Mode Features:**
 - **Intent Detection**: Automatically identifies what you're trying to achieve

package/dist/templates/slash-commands/_canonical/prd.md

@@ -5,7 +5,7 @@ description: Clavix Planning Mode - Transform ideas into structured PRDs through
 
 # Clavix Planning Mode
 
-You are helping the user create a Product Requirements Document (PRD) using Clavix Planning Mode's Socratic questioning approach. **Generated PRDs are automatically validated using universal prompt intelligence** for AI consumption quality.
+You are helping the user create a Product Requirements Document (PRD) using Clavix Planning Mode's Socratic questioning approach. **Generated PRDs are automatically validated using Clavix Intelligence™** for AI consumption quality.
 
 ## What is Clavix Planning Mode?
 

package/dist/templates/slash-commands/_canonical/start.md

@@ -5,7 +5,7 @@ description: Start conversational mode for iterative prompt development
 
 # Clavix Conversational Mode
 
-You are starting a Clavix conversational session for iterative prompt and requirements development. **When complete, use `/clavix:summarize` to extract and optimize requirements** using universal prompt intelligence.
+You are starting a Clavix conversational session for iterative prompt and requirements development. **When complete, use `/clavix:summarize` to extract and optimize requirements** using Clavix Intelligence™.
 
 ## Instructions
 
@@ -67,7 +67,7 @@ You are starting a Clavix conversational session for iterative prompt and requir
 
 After the conversational session, `/clavix:summarize` will:
 - Extract requirements from the conversation
-- Apply universal prompt intelligence optimization
+- Apply Clavix Intelligence™ optimization
 - Analyze intent and assess quality (Clarity, Efficiency, Structure, Completeness, Actionability)
 - Generate both original extraction and optimized version
 - Display quality scores and improvements

package/dist/templates/slash-commands/_canonical/summarize.md

@@ -5,7 +5,7 @@ description: Extract and optimize requirements from conversation
 
 # Clavix Conversation Summarization
 
-You are analyzing the conversation history and extracting optimized requirements. **Extracted prompts are automatically enhanced using universal prompt intelligence** for optimal AI consumption.
+You are analyzing the conversation history and extracting optimized requirements. **Extracted prompts are automatically enhanced using Clavix Intelligence™** for optimal AI consumption.
 
 ## Instructions
 
@@ -72,8 +72,8 @@ You are analyzing the conversation history and extracting optimized requirements
    [Success criteria and any important context]
    ```
 
-3. **Universal Optimization** (automatic with labeled improvements):
-   - After extracting the prompt, analyze using universal prompt intelligence
+3. **Clavix Intelligence™ Optimization** (automatic with labeled improvements):
+   - After extracting the prompt, analyze using Clavix Intelligence™
    - Apply optimizations for Clarity, Efficiency, Structure, Completeness, and Actionability
    - **Label all improvements** with quality dimension tags:
      - **[Efficiency]**: "Removed 12 conversational words, reduced from 45 to 28 words"

package/dist/types/agent.d.ts

@@ -37,5 +37,5 @@ export interface ManagedBlock {
     content: string;
     targetFile: string;
 }
-export type AgentType = 'agents-md' | 'amp' | 'augment' | 'claude-code' | 'cline' | 'codex' | 'codebuddy' | 'copilot-instructions' | 'crush' | 'cursor' | 'custom' | 'droid' | 'gemini' | 'kilocode' | 'octo-md' | 'opencode' | 'qwen' | 'roocode' | 'windsurf';
+export type AgentType = 'agents-md' | 'amp' | 'augment' | 'claude-code' | 'cline' | 'codex' | 'codebuddy' | 'copilot-instructions' | 'crush' | 'cursor' | 'custom' | 'droid' | 'gemini' | 'kilocode' | 'llxprt' | 'octo-md' | 'opencode' | 'qwen' | 'roocode' | 'windsurf';
 //# sourceMappingURL=agent.d.ts.map

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "clavix",
-  "version": "3.0.1",
-  "description": "Universal prompt intelligence for AI coding. Automatically optimizes prompts with intent detection, quality assessment, and adaptive patterns—no framework to learn. Works with Claude Code, Cursor, Windsurf, and 19+ other AI coding tools.",
+  "version": "3.2.0",
+  "description": "Clavix Intelligence™ for AI coding. Automatically optimizes prompts with intent detection, quality assessment, and adaptive patterns—no framework to learn. Works with Claude Code, Cursor, Windsurf, and 19+ other AI coding tools.",
   "type": "module",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",