claude-code-workflow 6.1.0 β 6.1.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +285 -285
- package/ccw/src/commands/tool.js +37 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,285 +1,285 @@
|
|
|
1
|
-
# π Claude Code Workflow (CCW)
|
|
2
|
-
|
|
3
|
-
<div align="center">
|
|
4
|
-
|
|
5
|
-
[](https://www.npmjs.com/package/claude-code-workflow)
|
|
7
|
-
[](LICENSE)
|
|
8
|
-
[]()
|
|
9
|
-
|
|
10
|
-
**Languages:** [English](README.md) | [δΈζ](README_CN.md)
|
|
11
|
-
|
|
12
|
-
</div>
|
|
13
|
-
|
|
14
|
-
---
|
|
15
|
-
|
|
16
|
-
**Claude Code Workflow (CCW)** is a JSON-driven multi-agent development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution. It transforms AI development from simple prompt chaining into a powerful orchestration system.
|
|
17
|
-
|
|
18
|
-
> **π Version 6.
|
|
19
|
-
>
|
|
20
|
-
> **Core Improvements**:
|
|
21
|
-
> -
|
|
22
|
-
> -
|
|
23
|
-
> -
|
|
24
|
-
> - β¨ **
|
|
25
|
-
>
|
|
26
|
-
> See [CHANGELOG.md](CHANGELOG.md) for complete details.
|
|
27
|
-
|
|
28
|
-
> π **New to CCW?** Check out the [**Getting Started Guide**](GETTING_STARTED.md) for a beginner-friendly 5-minute tutorial!
|
|
29
|
-
|
|
30
|
-
---
|
|
31
|
-
|
|
32
|
-
## β¨ Core Concepts
|
|
33
|
-
|
|
34
|
-
CCW is built on a set of core principles that distinguish it from traditional AI development approaches:
|
|
35
|
-
|
|
36
|
-
- **Context-First Architecture**: Eliminates uncertainty during execution through pre-defined context gathering, ensuring agents have the right information *before* implementation.
|
|
37
|
-
- **JSON-First State Management**: Task state is fully stored in `.task/IMPL-*.json` files as the single source of truth, enabling programmatic orchestration without state drift.
|
|
38
|
-
- **Autonomous Multi-Stage Orchestration**: Commands chain-invoke specialized sub-commands and agents to automate complex workflows with zero user intervention.
|
|
39
|
-
- **Multi-Model Strategy**: Leverages the unique strengths of different AI models (e.g., Gemini for analysis, Codex for implementation) for superior results.
|
|
40
|
-
- **Layered Memory System**: A 4-tier documentation system that provides context at the appropriate abstraction level, preventing information overload.
|
|
41
|
-
- **Specialized Role-Based Agents**: A suite of agents (`@code-developer`, `@test-fix-agent`, etc.) that emulate a real software team for diverse tasks.
|
|
42
|
-
|
|
43
|
-
---
|
|
44
|
-
|
|
45
|
-
## βοΈ Installation
|
|
46
|
-
|
|
47
|
-
### **π¦ npm Install (Recommended)**
|
|
48
|
-
|
|
49
|
-
Install globally via npm:
|
|
50
|
-
```bash
|
|
51
|
-
npm install -g claude-code-workflow
|
|
52
|
-
```
|
|
53
|
-
|
|
54
|
-
Then install workflow files to your system:
|
|
55
|
-
```bash
|
|
56
|
-
# Interactive installation
|
|
57
|
-
ccw install
|
|
58
|
-
|
|
59
|
-
# Global installation (to ~/.claude)
|
|
60
|
-
ccw install -m Global
|
|
61
|
-
|
|
62
|
-
# Project-specific installation
|
|
63
|
-
ccw install -m Path -p /path/to/project
|
|
64
|
-
```
|
|
65
|
-
|
|
66
|
-
### **π Alternative: One-Click Script Install**
|
|
67
|
-
|
|
68
|
-
**Windows (PowerShell):**
|
|
69
|
-
```powershell
|
|
70
|
-
Invoke-Expression (Invoke-WebRequest -Uri "https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.ps1" -UseBasicParsing).Content
|
|
71
|
-
```
|
|
72
|
-
|
|
73
|
-
**Linux/macOS (Bash/Zsh):**
|
|
74
|
-
```bash
|
|
75
|
-
bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.sh)
|
|
76
|
-
```
|
|
77
|
-
|
|
78
|
-
### **β
Verify Installation**
|
|
79
|
-
After installation, open **Claude Code** and verify that workflow commands are available by running:
|
|
80
|
-
```bash
|
|
81
|
-
/workflow:session:list
|
|
82
|
-
```
|
|
83
|
-
If slash commands (e.g., `/workflow:*`) are recognized, the installation was successful.
