claude-dreamteam 1.0.0 → 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
@@ -1,51 +1,89 @@
1
1
  # claude-dreamteam
2
2
 
3
- Stop configuring Claude Code manually. Describe your project, get a full dev team.
3
+ **You shouldn't need to learn Claude Code to use Claude Code.**
4
+
5
+ One command to unlock 100% of Claude Code's power. Zero learning curve.
6
+
7
+ ```bash
8
+ npx claude-dreamteam init
9
+ ```
4
10
 
5
11
  ---
6
12
 
7
13
  ## The Problem
8
14
 
9
- Every new Claude Code project starts the same way: you manually write a CLAUDE.md, figure out which agents you need, create skills for your tech stack, set up memory files, configure MCP servers...
15
+ Claude Code is a Ferrari with no steering wheel.
10
16
 
11
- It takes hours. And most people never get past Level 1.
17
+ The engine is incredible but to actually use it, you need to:
12
18
 
13
- ## The Solution
19
+ - Learn CLAUDE.md syntax and what to put in it
20
+ - Learn agent YAML frontmatter and how to write good agent prompts
21
+ - Learn skills structure and how triggering works
22
+ - Learn commands and `$ARGUMENTS`
23
+ - Learn memory system and the 200-line limit
24
+ - Learn MCP server configuration
25
+ - Learn hooks format
26
+ - Figure out how all of these connect to each other
14
27
 
15
- ```bash
16
- npx claude-dreamteam init
17
- ```
28
+ That's not vibe coding. That's hours of reading documentation before writing a single line of your actual project.
18
29
 
19
- One install. Then open any empty folder and tell Claude what you want to build:
30
+ Most people install Claude Code, type a few prompts, and never unlock 90% of what it can do. Not because they're not smart enough — because the setup barrier is too high.
31
+
32
+ ---
33
+
34
+ ## Without Dream Team vs With Dream Team
35
+
36
+ **Without** — you manually create each file, one by one, after reading docs:
20
37
 
21
38
  ```
22
- /dream food delivery app with React Native, Node.js, PostgreSQL, and Stripe
39
+ You: "How do I set up agents?"
40
+ Google: *reads docs for 30 minutes*
41
+ You: *creates one agent file with basic frontmatter*
42
+ You: "Now how do skills work?"
43
+ Google: *reads more docs*
44
+ ... 3 hours later, you have a half-configured environment
23
45
  ```
24
46
 
25
- The orchestrator reads your idea, detects your tech stack, and builds your entire Claude Code environment automatically:
47
+ **With** you describe your idea and everything gets built:
26
48
 
27
- - **CLAUDE.md** with your project's architecture, conventions, and rules
28
- - **Specialized agents** frontend-dev, backend-dev, tester, reviewer (tailored to YOUR stack)
29
- - **Skills** reusable tech-stack patterns that every agent consults
30
- - **Slash commands**/new-feature, /fix-bug, /run-tests, /review
31
- - **Memory system** persistent knowledge base that makes your project smarter over time
32
- - **MCP servers** auto-configured connections to GitHub, databases, Stripe, etc.
49
+ ```
50
+ You: /dream food delivery app with React Native, Node.js, and Stripe
51
+ Claude: [Level 1] Building CLAUDE.md... done
52
+ CLAUDE.md (94 lines)architecture, conventions, directory structure
53
+ .gitignoreconfigured for Node.js
54
+ [Level 2] Building MCP config... done
55
+ .mcp.json — 3 servers (github, postgres, filesystem)
56
+ [Level 3] Building skills and commands... done
57
+ Skills: react-native-patterns, nodejs-patterns, project-conventions
58
+ Commands: add, test, review, new-screen, new-endpoint
59
+ [Level 4] Building memory system... done
60
+ MEMORY.md (138 lines) — master index
61
+ codebase-map, patterns, antipatterns — ready
62
+ [Level 5] Building specialized agents... done
63
+ dev-mobile.md (sonnet) — owns app/screens/, app/components/
64
+ dev-backend.md (sonnet) — owns server/routes/, server/services/
65
+ dev-tester.md (sonnet, background: true) — owns __tests__/
66
+ dev-reviewer.md (opus, read-only) — code review specialist
67
+
68
+ Your Level: 5 / 10 — "Multi-Agent"
69
+ [=========================.............] 5/10
70
+
71
+ Ready! Try: /add user authentication with phone number
72
+ ```
33
73
 
