oh-my-customcode 0.99.0 → 0.99.1

package/README.md

@@ -13,7 +13,7 @@
 
 **[한국어 문서 (Korean)](./README_ko.md)**
 
-48 agents. 106 skills. 22 rules. One command.
+48 agents. 107 skills. 22 rules. One command.
 
 ```bash
 npm install -g oh-my-customcode && cd your-project && omcustom init
@@ -132,7 +132,7 @@ Each agent declares its tools, model, memory scope, and limitations in YAML fron
 
 ---
 
-### Skills (106)
+### Skills (107)
 
 | Category | Count | Includes |
 |----------|-------|----------|
@@ -272,7 +272,7 @@ your-project/
 ├── CLAUDE.md                   # Entry point
 ├── .claude/
 │   ├── agents/                 # 48 agent definitions
-│   ├── skills/                 # 106 skill modules
+│   ├── skills/                 # 107 skill modules
 │   ├── rules/                  # 22 governance rules (R000-R021)
 │   ├── hooks/                  # 15 lifecycle hook scripts
 │   ├── schemas/                # Tool input validation schemas

package/dist/cli/index.js

@@ -2334,7 +2334,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "0.99.0",
+    version: "0.99.1",
     description: "Batteries-included agent harness for Claude Code",
     type: "module",
     bin: {

package/dist/index.js

@@ -2007,7 +2007,7 @@ var package_default = {
   workspaces: [
     "packages/*"
   ],
-  version: "0.99.0",
+  version: "0.99.1",
   description: "Batteries-included agent harness for Claude Code",
   type: "module",
   bin: {

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "0.99.0",
+  "version": "0.99.1",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/skills/idea/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: idea
+description: Analyze a natural language idea against the project codebase and return structured issue specs
+scope: core
+version: 1.0.0
+user-invocable: true
+argument-hint: "<idea text>"
+---
+
+# /idea — Natural Language Idea Analysis
+
+Analyze a natural language idea against the current project's codebase, assess feasibility, scope, and return structured JSON for issue creation.
+
+## Usage
+
+```
+/idea Add OAuth login with Google and GitHub providers
+/idea 디스코드 봇에 모니터링 대시보드 추가
+```
+
+## Workflow
+
+### Phase 1: Parse Input
+
+Extract the core intent from the natural language input.
+
+### Phase 2: Codebase Analysis
+
+1. `Glob` and `Grep` to understand current project structure
+2. Identify relevant modules, files, and patterns
+3. Check for existing similar functionality or conflicts
+
+### Phase 3: Feasibility Analysis
+
+Analyze using a sonnet agent (always spawn with `mode: "bypassPermissions"`):
+
+- **Scope**: Which modules/files would be affected
+- **Complexity**: XS/S/M/L effort estimate
+- **Dependencies**: What existing code needs to change
+- **Risks**: Potential breaking changes or conflicts
+
+### Phase 4: Output
+
+Return a JSON block with the analysis:
+
+```json
+{
+  "title": "concise feature title",
+  "scope": "affected modules and files",
+  "estimatedIssues": 3,
+  "details": "2-3 sentence feasibility analysis",
+  "issueSpecs": [
+    {
+      "title": "issue title",
+      "body": "issue description with acceptance criteria",
+      "labels": ["enhancement"]
+    }
+  ]
+}
+```
+
+The JSON block MUST be wrapped in triple backtick json fence for parsing.
+
+## Model Selection
+
+| Phase | Model | Rationale |
+|-------|-------|-----------|
+| Phase 1-2 | orchestrator | Simple read/search |
+| Phase 3 | sonnet | Balanced analysis |
+
+## Integration
+
+| Rule | How |
+|------|-----|
+| R009 | Single agent for analysis |
+| R010 | Orchestrator manages phases; analysis delegated to agent with `mode: "bypassPermissions"` |
+
+## Output Format
+
+The output MUST contain a fenced JSON block that can be parsed by the calling system (e.g., builder-factory Discord bot). The JSON structure is the contract — do not change field names.

package/templates/CLAUDE.md

@@ -114,7 +114,7 @@ project/
 +-- CLAUDE.md                    # 진입점
 +-- .claude/
 |   +-- agents/                  # 서브에이전트 정의 (48 파일)
-|   +-- skills/                  # 스킬 (106 디렉토리)
+|   +-- skills/                  # 스킬 (107 디렉토리)
 |   +-- rules/                   # 전역 규칙 (R000-R022)
 |   +-- hooks/                   # 훅 스크립트 (보안, 검증, HUD)
 |   +-- contexts/                # 컨텍스트 파일 (ecomode)

package/templates/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.99.0",
+  "version": "0.99.1",
   "lastUpdated": "2026-04-18T00:00:00.000Z",
   "components": [
     {
@@ -18,7 +18,7 @@
       "name": "skills",
       "path": ".claude/skills",
       "description": "Reusable skill modules (includes slash commands)",
-      "files": 106
+      "files": 107
     },
     {
       "name": "guides",