|
|
84
|
-
|
|
85
|
-
---
|
|
86
|
-
|
|
87
|
-
## π₯οΈ CCW CLI Tool
|
|
88
|
-
|
|
89
|
-
The `ccw` command provides a powerful CLI for managing your Claude Code Workflow installation:
|
|
90
|
-
|
|
91
|
-
### **Commands**
|
|
92
|
-
|
|
93
|
-
| Command | Description |
|
|
94
|
-
|---------|-------------|
|
|
95
|
-
| `ccw install` | Install workflow files to Global (~/.claude) or specific Path |
|
|
96
|
-
| `ccw upgrade` | Upgrade existing installations to current package version |
|
|
97
|
-
| `ccw uninstall` | Remove workflow files from an installation |
|
|
98
|
-
| `ccw view` | Open the workflow dashboard in browser |
|
|
99
|
-
| `ccw serve` | Start dashboard server without opening browser |
|
|
100
|
-
| `ccw list` | List all managed installations |
|
|
101
|
-
|
|
102
|
-
### **Usage Examples**
|
|
103
|
-
|
|
104
|
-
```bash
|
|
105
|
-
# Install globally
|
|
106
|
-
ccw install -m Global
|
|
107
|
-
|
|
108
|
-
# Install to specific project
|
|
109
|
-
ccw install -m Path -p ./my-project
|
|
110
|
-
|
|
111
|
-
# Open dashboard
|
|
112
|
-
ccw view
|
|
113
|
-
|
|
114
|
-
# Start dashboard server on custom port
|
|
115
|
-
ccw serve -p 8080
|
|
116
|
-
|
|
117
|
-
# Upgrade all installations
|
|
118
|
-
ccw upgrade -a
|
|
119
|
-
|
|
120
|
-
# List installations
|
|
121
|
-
ccw list
|
|
122
|
-
```
|
|
123
|
-
|
|
124
|
-
### **Dashboard Features**
|
|
125
|
-
|
|
126
|
-
The CCW Dashboard (`ccw view`) provides:
|
|
127
|
-
- π **Session Overview**: View all workflow sessions with status and progress
|
|
128
|
-
- π **Task Management**: Track task execution and completion
|
|
129
|
-
- π **Review Sessions**: Manage code review cycles
|
|
130
|
-
- βοΈ **MCP Manager**: Configure and monitor MCP servers
|
|
131
|
-
- πͺ **Hook Manager**: Manage Claude Code hooks
|
|
132
|
-
- π **Project Explorer**: Navigate project structure and artifacts
|
|
133
|
-
|
|
134
|
-
---
|
|
135
|
-
|
|
136
|
-
## π οΈ Command Reference
|
|
137
|
-
|
|
138
|
-
CCW provides a rich set of commands for managing workflows, tasks, and interactions with AI tools. For a complete list and detailed descriptions of all available commands, please refer to the [**COMMAND_REFERENCE.md**](COMMAND_REFERENCE.md) file.
|
|
139
|
-
|
|
140
|
-
For detailed technical specifications of each command, see [**COMMAND_SPEC.md**](COMMAND_SPEC.md).
|
|
141
|
-
|
|
142
|
-
---
|
|
143
|
-
|
|
144
|
-
### π‘ **Need Help? Use the Interactive Command Guide**
|
|
145
|
-
|
|
146
|
-
CCW includes a built-in **Command Guide Skill** to help you discover and use commands effectively:
|
|
147
|
-
|
|
148
|
-
- **`CCW-help`** - Get interactive help and command recommendations
|
|
149
|
-
- **`CCW-issue`** - Report bugs or request features using guided templates
|
|
150
|
-
|
|
151
|
-
The Command Guide provides:
|
|
152
|
-
- π **Smart Command Search** - Find commands by keyword, category, or use case
|
|
153
|
-
- π€ **Next-Step Recommendations** - Get suggestions for what to do after any command
|
|
154
|
-
- π **Detailed Documentation** - View arguments, examples, and best practices
|
|
155
|
-
- π **Beginner Onboarding** - Learn the 14 core commands through guided learning paths
|
|
156
|
-
- π **Issue Reporting** - Generate standardized bug reports and feature requests
|
|
157
|
-
|
|
158
|
-
**Usage Examples**:
|
|
159
|
-
```
|
|
160
|
-
User: "CCW-help"
|
|
161
|
-
β Interactive menu with command search, recommendations, and documentation
|
|
162
|
-
|
|
163
|
-
User: "What should I do after /workflow:plan?"
|
|
164
|
-
β Recommends /workflow:execute, /workflow:action-plan-verify with workflow patterns
|
|
165
|
-
|
|
166
|
-
User: "CCW-issue"
|
|
167
|
-
β Guided template generation for bugs, features, or question inquiries
|
|
168
|
-
```
|
|
169
|
-
|
|
170
|
-
---
|
|
171
|
-
|
|
172
|
-
## π Quick Start
|
|
173
|
-
|
|
174
|
-
The best way to get started is by following the 5-minute tutorial in the [**Getting Started Guide**](GETTING_STARTED.md).
