ai-sprint-kit 2.1.37 → 2.1.39
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 +12 -164
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -6,25 +6,14 @@
|
|
|
6
6
|
|
|
7
7
|
## What is AI Sprint?
|
|
8
8
|
|
|
9
|
-
AI Sprint transforms Claude Code into a team of 12 specialized AI agents with 17 powerful commands
|
|
9
|
+
AI Sprint transforms Claude Code into a team of **12 specialized AI agents** with **17 powerful commands**. Build production-grade software with security-first, autonomous development.
|
|
10
10
|
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
-
|
|
14
|
-
-
|
|
15
|
-
-
|
|
16
|
-
-
|
|
17
|
-
- **Team Collaboration** - Shared memory and multi-session orchestration
|
|
18
|
-
|
|
19
|
-
## Features
|
|
20
|
-
|
|
21
|
-
- **12 AI Agents** - planner, implementer, tester, reviewer, security, devops, docs, debugger, researcher, verifier, browser-tester, deployment-smoke
|
|
22
|
-
- **17 Commands** - /ai-sprint-init, /ai-sprint-plan, /ai-sprint-code, /ai-sprint-test, /ai-sprint-review, /ai-sprint-secure, /ai-sprint-deploy, /ai-sprint-docs, /ai-sprint-debug, /ai-sprint-fix, /ai-sprint-scan, /ai-sprint-validate, /ai-sprint-browser-test, /ai-sprint-orchestrate, /ai-sprint-setup, /ai-sprint-auto, /ai-sprint-ralph
|
|
23
|
-
- **Automation Hooks** - PostToolUse (auto-format, lint, sound), Stop (final verification), SubagentStart (context injection)
|
|
24
|
-
- **Memory System** - Persistent context across sessions
|
|
25
|
-
- **Security-First** - Built-in SAST, secrets scanning, dependency audit
|
|
26
|
-
- **Browser Testing** - Playwright integration for UI verification
|
|
27
|
-
- **Team Orchestration** - Multi-session coordination patterns
|
|
11
|
+
**Features:**
|
|
12
|
+
- 12 AI Agents (planner, implementer, tester, reviewer, security, devops, docs, debugger, researcher, verifier, browser-tester, deployment-smoke)
|
|
13
|
+
- 17 Slash Commands for full development lifecycle
|
|
14
|
+
- Automation Hooks (auto-format, lint-check, sound notifications)
|
|
15
|
+
- Memory System for persistent context
|
|
16
|
+
- Security-First with built-in SAST, secrets scanning, dependency audit
|
|
28
17
|
|
|
29
18
|
## Quick Start
|
|
30
19
|
|
|
@@ -32,38 +21,7 @@ AI Sprint transforms Claude Code into a team of 12 specialized AI agents with 17
|
|
|
32
21
|
npx ai-sprint-kit init
|
|
33
22
|
```
|
|
34
23
|
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
## CLI Commands
|
|
38
|
-
|
|
39
|
-
```bash
|
|
40
|
-
ai-sprint init # Install AI Sprint framework
|
|
41
|
-
ai-sprint update # Update to latest version
|
|
42
|
-
ai-sprint check-update # Check if update available
|
|
43
|
-
ai-sprint validate # Validate installation
|
|
44
|
-
ai-sprint doctor # Diagnose issues
|
|
45
|
-
ai-sprint repair # Repair installation
|
|
46
|
-
ai-sprint reinstall # Clean reinstall
|
|
47
|
-
ai-sprint list # Show features
|
|
48
|
-
ai-sprint init-ci # Generate CI/CD workflow
|
|
49
|
-
ai-sprint setup-env # Configure environment variables
|
|
50
|
-
ai-sprint setup-mcp # Configure MCP servers
|
|
51
|
-
```
|
|
52
|
-
|
|
53
|
-
## MCP Servers
|
|
54
|
-
|
|
55
|
-
AI Sprint Kit supports 6 MCP (Model Context Protocol) servers:
|
|
56
|
-
|
|
57
|
-
| Server | Package | API Key | Purpose |
|
|
58
|
-
|--------|---------|---------|---------|
|
|
59
|
-
| **Exa** | `exa-mcp-server` | Optional | Web search with clean results |
|
|
60
|
-
| **Context7** | `@upstash/context7-mcp` | Optional | Library documentation |
|
|
61
|
-
| **Human MCP** | `@goonnguyen/human-mcp` | Optional (Gemini) | Multimodal AI |
|
|
62
|
-
| **Playwright** | `@playwright/mcp@latest` | None | Browser automation |
|
|
63
|
-
| **Sequential Thinking** | `@modelcontextprotocol/server-sequential-thinking` | None | Complex reasoning |
|
|
64
|
-
| **Time** | `mcp-server-time` (uvx) | None | Timezone operations |
|
|
65
|
-
|
|
66
|
-
Configured during install (default YES). Reconfigure: `ai-sprint setup-mcp`
|
|
24
|
+
That's it! The installer will guide you through setup.
