agentic-code 0.6.5 → 0.6.7

package/.agents/tasks/task-analysis.md

@@ -100,6 +100,51 @@ Count affected components:
 - Integration complexity
 - Testing requirements
 
+#### File Count Estimation Process [MANDATORY]
+
+Before determining scale, investigate existing code with concrete steps:
+
+1. **Identify entry points**: Find files directly related to the task (e.g., components, API endpoints, handlers)
+2. **Trace dependencies**: Follow imports and callers to discover connected files
+3. **Include test files**: Add related test files to the count
+4. **List explicitly**: Document affected file paths as evidence for scale determination
+
+**Scale determination must cite specific file paths as evidence.**
+
+Example output:
+```
+Affected Files (5 files → Medium scale):
+- src/components/UserProfile.tsx (modify)
+- src/hooks/useUser.ts (modify)
+- src/api/userApi.ts (modify)
+- src/components/__tests__/UserProfile.test.tsx (modify)
+- src/hooks/__tests__/useUser.test.ts (modify)
+```
+
+#### Scale Confidence
+
+Indicate certainty level of scale determination:
+
+- **confirmed**: Scale is certain based on clear requirements and identified files
+- **provisional**: Scale may change depending on user answers to clarifying questions
+
+When provisional, always document **Scope Dependencies** - questions whose answers affect scale.
+
+#### Scope Dependencies
+
+When scale confidence is provisional, explicitly document factors that could change the scale:
+
+```
+Scope Dependencies:
+- Authentication method: Use existing OAuth → Medium (3 files) / New implementation → Large (8 files)
+- Caching requirement: None → Medium / Required → Large (adds Redis integration)
+```
+
+This enables:
+1. User to understand what decisions affect scope
+2. Re-evaluation when requirements are clarified
+3. Transparent reasoning for scale determination
+
 ### Step 4: Execute Rule Selection [BLOCKING CHECKPOINT]
 
 **EXECUTION GATES - System HALTS if any step skipped:**
@@ -245,8 +290,16 @@ Based on scale and complexity:
 [RULE SELECTION CHECKPOINT]
 Task Type: [type]
 Task Scale: [scale]
+Scale Confidence: [confirmed/provisional]
 SESSION_BASELINE_DATE: [stored date from initial setup]
 
+Affected Files:
+- [path/to/file1] (create/modify)
+- [path/to/file2] (create/modify)
+
+Scope Dependencies (if provisional):
+- [Question that affects scale]: If [condition A] → [scale], If [condition B] → [scale]
+
 Path Recommendation:
 - [Direct execution of task definitions] OR
 - [Workflow recommended: agentic-coding.md]

package/README.md

@@ -4,7 +4,7 @@ Your AI (LLM), guided by built-in workflows. Describe what you want, and it foll
 
 [![MIT License](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
 [![AGENTS.md](https://img.shields.io/badge/AGENTS.md-compliant-blue.svg)](https://agents.md)
-[![Version](https://img.shields.io/badge/version-0.6.4-blue.svg)](package.json)
+[![Version](https://img.shields.io/badge/version-0.6.7-blue.svg)](package.json)
 
 ![Demo: Building a Slack bot with Agentic Code](.github/assets/demo.gif)
 
@@ -34,7 +34,7 @@ npx agentic-code my-project && cd my-project
 # Ready to go
 ```
 
-That's it. Works with **any AI tool** - Codex, Cursor, Aider, or anything [AGENTS.md](https://agents.md) compatible.
+That's it. Works with **any AI tool** - Cursor, Codex, Aider, or anything [AGENTS.md](https://agents.md) compatible.
 
 ## Why This Exists
 
@@ -110,6 +110,20 @@ cp -r path/to/agentic-code/.agents .
 
 `.agents/skills/` contains reusable skill files in the [Codex Skills format](https://github.com/openai/codex/blob/main/docs/skills.md). Each skill has a `SKILL.md` with instructions that AI agents can discover and apply.
 
+**Cursor**: Install skills for Cursor Editor:
+
+```bash
+# User scope (all projects)
+npx agentic-code skills --cursor
+# Installs to ~/.cursor/skills/agentic-code/
+
+# Project scope (current project only)
+npx agentic-code skills --cursor --project
+# Installs to ./.cursor/skills/agentic-code/
+```
+
+> Note: Skills feature in Cursor requires Nightly release channel.
+
 **Codex**: Install skills for Codex CLI:
 
 ```bash
@@ -120,16 +134,19 @@ npx agentic-code skills --codex
 # Project scope (current project only)
 npx agentic-code skills --codex --project
 # Installs to ./.codex/skills/agentic-code/
+```
 