|
|
175
|
-
|
|
176
|
-
Here's a quick example of a common development workflow:
|
|
177
|
-
|
|
178
|
-
### **Option 1: Lite-Plan Workflow** (β‘ Recommended for Quick Tasks)
|
|
179
|
-
|
|
180
|
-
Lightweight interactive workflow with in-memory planning and immediate execution:
|
|
181
|
-
|
|
182
|
-
```bash
|
|
183
|
-
# Basic usage with auto-detection
|
|
184
|
-
/workflow:lite-plan "Add JWT authentication to user login"
|
|
185
|
-
|
|
186
|
-
# Force code exploration
|
|
187
|
-
/workflow:lite-plan -e "Refactor logging module for better performance"
|
|
188
|
-
|
|
189
|
-
# Basic usage
|
|
190
|
-
/workflow:lite-plan "Add unit tests for authentication service"
|
|
191
|
-
```
|
|
192
|
-
|
|
193
|
-
**Interactive Flow**:
|
|
194
|
-
1. **Phase 1**: Automatic task analysis and smart code exploration (if needed)
|
|
195
|
-
2. **Phase 2**: Answer clarification questions (if any)
|
|
196
|
-
3. **Phase 3**: Review generated plan and task breakdown
|
|
197
|
-
4. **Phase 4**: Three-dimensional confirmation:
|
|
198
|
-
- β
Confirm/Modify/Cancel task
|
|
199
|
-
- π§ Choose execution: Agent / Provide Plan Only / CLI (Gemini/Qwen/Codex)
|
|
200
|
-
- π Optional code review: No / Claude / Gemini / Qwen / Codex
|
|
201
|
-
5. **Phase 5**: Watch live execution and task tracking
|
|
202
|
-
|
|
203
|
-
### **Option 2: Lite-Fix Workflow** (π Recommended for Bug Fixes)
|
|
204
|
-
|
|
205
|
-
Intelligent bug diagnosis and fix workflow with adaptive severity assessment:
|
|
206
|
-
|
|
207
|
-
```bash
|
|
208
|
-
# Standard bug fix (auto-adapts based on severity)
|
|
209
|
-
/workflow:lite-fix "User avatar upload fails with 413 error"
|
|
210
|
-
|
|
211
|
-
# Production hotfix mode
|
|
212
|
-
/workflow:lite-fix --hotfix "Payment gateway 5xx errors"
|
|
213
|
-
```
|
|
214
|
-
|
|
215
|
-
**Workflow Features**:
|
|
216
|
-
- **Phase 1**: Intelligent root cause diagnosis with adaptive search
|
|
217
|
-
- **Phase 2**: Automatic impact assessment and risk scoring
|
|
218
|
-
- **Phase 3**: Fix strategy generation based on complexity
|
|
219
|
-
- **Phase 4**: Risk-aware verification planning
|
|
220
|
-
- **Phase 5**: User confirmation with execution selection
|
|
221
|
-
- **Phase 6**: Execution dispatch with complete artifact tracking
|
|
222
|
-
|
|
223
|
-
**Session Artifacts** (saved to `.workflow/.lite-fix/{bug-slug}-{timestamp}/`):
|
|
224
|
-
- `diagnosis.json` - Root cause analysis and reproduction steps
|
|
225
|
-
- `impact.json` - Risk score, severity, and workflow adaptations
|
|
226
|
-
- `fix-plan.json` - Fix strategy and implementation tasks
|
|
227
|
-
- `task.json` - Enhanced Task JSON with complete context
|
|
228
|
-
- `followup.json` - Auto-generated follow-up tasks (hotfix mode only)
|
|
229
|
-
|
|
230
|
-
### **Option 3: Full Workflow** (π Comprehensive Planning)
|
|
231
|
-
|
|
232
|
-
Traditional multi-stage workflow for complex projects:
|
|
233
|
-
|
|
234
|
-
1. **Create Plan** (auto-starts session):
|
|
235
|
-
```bash
|
|
236
|
-
/workflow:plan "Implement JWT-based user login and registration"
|
|
237
|
-
```
|
|
238
|
-
2. **Execute Plan**:
|
|
239
|
-
```bash
|
|
240
|
-
/workflow:execute
|
|
241
|
-
```
|
|
242
|
-
3. **View Status** (optional):
|
|
243
|
-
```bash
|
|
244
|
-
/workflow:status
|
|
245
|
-
```
|
|
246
|
-
|
|
247
|
-
---
|
|
248
|
-
|
|
249
|
-
## π Documentation
|
|
250
|
-
|
|
251
|
-
CCW provides comprehensive documentation to help you get started quickly and master advanced features:
|
|
252
|
-
|
|
253
|
-
### π **Getting Started**
|
|
254