|
|
67
25
|
|
|
68
26
|
## Requirements
|
|
69
27
|
|
|
@@ -79,123 +37,13 @@ Configured during install (default YES). Reconfigure: `ai-sprint setup-mcp`
|
|
|
79
37
|
4. Run: `npx ai-sprint-kit init`
|
|
80
38
|
5. Start Claude Code: `claude`
|
|
81
39
|
|
|
82
|
-
##
|
|
83
|
-
|
|
84
|
-
Visit [ai-sprint-kit.app.data-espresso.com](https://ai-sprint-kit.app.data-espresso.com) for pricing details.
|
|
85
|
-
|
|
86
|
-
## Commands
|
|
87
|
-
|
|
88
|
-
```
|
|
89
|
-
/ai-sprint-init - Initialize project context (scan + CLAUDE.md)
|
|
90
|
-
/ai-sprint-plan - Create implementation plans
|
|
91
|
-
/ai-sprint-code - Generate or refactor code
|
|
92
|
-
/ai-sprint-test - Generate and run tests
|
|
93
|
-
/ai-sprint-review - Code quality review
|
|
94
|
-
/ai-sprint-secure - Security scanning (SAST + secrets + deps)
|
|
95
|
-
/ai-sprint-deploy - CI/CD setup and deployment
|
|
96
|
-
/ai-sprint-docs - Generate documentation
|
|
97
|
-
/ai-sprint-debug - Investigate issues
|
|
98
|
-
/ai-sprint-fix - Autonomous bug fix cycle
|
|
99
|
-
/ai-sprint-scan - Index codebase for AI context
|
|
100
|
-
/ai-sprint-validate - Pre-commit validation
|
|
101
|
-
/ai-sprint-browser-test - Browser automation tests (Playwright)
|
|
102
|
-
/ai-sprint-orchestrate - Multi-session coordination
|
|
103
|
-
/ai-sprint-setup - Configuration wizard
|
|
104
|
-
/ai-sprint-auto - Full autonomous development cycle
|
|
105
|
-
/ai-sprint-ralph - Persistent loop until task complete
|
|
106
|
-
```
|
|
107
|
-
|
|
108
|
-
## Ralph Loop - Autonomous Task Completion
|
|
109
|
-
|
|
110
|
-
Ralph runs tasks in a persistent loop until completion or max iterations reached. Ideal for migrations, batch fixes, and tasks with clear success criteria.
