oh-my-claude-sisyphus 3.1.0 → 3.2.0

package/docs/FULL-README.md

@@ -10,7 +10,7 @@
 
 # oh-my-claudecode
 
-[![Version](https://img.shields.io/badge/version-3.0.11-ff6b6b)](https://github.com/Yeachan-Heo/oh-my-claudecode)
+[![Version](https://img.shields.io/badge/version-3.2.0-ff6b6b)](https://github.com/Yeachan-Heo/oh-my-claudecode)
 [![npm version](https://img.shields.io/npm/v/oh-my-claudecode?color=cb3837)](https://www.npmjs.com/package/oh-my-claudecode)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Node.js](https://img.shields.io/badge/Node.js-20+-339933?logo=node.js&logoColor=white)](https://nodejs.org/)
@@ -76,6 +76,73 @@ See [CHANGELOG.md](CHANGELOG.md) for full details.
 
 ---
 
+## NEW in 3.1: oh-my-opencode Integration
+
+The following features were integrated from oh-my-opencode to enhance orchestration capabilities:
+
+### Notepad Wisdom System
+
+Plan-scoped wisdom capture for persistent learnings, decisions, issues, and problems. Stores wisdom in `.omc/notepads/{plan-name}/` with timestamped entries.
+
+**Functions:** `initPlanNotepad()`, `addLearning()`, `addDecision()`, `addIssue()`, `addProblem()`, `getWisdomSummary()`
+
+**Benefits:**
+- Separates learnings by plan for better organization
+- Automatic timestamp tracking for temporal context
+- Structured wisdom capture (learning vs decision vs issue vs problem)
+- Persistent storage survives session resets
+
+### Delegation Categories
+
+Semantic task categorization that auto-maps to model tier, temperature, and thinking budget.
+
+**Categories:**
+- `visual-engineering` - UI/visual reasoning, frontend work, design systems (Opus, extended thinking)
+- `ultrabrain` - Deep reasoning tasks (Opus, maximum thinking)
+- `artistry` - Creative writing, novel approaches, innovative solutions (Sonnet, high temperature 0.9)
+- `quick` - Simple lookups (Haiku, no thinking)
+- `writing` - Documentation and content (Haiku, standard temperature)
+
+**Benefits:**
+- Automatic optimal model selection
+- Context-aware temperature tuning
+- Efficient thinking budget allocation
+- Semantic task routing without manual configuration
+
+### Directory Diagnostics
+
+Project-level type checking via `lsp_diagnostics_directory` tool with dual strategy (tsc fast, LSP fallback).
+
+**Capabilities:**
+- Scan entire project directory for type errors
+- Automatic TypeScript compiler optimization
+- Fallback to LSP when tsc unavailable
+- Batch processing with progress reporting
+
+**Benefits:**
+- Comprehensive project health checks
+- Performance-optimized with smart strategy selection
+- Deep language server integration for accuracy
+- Works with or without explicit TypeScript setup
+
+### Session Resume
+
+Background agent resumption with context preservation via `resumeSession()`.
+
+**Capabilities:**
+- Automatic session state recovery
+- Context preservation across interruptions
+- Background agent reconnection
+- Graceful degradation on failure
+
+**Benefits:**
+- Uninterrupted workflow during agent crashes
+- Persistent work state across sessions
+- No manual context re-entry needed
+- Seamless continuation of complex tasks
+
+---
+
 ## Quick Install
 
 Choose **ONE** installation method below. Do not mix methods.
@@ -692,6 +759,7 @@ The original oh-my-opencode used multiple AI providers. This project uses Claude
 | **lsp_code_actions** | ✅ Implemented | Get available refactorings |
 | **lsp_code_action_resolve** | ✅ Implemented | Get details of a code action |
 | **lsp_servers** | ✅ Implemented | List available language servers |
+| **lsp_diagnostics_directory** | ✅ Implemented | Project-level type checking (tsc fast path, LSP fallback) |
 
 > **Note:** LSP tools require language servers to be installed (typescript-language-server, pylsp, rust-analyzer, gopls, etc.). Use `lsp_servers` to check installation status.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-claude-sisyphus",
-  "version": "3.1.0",
+  "version": "3.2.0",
   "description": "Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode",
   "type": "module",
   "main": "dist/index.js",

