superclaude-kiro 1.0.8 → 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
|
|
@@ -158,39 +158,48 @@ npm publish
|
|
|
158
158
|
|
|
159
159
|
## MCP Server Setup
|
|
160
160
|
|
|
161
|
-
SuperClaude includes
|
|
161
|
+
SuperClaude includes 4 pre-configured MCP servers that work out of the box:
|
|
162
162
|
|
|
163
|
-
|
|
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 |
|
|
164
169
|
|
|
165
|
-
|
|
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:
|
|
166
175
|
|
|
167
176
|
1. **Create a free account** at [morphllm.com](https://www.morphllm.com)
|
|
168
177
|
2. **Get your API key** from [dashboard/api-keys](https://www.morphllm.com/dashboard/api-keys)
|
|
169
|
-
3. **
|
|
170
|
-
|
|
171
|
-
```
|
|
172
|
-
|
|
173
|
-
|
|
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
|
+
}
|
|
174
193
|
```
|
|
175
194
|
|
|
176
|
-
|
|
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)).
|
|
177
196
|
|
|
178
197
|
**Pricing**: Free tier includes 500 requests/month. Paid usage is ~$1/million tokens.
|
|
179
198
|
|
|
180
|
-
### Other MCP Servers (No Setup Required)
|
|
181
|
-
|
|
182
|
-
| Server | Purpose |
|
|
183
|
-
|--------|---------|
|
|
184
|
-
| `sequential-thinking` | Structured reasoning and problem-solving |
|
|
185
|
-
| `context7` | Library documentation lookup |
|
|
186
|
-
| `playwright` | Browser automation and testing |
|
|
187
|
-
| `serena` | Semantic code analysis and editing |
|
|
188
|
-
|
|
189
199
|
## Requirements
|
|
190
200
|
|
|
191
201
|
- Node.js 18+
|
|
192
202
|
- Kiro CLI installed (`~/.kiro` directory exists)
|
|
193
|
-
- (Optional) MorphLLM API key for fast file editing
|
|
194
203
|
|
|
195
204
|
## Troubleshooting
|
|
196
205
|
|
|
@@ -216,16 +225,11 @@ cat ~/.kiro/settings/mcp.json
|
|
|
216
225
|
|
|
217
226
|
### MorphLLM not working
|
|
218
227
|
|
|
219
|
-
|
|
220
|
-
# Check if API key is set
|
|
221
|
-
echo $MORPH_API_KEY
|
|
222
|
-
|
|
223
|
-
# If empty, add to your shell profile
|
|
224
|
-
echo 'export MORPH_API_KEY="your-key-here"' >> ~/.zshrc
|
|
225
|
-
source ~/.zshrc
|
|
226
|
-
```
|
|
228
|
+
MorphLLM requires manual setup. See [MCP Server Setup](#mcp-server-setup) above.
|
|
227
229
|
|
|
228
|
-
|
|
230
|
+
**Common issues:**
|
|
231
|
+
- API key must be hardcoded in mcp.json (environment variable expansion doesn't work reliably)
|
|
232
|
+
- Get your API key from [morphllm.com/dashboard/api-keys](https://www.morphllm.com/dashboard/api-keys)
|
|
229
233
|
|
|
230
234
|
### Reinstall from scratch
|
|
231
235
|
|
package/dist/agents/sc-pm.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
"$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": "${MORPH_API_KEY}"
|
|
108
|
-
},
|
|
109
|
-
"autoApprove": [
|
|
110
|
-
"edit_file"
|
|
111
|
-
]
|
|
112
98
|
}
|
|
113
99
|
}
|
|
114
100
|
}
|