|
-
- [**Getting Started Guide**](GETTING_STARTED.md) - 5-minute quick start tutorial
|
|
255
|
-
- [**Installation Guide**](INSTALL.md) - Detailed installation instructions ([δΈζ](INSTALL_CN.md))
|
|
256
|
-
- [**Workflow Decision Guide**](WORKFLOW_DECISION_GUIDE.md) - π³ Interactive flowchart to choose the right command
|
|
257
|
-
- [**Examples**](EXAMPLES.md) - Real-world use cases and practical examples
|
|
258
|
-
- [**FAQ**](FAQ.md) - Common questions and troubleshooting
|
|
259
|
-
|
|
260
|
-
### ποΈ **Architecture & Design**
|
|
261
|
-
- [**Architecture Overview**](ARCHITECTURE.md) - System design and core components
|
|
262
|
-
- [**Project Introduction**](PROJECT_INTRODUCTION.md) - Detailed project overview
|
|
263
|
-
- [**Workflow Diagrams**](WORKFLOW_DIAGRAMS.md) - Visual workflow representations
|
|
264
|
-
|
|
265
|
-
### π **Command Reference**
|
|
266
|
-
- [**Command Reference**](COMMAND_REFERENCE.md) - Complete list of all commands
|
|
267
|
-
- [**Command Spec**](COMMAND_SPEC.md) - Detailed technical specifications
|
|
268
|
-
- [**Command Flow Standard**](COMMAND_FLOW_STANDARD.md) - Command design patterns
|
|
269
|
-
|
|
270
|
-
### π€ **Contributing**
|
|
271
|
-
- [**Contributing Guide**](CONTRIBUTING.md) - How to contribute to CCW
|
|
272
|
-
- [**Changelog**](CHANGELOG.md) - Version history and release notes
|
|
273
|
-
|
|
274
|
-
---
|
|
275
|
-
|
|
276
|
-
## π€ Contributing & Support
|
|
277
|
-
|
|
278
|
-
- **Repository**: [GitHub - Claude-Code-Workflow](https://github.com/catlog22/Claude-Code-Workflow)
|
|
279
|
-
- **Issues**: Report bugs or request features on [GitHub Issues](https://github.com/catlog22/Claude-Code-Workflow/issues).
|
|
280
|
-
- **Discussions**: Join the [Community Forum](https://github.com/catlog22/Claude-Code-Workflow/discussions).
|
|
281
|
-
- **Contributing**: See [CONTRIBUTING.md](CONTRIBUTING.md) for contribution guidelines.
|
|
282
|
-
|
|
283
|
-
## π License
|
|
284
|
-
|
|
285
|
-
This project is licensed under the **MIT License**. See the [LICENSE](LICENSE) file for details.
|
|
1
|
+
# π Claude Code Workflow (CCW)
|
|
2
|
+
|
|
3
|
+
<div align="center">
|
|
4
|
+
|
|
5
|
+
[](https://github.com/catlog22/Claude-Code-Workflow/releases)
|
|
6
|
+
[](https://www.npmjs.com/package/claude-code-workflow)
|
|
7
|
+
[](LICENSE)
|
|
8
|
+
[]()
|
|
9
|
+
|
|
10
|
+
**Languages:** [English](README.md) | [δΈζ](README_CN.md)
|
|
11
|
+
|
|
12
|
+
</div>
|
|
13
|
+
|
|
14
|
+
---
|
|
15
|
+
|
|
16
|
+
**Claude Code Workflow (CCW)** is a JSON-driven multi-agent development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution. It transforms AI development from simple prompt chaining into a powerful orchestration system.
|
|
17
|
+
|
|
18
|
+
> **π Version 6.1.0: Dashboard Icon Unification & CCW Tool System**
|
|
19
|
+
>
|
|
20
|
+
> **Core Improvements**:
|
|
21
|
+
> - π¨ **Dashboard Icon Unification**: Complete migration to Lucide Icons library across all views
|
|
22
|
+
> - π οΈ **CCW Tool Exec System**: New `ccw tool exec` command for executing tools with JSON parameters
|
|
23
|
+
> - π **Explorer Enhancements**: Async task execution, CLI selector improvements, WebSocket frame handling
|
|
24
|
+
> - β¨ **Smart Server Recognition**: Intelligent workspace switching and MCP multi-source configuration
|
|
25
|
+
>
|
|
26
|
+
> See [CHANGELOG.md](CHANGELOG.md) for complete details.
|
|
27
|
+
|
|
28
|
+
> π **New to CCW?** Check out the [**Getting Started Guide**](GETTING_STARTED.md) for a beginner-friendly 5-minute tutorial!