package/skills/autopilot/SKILL.md

@@ -0,0 +1,168 @@
+---
+name: autopilot
+description: Full autonomous execution from idea to working code
+user-invocable: true
+---
+
+# Autopilot Skill
+
+Full autonomous execution from idea to working code.
+
+## Overview
+
+Autopilot is the ultimate hands-off mode. Give it a brief product idea (2-3 lines) and it handles everything:
+
+1. **Understands** your requirements (Analyst)
+2. **Designs** the technical approach (Architect)
+3. **Plans** the implementation (Critic-validated)
+4. **Builds** with parallel agents (Ralph + Ultrawork)
+5. **Tests** until everything passes (UltraQA)
+6. **Validates** quality and security (Multi-architect review)
+
+## Usage
+
+```
+/autopilot <your idea>
+/ap "A CLI tool that tracks daily habits"
+/autopilot Add dark mode to the app
+```
+
+## Magic Keywords
+
+These phrases auto-activate autopilot:
+- "autopilot", "auto pilot", "autonomous"
+- "build me", "create me", "make me"
+- "full auto", "handle it all"
+- "I want a/an..."
+
+## Phases
+
+### Phase 0: Expansion
+
+**Goal:** Turn vague idea into detailed spec
+
+**Agents:**
+- Analyst (Opus) - Extract requirements
+- Architect (Opus) - Technical specification
+
+**Output:** `.omc/autopilot/spec.md`
+
+### Phase 1: Planning
+
+**Goal:** Create implementation plan from spec
+
+**Agents:**
+- Architect (Opus) - Create plan (direct mode, no interview)
+- Critic (Opus) - Validate plan
+
+**Output:** `.omc/plans/autopilot-impl.md`
+
+### Phase 2: Execution
+
+**Goal:** Implement the plan
+
+**Mode:** Ralph + Ultrawork (persistence + parallelism)
+
+**Agents:**
+- Executor-low (Haiku) - Simple tasks
+- Executor (Sonnet) - Standard tasks
+- Executor-high (Opus) - Complex tasks
+
+### Phase 3: QA
+
+**Goal:** All tests pass
+
+**Mode:** UltraQA
+
+**Cycle:**
+1. Build
+2. Lint
+3. Test
+4. Fix failures
+5. Repeat (max 5 cycles)
+
+### Phase 4: Validation
+
+**Goal:** Multi-perspective approval
+
+**Agents (parallel):**
+- Architect - Functional completeness
+- Security-reviewer - Vulnerability check
+- Code-reviewer - Quality review
+
+**Rule:** All must APPROVE or issues get fixed and re-validated.
+
+## Configuration
+
+Optional settings in `.claude/settings.json`:
+
+```json
+{
+  "omc": {
+    "autopilot": {
+      "maxIterations": 10,
+      "maxQaCycles": 5,
+      "maxValidationRounds": 3,
+      "pauseAfterExpansion": false,
+      "pauseAfterPlanning": false,
+      "skipQa": false,
+      "skipValidation": false
+    }
+  }
+}
+```
+
+## Cancellation
+
+```
+/cancel-autopilot
+```
+
+Or say: "stop", "cancel", "abort"
+
+Progress is preserved for resume.
+
+## Resume
+
+If autopilot was cancelled or failed, just run `/autopilot` again to resume from where it stopped.
+
+## Examples
+
+**New Project:**
+```
+/autopilot A REST API for a bookstore inventory with CRUD operations
+```
+
+**Feature Addition:**
+```
+/autopilot Add user authentication with JWT tokens
+```
+
+**Enhancement:**
+```
+/ap Add dark mode support with system preference detection
+```
+
+## Best Practices
+
+1. **Be specific about the domain** - "bookstore" not "store"
+2. **Mention key features** - "with CRUD", "with authentication"
+3. **Specify constraints** - "using TypeScript", "with PostgreSQL"
+4. **Let it run** - Don't interrupt unless truly needed
+
+## Troubleshooting
+
+**Stuck in a phase?**
+- Check TODO list for blocked tasks
+- Review `.omc/autopilot-state.json` for state
+- Cancel and resume if needed
+
+**Validation keeps failing?**
+- Review the specific issues
+- Consider if requirements were too vague
+- Cancel and provide more detail
+
+**QA cycles exhausted?**
+- Same error 3 times = fundamental issue
+- Review the error pattern
+- May need manual intervention

package/skills/cancel-autopilot/SKILL.md

@@ -0,0 +1,53 @@
+---
+name: cancel-autopilot
+description: Cancel active autopilot session
+user-invocable: true
+---
+
+# Cancel Autopilot Skill
+
+Cancel an active autopilot session gracefully.
+
+## What It Does
+
+- Stops the active autopilot workflow
+- Cleans up any active Ralph or UltraQA state
+- Preserves progress for potential resume
+
+## Usage
+
+```
+/cancel-autopilot
+```
+
+Or say: "stop autopilot", "cancel autopilot", "abort autopilot"
+
+## What Gets Cleaned Up
+
+1. **Autopilot state** - Marked as inactive (preserved for resume)
+2. **Ralph state** - Cleared if active
+3. **Ultrawork state** - Cleared if linked to Ralph
+4. **UltraQA state** - Cleared if active
+
+## Progress Preservation
+
+When cancelled, autopilot preserves:
+- Current phase
+- Files created/modified
+- Spec and plan files
+- Validation verdicts
+
+Run `/autopilot` to resume from where you left off.
+
+## Force Clear
+
+To completely clear all state (no resume):
+
+```
+/cancel-autopilot --clear
+```
+
+This removes all autopilot files including:
+- `.omc/autopilot-state.json`
+- `.omc/autopilot/` directory
+- `.omc/plans/autopilot-impl.md`