-# Custom path
+**Custom path**:
+
+```bash
 npx agentic-code skills --path ./custom/skills
 # Installs to ./custom/skills/agentic-code/
 ```
 
 ## Common Questions
 
-**Q: Can I use this with other AI coding tools besides Codex?**  
-Yes! This framework works with any AGENTS.md-compatible tool like Cursor, Aider, and other LLM-assisted development environments.
+**Q: Can I use this with other AI coding tools?**
+Yes! This framework works with any AGENTS.md-compatible tool like Cursor, Codex, Aider, and other LLM-assisted development environments.
 
 **Q: What programming languages are supported?**
 The framework is language-agnostic and works with any programming language through general development principles. TypeScript-specific rules are available in `skills/*/references/typescript.md`.

package/bin/cli.js

@@ -9,8 +9,8 @@ const args = process.argv.slice(2);
 
 // Subcommand routing
 if (args[0] === 'skills') {
-  // Delegate to install-codex-skills
-  const installSkills = require('./install-codex-skills');
+  // Delegate to install-skills
+  const installSkills = require('./install-skills');
   installSkills.run(args.slice(1));
   process.exit(0);
 }
@@ -24,12 +24,13 @@ if (!projectName) {
 
 Usage:
   npx agentic-code <project-name>       Create a new project
-  npx agentic-code skills [options]     Install skills to Codex CLI
+  npx agentic-code skills [options]     Install skills to Codex/Cursor
 
 Examples:
   npx agentic-code my-project
   npx agentic-code skills --codex
-  npx agentic-code skills --codex --project
+  npx agentic-code skills --cursor
+  npx agentic-code skills --cursor --project
 
 For skills options, run: npx agentic-code skills --help
 `);

package/bin/{install-codex-skills.js → install-skills.js}

@@ -16,8 +16,12 @@ const TARGETS = {
     name: 'agentic-code',
     description: 'OpenAI Codex CLI',
     postInstall: 'Restart Codex to load the skills.\nNote: Enable skills with --enable skills flag or in config.toml'
+  },
+  cursor: {
+    name: 'agentic-code',
+    description: 'Cursor Editor',
+    postInstall: 'Restart Cursor to load the skills.\nNote: Skills feature requires Nightly release channel.'
   }
-  // Future targets can be added here
 };
 
 // Get target directory based on target and scope
@@ -30,6 +34,14 @@ function getTargetDir(targetKey, scope) {
     const codexHome = process.env.CODEX_HOME || path.join(os.homedir(), '.codex');
     return path.join(codexHome, 'skills');
   }
+  if (targetKey === 'cursor') {
+    if (scope === SCOPES.project) {
+      return path.join(process.cwd(), '.cursor', 'skills');
+    }
+    // User scope: respect CURSOR_CONFIG_DIR environment variable
+    const cursorHome = process.env.CURSOR_CONFIG_DIR || path.join(os.homedir(), '.cursor');
+    return path.join(cursorHome, 'skills');
+  }
   return null;
 }
 
@@ -91,18 +103,25 @@ Usage: npx agentic-code skills [options]
 
 Options:
   --codex         Install skills to Codex CLI (default)
+  --cursor        Install skills to Cursor Editor
   --project       Install to project scope instead of user scope
   --path <path>   Install to custom path
   --help          Show this help message
 
 Scopes:
-  user (default)  Install to user directory (~/.codex/skills/ or $CODEX_HOME/skills/)
-  project         Install to current project (./.codex/skills/)
+  user (default)  Install to user directory
+  project         Install to current project
+
+Target directories:
+  Codex:   ~/.codex/skills/ (user) or ./.codex/skills/ (project)
+  Cursor:  ~/.cursor/skills/ (user) or ./.cursor/skills/ (project)
 
 Examples:
   npx agentic-code skills                    # Install to ~/.codex/skills/ (user scope)
   npx agentic-code skills --codex            # Same as above (explicit)
   npx agentic-code skills --codex --project  # Install to ./.codex/skills/ (project scope)
+  npx agentic-code skills --cursor           # Install to ~/.cursor/skills/ (user scope)
+  npx agentic-code skills --cursor --project # Install to ./.cursor/skills/ (project scope)
   npx agentic-code skills --path ./my-skills # Install to ./my-skills/agentic-code
 `);
     process.exit(0);
@@ -112,7 +131,9 @@ Examples:
 
   // Determine target (default: codex)
   let targetKey = customPath ? 'custom' : 'codex';
-  if (args.includes('--codex')) {
+  if (args.includes('--cursor')) {
+    targetKey = customPath ? 'custom' : 'cursor';
+  } else if (args.includes('--codex')) {
     targetKey = customPath ? 'custom' : 'codex';
   }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentic-code",
-  "version": "0.6.5",
+  "version": "0.6.7",
   "description": "Task-oriented context engineering framework for LLM coding agents - AGENTS.md standard compliant",
   "files": [
     "bin/",