|
|
29
|
+
|
|
30
|
+
---
|
|
31
|
+
|
|
32
|
+
## β¨ Core Concepts
|
|
33
|
+
|
|
34
|
+
CCW is built on a set of core principles that distinguish it from traditional AI development approaches:
|
|
35
|
+
|
|
36
|
+
- **Context-First Architecture**: Eliminates uncertainty during execution through pre-defined context gathering, ensuring agents have the right information *before* implementation.
|
|
37
|
+
- **JSON-First State Management**: Task state is fully stored in `.task/IMPL-*.json` files as the single source of truth, enabling programmatic orchestration without state drift.
|
|
38
|
+
- **Autonomous Multi-Stage Orchestration**: Commands chain-invoke specialized sub-commands and agents to automate complex workflows with zero user intervention.
|
|
39
|
+
- **Multi-Model Strategy**: Leverages the unique strengths of different AI models (e.g., Gemini for analysis, Codex for implementation) for superior results.
|
|
40
|
+
- **Layered Memory System**: A 4-tier documentation system that provides context at the appropriate abstraction level, preventing information overload.
|
|
41
|
+
- **Specialized Role-Based Agents**: A suite of agents (`@code-developer`, `@test-fix-agent`, etc.) that emulate a real software team for diverse tasks.
|
|
42
|
+
|
|
43
|
+
---
|
|
44
|
+
|
|
45
|
+
## βοΈ Installation
|
|
46
|
+
|
|
47
|
+
### **π¦ npm Install (Recommended)**
|
|
48
|
+
|
|
49
|
+
Install globally via npm:
|
|
50
|
+
```bash
|
|
51
|
+
npm install -g claude-code-workflow
|
|
52
|
+
```
|
|
53
|
+
|
|
54
|
+
Then install workflow files to your system:
|
|
55
|
+
```bash
|
|
56
|
+
# Interactive installation
|
|
57
|
+
ccw install
|
|
58
|
+
|
|
59
|
+
# Global installation (to ~/.claude)
|
|
60
|
+
ccw install -m Global
|
|
61
|
+
|
|
62
|
+
# Project-specific installation
|
|
63
|
+
ccw install -m Path -p /path/to/project
|
|
64
|
+
```
|
|
65
|
+
|
|
66
|
+
### **π Alternative: One-Click Script Install**
|
|
67
|
+
|
|
68
|
+
**Windows (PowerShell):**
|
|
69
|
+
```powershell
|
|
70
|
+
Invoke-Expression (Invoke-WebRequest -Uri "https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.ps1" -UseBasicParsing).Content
|
|
71
|
+
```
|
|
72
|
+
|
|
73
|
+
**Linux/macOS (Bash/Zsh):**
|
|
74
|
+
```bash
|
|
75
|
+
bash <(curl -fsSL https://raw.githubusercontent.com/catlog22/Claude-Code-Workflow/main/install-remote.sh)
|
|
76
|
+
```
|
|
77
|
+
|
|
78
|
+
### **β
Verify Installation**
|
|
79
|
+
After installation, open **Claude Code** and verify that workflow commands are available by running:
|
|
80
|
+
```bash
|
|
81
|
+
/workflow:session:list
|
|
82
|
+
```
|
|
83
|
+
If slash commands (e.g., `/workflow:*`) are recognized, the installation was successful.
|
|
84
|
+
|
|
85
|
+
---
|
|
86
|
+
|
|
87
|
+
## π₯οΈ CCW CLI Tool
|
|
88
|
+
|
|
89
|
+
The `ccw` command provides a powerful CLI for managing your Claude Code Workflow installation:
|
|
90
|
+
|
|
91
|
+
### **Commands**
|
|
92
|
+
|
|
93
|
+
| Command | Description |
|
|
94
|
+
|---------|-------------|
|
|
95
|
+
| `ccw install` | Install workflow files to Global (~/.claude) or specific Path |
|
|
96
|
+
| `ccw upgrade` | Upgrade existing installations to current package version |
|
|
97
|
+
| `ccw uninstall` | Remove workflow files from an installation |
|
|
98
|
+
| `ccw view` | Open the workflow dashboard in browser |
|
|
99