|
|
111
|
-
|
|
112
|
-
### Simple Mode (Single Task)
|
|
113
|
-
|
|
114
|
-
```bash
|
|
115
|
-
# Fix all TypeScript errors
|
|
116
|
-
/ai-sprint-ralph "fix all TypeScript errors" --promise "tsc: 0 errors"
|
|
117
|
-
|
|
118
|
-
# Migrate tests to vitest
|
|
119
|
-
/ai-sprint-ralph "migrate jest to vitest" --max-iterations 30
|
|
120
|
-
|
|
121
|
-
# Add dark mode
|
|
122
|
-
/ai-sprint-ralph "add dark mode toggle" --promise "DARK MODE DONE" --max-iterations 10
|
|
123
|
-
```
|
|
124
|
-
|
|
125
|
-
### PRD Mode (Multi-Feature)
|
|
126
|
-
|
|
127
|
-
Create `ai_context/ralph/prd.md`:
|
|
40
|
+
## Documentation
|
|
128
41
|
|
|
129
|
-
|
|
130
|
-
# Project: User Authentication
|
|
42
|
+
Full documentation available after purchase at [github.com/apiasak/ai-sprint-pro](https://github.com/apiasak/ai-sprint-pro)
|
|
131
43
|
|
|
132
|
-
##
|
|
133
|
-
|
|
134
|
-
### 1. Login Form
|
|
135
|
-
- [ ] Add login form component
|
|
136
|
-
- [ ] Implement JWT validation
|
|
137
|
-
- [ ] Add logout functionality
|
|
138
|
-
|
|
139
|
-
### 2. API Endpoints
|
|
140
|
-
- [ ] Create /api/users endpoint
|
|
141
|
-
- [ ] Add authentication middleware
|
|
142
|
-
```
|
|
143
|
-
|
|
144
|
-
Then run:
|
|
145
|
-
|
|
146
|
-
```bash
|
|
147
|
-
/ai-sprint-ralph --prd ai_context/ralph/prd.md --max-iterations 50
|
|
148
|
-
```
|
|
149
|
-
|
|
150
|
-
Ralph works through each feature, checking off tasks as completed.
|
|
151
|
-
|
|
152
|
-
### Options
|
|
153
|
-
|
|
154
|
-
| Option | Default | Description |
|
|
155
|
-
|--------|---------|-------------|
|
|
156
|
-
| `--max-iterations N` | 20 | Maximum loop iterations |
|
|
157
|
-
| `--promise STRING` | `<promise>COMPLETED</promise>` | Completion detection string |
|
|
158
|
-
| `--prd FILE` | none | PRD file for multi-feature mode |
|
|
159
|
-
| `--verbose`, `-v` | false | Show real-time output (recommended for debugging) |
|
|
160
|
-
| `--no-auto-commit` | false | Disable git commit after iteration |
|
|
161
|
-
| `--resume` | false | Resume interrupted session |
|
|
162
|
-
|
|
163
|
-
### Shell Script (Fully Autonomous)
|
|
164
|
-
|
|
165
|
-
For **unattended execution** without approval prompts, use the shell script:
|
|
166
|
-
|
|
167
|
-
```bash
|
|
168
|
-
# Simple mode (with verbose output)
|
|
169
|
-
.claude/scripts/ralph-loop.sh "fix all TypeScript errors" --promise "0 errors" --verbose
|
|
170
|
-
|
|
171
|
-
# PRD mode
|
|
172
|
-
.claude/scripts/ralph-loop.sh --prd ai_context/ralph/prd.md --max-iterations 50 --verbose
|
|
173
|
-
|
|
174
|
-
# Check status
|
|
175
|
-
.claude/scripts/ralph-status.sh
|
|
176
|
-
|
|
177
|
-
# Resume interrupted session
|
|
178
|
-
.claude/scripts/ralph-loop.sh --resume --verbose
|
|
179
|
-
```
|
|
180
|
-
|
|
181
|
-
The shell script uses `--dangerously-skip-permissions` to bypass approval gates - ideal for overnight tasks, migrations, and CI/CD pipelines.
|
|
182
|
-
|
|
183
|
-
### Writing Good Prompts
|
|
184
|
-
|
|
185
|
-
**Good prompts converge** - each iteration brings you closer to success:
|
|
186
|
-
|
|
187
|
-
```
|
|
188
|
-
Migrate all test files from Jest to Vitest.
|
|
189
|
-
|
|
190
|
-
SUCCESS CRITERIA:
|
|
191
|
-
1. All imports use "vitest" not "jest"
|
|
192
|
-
2. npm run test exits with code 0
|
|
193
|
-
3. Zero jest dependencies remain
|
|
194
|
-
|
|
195
|
-
When ALL criteria met, output: <promise>MIGRATION COMPLETE</promise>
|
|
196
|
-
```
|
|
44
|
+
## Pricing
|
|
197
45
|
|
|
198
|
-
|
|
46
|
+
Visit [ai-sprint-kit.app.data-espresso.com](https://ai-sprint-kit.app.data-espresso.com) for pricing details.
|
|
199
47
|
|
|
200
48
|
## Support
|
|
201
49
|
|