superclaude-kiro 1.0.7 → 1.1.0
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
CHANGED
|
@@ -88,7 +88,7 @@ npx superclaude-kiro uninstall
|
|
|
88
88
|
|
|
89
89
|
All agents are configured with:
|
|
90
90
|
- `"tools": ["*"]` - Access to all tools
|
|
91
|
-
- `"allowedTools": ["*", "@context7", "@
|
|
91
|
+
- `"allowedTools": ["*", "@context7", "@playwright", "@sequential-thinking", "@serena"]` - All built-in and MCP tools pre-approved
|
|
92
92
|
- `"toolsSettings"` - Shell and write operations auto-allowed
|
|
93
93
|
- `"model": "claude-sonnet-4.5"` - Claude Sonnet 4.5
|
|
94
94
|
- `"useLegacyMcpJson": true` - Uses global MCP servers
|
|
@@ -156,6 +156,46 @@ npm version patch
|
|
|
156
156
|
npm publish
|
|
157
157
|
```
|
|
158
158
|
|
|
159
|
+
## MCP Server Setup
|
|
160
|
+
|
|
161
|
+
SuperClaude includes 4 pre-configured MCP servers that work out of the box:
|
|
162
|
+
|
|
163
|
+
| Server | Purpose |
|
|
164
|
+
|--------|---------|
|
|
165
|
+
| `sequential-thinking` | Structured reasoning and problem-solving |
|
|
166
|
+
| `context7` | Library documentation lookup |
|
|
167
|
+
| `playwright` | Browser automation and testing |
|
|
168
|
+
| `serena` | Semantic code analysis and editing |
|
|
169
|
+
|
|
170
|
+
### MorphLLM Fast Apply (Optional - Manual Setup Required)
|
|
171
|
+
|
|
172
|
+
The `morphllm-fast-apply` MCP server provides ultra-fast file editing (10,500+ tokens/sec). **It is NOT included by default** due to Kiro CLI environment variable limitations.
|
|
173
|
+
|
|
174
|
+
To add MorphLLM support:
|
|
175
|
+
|
|
176
|
+
1. **Create a free account** at [morphllm.com](https://www.morphllm.com)
|
|
177
|
+
2. **Get your API key** from [dashboard/api-keys](https://www.morphllm.com/dashboard/api-keys)
|
|
178
|
+
3. **Add to your mcp.json** (`~/.kiro/settings/mcp.json`):
|
|
179
|
+
|
|
180
|
+
```json
|
|
181
|
+
{
|
|
182
|
+
"mcpServers": {
|
|
183
|
+
"morphllm-fast-apply": {
|
|
184
|
+
"command": "npx",
|
|
185
|
+
"args": ["-y", "@morph-llm/morph-fast-apply"],
|
|
186
|
+
"env": {
|
|
187
|
+
"MORPH_API_KEY": "your-actual-api-key-here"
|
|
188
|
+
},
|
|
189
|
+
"autoApprove": ["edit_file"]
|
|
190
|
+
}
|
|
191
|
+
}
|
|
192
|
+
}
|
|
193
|
+
```
|
|
194
|
+
|
|
195
|
+
**Important**: Replace `"your-actual-api-key-here"` with your actual API key. The `${MORPH_API_KEY}` environment variable syntax does not work reliably in Kiro CLI ([known issue](https://github.com/kirodotdev/Kiro/issues/3909)).
|
|
196
|
+
|
|
197
|
+
**Pricing**: Free tier includes 500 requests/month. Paid usage is ~$1/million tokens.
|
|
198
|
+
|
|
159
199
|
## Requirements
|
|
160
200
|
|
|
161
201
|
- Node.js 18+
|
|
@@ -183,6 +223,14 @@ kiro-cli mcp list
|
|
|
183
223
|
cat ~/.kiro/settings/mcp.json
|
|
184
224
|
```
|
|
185
225
|
|
|
226
|
+
### MorphLLM not working
|
|
227
|
+
|
|
228
|
+
MorphLLM requires manual setup. See [MCP Server Setup](#mcp-server-setup) above.