|
+
| `ccw serve` | Start dashboard server without opening browser |
|
|
100
|
+
| `ccw list` | List all managed installations |
|
|
101
|
+
|
|
102
|
+
### **Usage Examples**
|
|
103
|
+
|
|
104
|
+
```bash
|
|
105
|
+
# Install globally
|
|
106
|
+
ccw install -m Global
|
|
107
|
+
|
|
108
|
+
# Install to specific project
|
|
109
|
+
ccw install -m Path -p ./my-project
|
|
110
|
+
|
|
111
|
+
# Open dashboard
|
|
112
|
+
ccw view
|
|
113
|
+
|
|
114
|
+
# Start dashboard server on custom port
|
|
115
|
+
ccw serve -p 8080
|
|
116
|
+
|
|
117
|
+
# Upgrade all installations
|
|
118
|
+
ccw upgrade -a
|
|
119
|
+
|
|
120
|
+
# List installations
|
|
121
|
+
ccw list
|
|
122
|
+
```
|
|
123
|
+
|
|
124
|
+
### **Dashboard Features**
|
|
125
|
+
|
|
126
|
+
The CCW Dashboard (`ccw view`) provides:
|
|
127
|
+
- π **Session Overview**: View all workflow sessions with status and progress
|
|
128
|
+
- π **Task Management**: Track task execution and completion
|
|
129
|
+
- π **Review Sessions**: Manage code review cycles
|
|
130
|
+
- βοΈ **MCP Manager**: Configure and monitor MCP servers
|
|
131
|
+
- πͺ **Hook Manager**: Manage Claude Code hooks
|
|
132
|
+
- π **Project Explorer**: Navigate project structure and artifacts
|
|
133
|
+
|
|
134
|
+
---
|
|
135
|
+
|
|
136
|
+
## π οΈ Command Reference
|
|
137
|
+
|
|
138
|
+
CCW provides a rich set of commands for managing workflows, tasks, and interactions with AI tools. For a complete list and detailed descriptions of all available commands, please refer to the [**COMMAND_REFERENCE.md**](COMMAND_REFERENCE.md) file.
|
|
139
|
+
|
|
140
|
+
For detailed technical specifications of each command, see [**COMMAND_SPEC.md**](COMMAND_SPEC.md).
|
|
141
|
+
|
|
142
|
+
---
|
|
143
|
+
|
|
144
|
+
### π‘ **Need Help? Use the Interactive Command Guide**
|
|
145
|
+
|
|
146
|
+
CCW includes a built-in **Command Guide Skill** to help you discover and use commands effectively:
|
|
147
|
+
|
|
148
|
+
- **`CCW-help`** - Get interactive help and command recommendations
|
|
149
|
+
- **`CCW-issue`** - Report bugs or request features using guided templates
|
|
150
|
+
|
|
151
|
+
The Command Guide provides:
|
|
152
|
+
- π **Smart Command Search** - Find commands by keyword, category, or use case
|
|
153
|
+
- π€ **Next-Step Recommendations** - Get suggestions for what to do after any command
|
|
154
|
+
- π **Detailed Documentation** - View arguments, examples, and best practices
|
|
155
|
+
- π **Beginner Onboarding** - Learn the 14 core commands through guided learning paths
|
|
156
|
+
- π **Issue Reporting** - Generate standardized bug reports and feature requests
|
|
157
|
+
|
|
158
|
+
**Usage Examples**:
|
|
159
|
+
```
|
|
160
|
+
User: "CCW-help"
|
|
161
|
+
β Interactive menu with command search, recommendations, and documentation
|
|
162
|
+
|
|
163
|
+
User: "What should I do after /workflow:plan?"
|
|
164
|
+
β Recommends /workflow:execute, /workflow:action-plan-verify with workflow patterns
|
|
165
|
+
|
|
166
|
+
User: "CCW-issue"
|
|
167
|
+
β Guided template generation for bugs, features, or question inquiries
|
|
168
|
+
```
|
|
169
|
+
|
|
170
|
+
---
|
|
171
|
+
|
|
172
|
+
## π Quick Start
|
|
173
|
+
|
|
174
|
+
The best way to get started is by following the 5-minute tutorial in the [**Getting Started Guide**](GETTING_STARTED.md).
|
|
175
|
+
|
|
176
|
+
Here's a quick example of a common development workflow:
|
|
177
|
+
|
|
178
|
+
### **Option 1: Lite-Plan Workflow** (β‘ Recommended for Quick Tasks)
|
|
179
|
+
|
|
180
|
+
Lightweight interactive workflow with in-memory planning and immediate execution:
|
|
181
|
+
|
|
182
|
+
```bash
|
|
183
|
+
# Basic usage with auto-detection
|
|
184
|
+
/workflow:lite-plan "Add JWT authentication to user login"
|
|
185
|
+
|
|
186
|
+
# Force code exploration
|
|
187
|
+
/workflow:lite-plan -e "Refactor logging module for better performance"
|
|
188
|
+
|
|
189
|
+
# Basic usage
|
|
190
|
+
/workflow:lite-plan "Add unit tests for authentication service"
|
|
191
|
+
```
|
|
192
|
+
|
|
193
|
+
**Interactive Flow**:
|
|
194
|
+
1. **Phase 1**: Automatic task analysis and smart code exploration (if needed)
|
|
195
|
+
2. **Phase 2**: Answer clarification questions (if any)
|
|
196
|
+
3. **Phase 3**: Review generated plan and task breakdown
|
|
197
|
+
4. **Phase 4**: Three-dimensional confirmation:
|
|
198
|
+
- β
Confirm/Modify/Cancel task
|
|
199
|
+
- π§ Choose execution: Agent / Provide Plan Only / CLI (Gemini/Qwen/Codex)
|
|
200
|
+
- π Optional code review: No / Claude / Gemini / Qwen / Codex
|
|
201
|
+
5. **Phase 5**: Watch live execution and task tracking
|
|
202
|
+
|
|
203
|
+
### **Option 2: Lite-Fix Workflow** (π Recommended for Bug Fixes)
|
|
204
|
+
|
|
205
|
+
Intelligent bug diagnosis and fix workflow with adaptive severity assessment:
|
|
206
|
+
|
|
207
|
+
```bash
|
|
208
|
+
# Standard bug fix (auto-adapts based on severity)
|
|
209
|
+
/workflow:lite-fix "User avatar upload fails with 413 error"
|
|
210
|
+
|
|
211
|
+
# Production hotfix mode
|
|
212
|
+
/workflow:lite-fix --hotfix "Payment gateway 5xx errors"
|
|
213
|
+
```
|
|
214
|
+
|
|
215
|
+
**Workflow Features**:
|
|
216
|
+
- **Phase 1**: Intelligent root cause diagnosis with adaptive search
|
|
217
|
+
- **Phase 2**: Automatic impact assessment and risk scoring
|
|
218
|
+
- **Phase 3**: Fix strategy generation based on complexity
|
|
219
|
+
- **Phase 4**: Risk-aware verification planning
|
|
220
|
+
- **Phase 5**: User confirmation with execution selection
|
|
221
|
+
- **Phase 6**: Execution dispatch with complete artifact tracking
|
|
222
|
+
|
|
223
|
+
**Session Artifacts** (saved to `.workflow/.lite-fix/{bug-slug}-{timestamp}/`):
|
|
224
|
+
- `diagnosis.json` - Root cause analysis and reproduction steps
|
|
225
|
+
- `impact.json` - Risk score, severity, and workflow adaptations
|
|
226
|
+
- `fix-plan.json` - Fix strategy and implementation tasks
|
|
227
|
+
- `task.json` - Enhanced Task JSON with complete context
|
|
228
|
+
- `followup.json` - Auto-generated follow-up tasks (hotfix mode only)
|
|
229
|
+
|
|
230
|
+
### **Option 3: Full Workflow** (π Comprehensive Planning)
|
|
231
|
+
|
|
232
|
+
Traditional multi-stage workflow for complex projects:
|
|
233
|
+
|
|
234
|
+
1. **Create Plan** (auto-starts session):
|
|
235
|
+
```bash
|
|
236
|
+
/workflow:plan "Implement JWT-based user login and registration"
|
|
237
|
+
```
|
|
238
|
+
2. **Execute Plan**:
|
|
239
|
+
```bash
|
|
240
|
+
/workflow:execute
|
|
241
|
+
```
|
|
242
|
+
3. **View Status** (optional):
|
|
243
|
+
```bash
|
|
244
|
+
/workflow:status
|
|
245
|
+
```
|
|
246
|
+
|
|
247
|
+
---
|
|
248
|
+
|
|
249
|
+
## π Documentation
|
|
250
|
+
|
|
251
|
+
CCW provides comprehensive documentation to help you get started quickly and master advanced features:
|
|
252
|
+
|
|
253
|
+
### π **Getting Started**
|
|
254
|
+
- [**Getting Started Guide**](GETTING_STARTED.md) - 5-minute quick start tutorial
|
|
255
|
+
- [**Installation Guide**](INSTALL.md) - Detailed installation instructions ([δΈζ](INSTALL_CN.md))
|
|
256
|
+
- [**Workflow Decision Guide**](WORKFLOW_DECISION_GUIDE.md) - π³ Interactive flowchart to choose the right command
|
|
257
|
+
- [**Examples**](EXAMPLES.md) - Real-world use cases and practical examples
|
|
258
|
+
- [**FAQ**](FAQ.md) - Common questions and troubleshooting
|
|
259
|
+
|
|
260
|
+
### ποΈ **Architecture & Design**
|
|
261
|
+
- [**Architecture Overview**](ARCHITECTURE.md) - System design and core components
|
|
262
|
+
- [**Project Introduction**](PROJECT_INTRODUCTION.md) - Detailed project overview
|
|
263
|
+
- [**Workflow Diagrams**](WORKFLOW_DIAGRAMS.md) - Visual workflow representations
|
|
264
|
+
|
|
265
|
+
### π **Command Reference**
|
|
266
|
+
- [**Command Reference**](COMMAND_REFERENCE.md) - Complete list of all commands
|
|
267
|
+
- [**Command Spec**](COMMAND_SPEC.md) - Detailed technical specifications
|
|
268
|
+
- [**Command Flow Standard**](COMMAND_FLOW_STANDARD.md) - Command design patterns
|
|
269
|
+
|
|
270
|
+
### π€ **Contributing**
|
|
271
|
+
- [**Contributing Guide**](CONTRIBUTING.md) - How to contribute to CCW
|
|
272
|
+
- [**Changelog**](CHANGELOG.md) - Version history and release notes
|
|
273
|
+
|
|
274
|
+
---
|
|
275
|
+
|
|
276
|
+
## π€ Contributing & Support
|
|
277
|
+
|
|
278
|
+
- **Repository**: [GitHub - Claude-Code-Workflow](https://github.com/catlog22/Claude-Code-Workflow)
|
|
279
|
+
- **Issues**: Report bugs or request features on [GitHub Issues](https://github.com/catlog22/Claude-Code-Workflow/issues).