|
|
229
|
+
|
|
230
|
+
**Common issues:**
|
|
231
|
+
- API key must be hardcoded in mcp.json (environment variable expansion doesn't work reliably)
|
|
232
|
+
- Get your API key from [morphllm.com/dashboard/api-keys](https://www.morphllm.com/dashboard/api-keys)
|
|
233
|
+
|
|
186
234
|
### Reinstall from scratch
|
|
187
235
|
|
|
188
236
|
```bash
|
package/dist/agents/sc-pm.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"$schema": "https://raw.githubusercontent.com/aws/amazon-q-developer-cli/refs/heads/main/schemas/agent-v1.json",
|
|
3
3
|
"name": "superclaude",
|
|
4
4
|
"description": "SuperClaude Framework Agent - Comprehensive development orchestration with specialized behaviors, flags, and MCP integrations",
|
|
5
|
-
"prompt": "You are operating with the SuperClaude framework context. You have access to all SuperClaude behaviors.\n\n## How to Use SuperClaude Commands\nThe user can reference any SuperClaude command using #sc-[command] syntax. When they do, load and follow the corresponding steering file.\n\n## Available Commands\n- #sc-analyze: Comprehensive code analysis\n- #sc-brainstorm: Interactive requirements discovery\n- #sc-build: Project building with error handling\n- #sc-cleanup: Code cleanup and optimization\n- #sc-design: System and component design\n- #sc-document: Documentation generation\n- #sc-estimate: Development estimates\n- #sc-explain: Code explanations\n- #sc-git: Git operations\n- #sc-implement: Feature implementation\n- #sc-improve: Code improvements\n- #sc-index: Project documentation generation\n- #sc-pm: Project management orchestration\n- #sc-reflect: Task reflection\n- #sc-research: Deep web research\n- #sc-save / #sc-load: Session management\n- #sc-spawn: Task orchestration\n- #sc-task: Complex task execution\n- #sc-test: Test execution\n- #sc-troubleshoot: Issue diagnosis\n- #sc-workflow: Workflow generation\n- #sc-help: Show all commands and flags\n\n## Behavioral Modes (use as natural language)\n- 'brainstorm mode': Collaborative discovery mindset, ask probing questions\n- 'think deeply' or 'analyze thoroughly': Deeper structured analysis\n- 'delegate this': Break into sub-tasks\n- 'safe mode': Maximum validation before execution\n- 'be token efficient': Reduced context, concise responses\n\n## MCP Tools Available\nYou have access to sequential-thinking, context7, playwright,
|
|
5
|
+
"prompt": "You are operating with the SuperClaude framework context. You have access to all SuperClaude behaviors.\n\n## How to Use SuperClaude Commands\nThe user can reference any SuperClaude command using #sc-[command] syntax. When they do, load and follow the corresponding steering file.\n\n## Available Commands\n- #sc-analyze: Comprehensive code analysis\n- #sc-brainstorm: Interactive requirements discovery\n- #sc-build: Project building with error handling\n- #sc-cleanup: Code cleanup and optimization\n- #sc-design: System and component design\n- #sc-document: Documentation generation\n- #sc-estimate: Development estimates\n- #sc-explain: Code explanations\n- #sc-git: Git operations\n- #sc-implement: Feature implementation\n- #sc-improve: Code improvements\n- #sc-index: Project documentation generation\n- #sc-pm: Project management orchestration\n- #sc-reflect: Task reflection\n- #sc-research: Deep web research\n- #sc-save / #sc-load: Session management\n- #sc-spawn: Task orchestration\n- #sc-task: Complex task execution\n- #sc-test: Test execution\n- #sc-troubleshoot: Issue diagnosis\n- #sc-workflow: Workflow generation\n- #sc-help: Show all commands and flags\n\n## Behavioral Modes (use as natural language)\n- 'brainstorm mode': Collaborative discovery mindset, ask probing questions\n- 'think deeply' or 'analyze thoroughly': Deeper structured analysis\n- 'delegate this': Break into sub-tasks\n- 'safe mode': Maximum validation before execution\n- 'be token efficient': Reduced context, concise responses\n\n## MCP Tools Available\nYou have access to sequential-thinking, context7, playwright, and serena MCP servers for enhanced capabilities.",
|
|
6
6
|
"mcpServers": {},
|
|
7
7
|
"tools": [
|
|
8
8
|
"*"
|
|
@@ -10,7 +10,6 @@
|
|
|
10
10
|
"allowedTools": [
|
|
11
11
|
"*",
|
|
12
12
|
"@context7",
|
|
13
|
-
"@morphllm-fast-apply",
|
|
14
13
|
"@playwright",
|
|
15
14
|
"@sequential-thinking",
|
|
16
15
|
"@serena"
|
|
@@ -95,20 +95,6 @@
|
|
|
95
95
|
"think_about_whether_you_are_done",
|
|
96
96
|
"initial_instructions"
|
|
97
97
|
]
|
|
98
|
-
},
|
|
99
|
-
"morphllm-fast-apply": {
|
|
100
|
-
"type": "stdio",
|
|
101
|
-
"command": "npx",
|
|
102
|
-
"args": [
|
|
103
|
-
"-y",
|
|
104
|
-
"@morph-llm/morph-fast-apply"
|
|
105
|
-
],
|
|
106
|
-
"env": {
|
|
107
|
-
"MORPH_API_KEY": "YOUR_MORPH_API_KEY"
|
|
108
|
-
},
|
|
109
|
-
"autoApprove": [
|
|
110
|
-
"edit_file"
|
|
111
|
-
]
|
|
112
98
|
}
|
|
113
99
|
}
|
|
114
100
|
}
|