|
|
280
|
+
- **Discussions**: Join the [Community Forum](https://github.com/catlog22/Claude-Code-Workflow/discussions).
|
|
281
|
+
- **Contributing**: See [CONTRIBUTING.md](CONTRIBUTING.md) for contribution guidelines.
|
|
282
|
+
|
|
283
|
+
## π License
|
|
284
|
+
|
|
285
|
+
This project is licensed under the **MIT License**. See the [LICENSE](LICENSE) file for details.
|
package/ccw/src/commands/tool.js
CHANGED
|
@@ -97,6 +97,42 @@ async function readStdin() {
|
|
|
97
97
|
});
|
|
98
98
|
}
|
|
99
99
|
|
|
100
|
+
/**
|
|
101
|
+
* Smart JSON parser with Windows path handling
|
|
102
|
+
*/
|
|
103
|
+
function parseJsonWithPathFix(jsonString) {
|
|
104
|
+
try {
|
|
105
|
+
// Try normal parse first
|
|
106
|
+
return JSON.parse(jsonString);
|
|
107
|
+
} catch (firstError) {
|
|
108
|
+
// If parsing fails, try to fix Windows paths
|
|
109
|
+
try {
|
|
110
|
+
// Pattern: "path": "X:\..." or "path":"X:\..."
|
|
111
|
+
const fixedJson = jsonString.replace(
|
|
112
|
+
/("(?:path|file|target|source|dest|destination)":\s*")([A-Za-z]:[^"]+)"/g,
|
|
113
|
+
(match, prefix, path) => {
|
|
114
|
+
// Convert backslashes to forward slashes (universal)
|
|
115
|
+
const fixedPath = path.replace(/\\/g, '/');
|
|
116
|
+
return `${prefix}${fixedPath}"`;
|
|
117
|
+
}
|
|
118
|
+
);
|
|
119
|
+
|
|
120
|
+
return JSON.parse(fixedJson);
|
|
121
|
+
} catch (secondError) {
|
|
122
|
+
// If still fails, throw original error with helpful message
|
|
123
|
+
const errorMsg = firstError.message;
|
|
124
|
+
const hint = errorMsg.includes('escaped character') || errorMsg.includes('position')
|
|
125
|
+
? '\n\n' + chalk.yellow('Hint: Windows paths in JSON need forward slashes or double backslashes:') +
|
|
126
|
+
'\n ' + chalk.green('β "D:/Claude_dms3/file.md"') +
|
|
127
|
+
'\n ' + chalk.green('β "D:\\\\Claude_dms3\\\\file.md"') +
|
|
128
|
+
'\n ' + chalk.red('β "D:\\Claude_dms3\\file.md"')
|
|
129
|
+
: '';
|
|
130
|
+
|
|
131
|
+
throw new Error(errorMsg + hint);
|
|
132
|
+
}
|
|
133
|
+
}
|
|
134
|
+
}
|
|
135
|
+
|
|
100
136
|
/**
|
|
101
137
|
* Execute a tool with given parameters
|
|
102
138
|
*/
|
|
@@ -119,7 +155,7 @@ async function execAction(toolName, jsonInput, options) {
|
|
|
119
155
|
|
|
120
156
|
if (jsonInput) {
|
|
121
157
|
try {
|
|
122
|
-
params =
|
|
158
|
+
params = parseJsonWithPathFix(jsonInput);
|
|
123
159
|
} catch (error) {
|
|
124
160
|
console.error(chalk.red(`Invalid JSON: ${error.message}`));
|
|
125
161
|
process.exit(1);
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "claude-code-workflow",
|
|
3
|
-
"version": "6.1.
|
|
3
|
+
"version": "6.1.1",
|
|
4
4
|
"description": "JSON-driven multi-agent development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "ccw/src/index.js",
|