34
- Everything is project-specific. Not generic templates. Real, usable infrastructure.
74
+ **2 minutes. Zero documentation. Full environment.**
35
75
 
36
76
  ---
37
77
 
38
78
  ## Quick Start
39
79
 
40
- ### 1. Install (once, takes 2 seconds)
80
+ ### 1. Install (once)
41
81
 
42
82
  ```bash
43
83
  npx claude-dreamteam init
44
84
  ```
45
85
 
46
- This copies the orchestrator into `~/.claude/` so it's available in every project.
47
-
48
- ### 2. Create your project
86
+ ### 2. Open any project folder
49
87
 
50
88
  ```bash
51
89
  mkdir my-app && cd my-app
@@ -55,13 +93,19 @@ claude
55
93
  ### 3. Describe your idea
56
94
 
57
95
  ```
58
- /dream SaaS analytics dashboard with Next.js, Python FastAPI backend,
59
- PostgreSQL database, Stripe billing, deployed on Vercel
96
+ /dream SaaS analytics dashboard with Next.js, Python FastAPI,
97
+ PostgreSQL, Stripe billing, deployed on Vercel
60
98
  ```
61
99
 
62
- That's it. The orchestrator takes over and builds everything.
100
+ The orchestrator analyzes your idea, detects the stack, and builds Levels 1-5 automatically.
101
+
102
+ ### 4. Start building
103
+
104
+ ```
105
+ /add user authentication with Google OAuth
106
+ ```
63
107
 
64
- ### 4. Level up when you're ready
108
+ ### 5. Level up when ready
65
109
 
66
110
  ```
67
111
  /level-up
@@ -69,160 +113,228 @@ That's it. The orchestrator takes over and builds everything.
69
113
 
70
114
  ---
71
115
 
72
- ## The 10 Levels
116
+ ## 7 Commands — All Plain English
73
117
 
74
- We mapped out 10 levels of Claude Code mastery. Most people are stuck at Level 0-1.
75
- The gap between levels isn't knowledge — it's setup. Dream Team closes that gap.
118
+ No jargon. No dev knowledge needed. Just type what you want.
119
+
120
+ ### Build & Grow
121
+
122
+ | Command | What it does |
123
+ |---------|-------------|
124
+ | `/dream` `"your idea"` | Describe your project, get the entire AI dev environment built |
125
+ | `/level-up` | See your current level (0-10), build the next one |
126
+ | `/evolve` | Auto-find and fix gaps in your agents, skills, and memory |
127
+
128
+ ### Everyday Use
129
+
130
+ | Command | What it does |
131
+ |---------|-------------|
132
+ | `/fix` `"what's broken"` | Describe the bug in plain English, get it fixed |
133
+ | `/ship` | Save your work and push to GitHub (auto-generates commit message) |
134
+ | `/explain` `"anything"` | Explain code, errors, or concepts like you're not a developer |
135
+ | `/status` | Quick health check — what's working, what changed, what to do next |
136
+
137
+ ### Real Workflow Example
76
138
 
77
139
  ```
78
- Level 0 Terminal Tourist You type prompts and hope for the best
79
- Level 1 Foundation CLAUDE.md exists with project conventions
80
- Level 2 Connected MCP servers configured (GitHub, DB, APIs)
81
- Level 3 Skilled Custom skills + slash commands
82
- Level 4 Remembering Memory system — project gets smarter over time
83
- Level 5 Multi-Agent Specialized agents working together
84
- Level 6 Headless CLI scripts, git hooks, automation
85
- Level 7 Visual Browser automation with Playwright
86
- Level 8 Parallel Multiple agents running concurrently
87
- Level 9 Always-On Cron jobs, background agents running 24/7
88
- Level 10 Self-Evolving Autonomous loops — agents that improve agents
89
- ```
140
+ /dream fitness tracker app with React Native and Firebase
141
+ ... orchestrator builds your entire dev environment ...
90
142
 
91
- `/dream` builds you to **Level 5** by default. From there, `/level-up` takes you one step at a time.
143
+ /add user profile page with avatar upload
144
+ ... specialist agent builds the feature ...
92
145
 
93
- ---
146
+ /fix the avatar doesn't show after upload
147
+ ... agent finds the bug, fixes it, explains what happened ...
94
148
 
95
- ## Three Commands
149
+ /explain what does useEffect do in the profile component
150
+ ... explains in plain English, no jargon ...
96
151
 
97
- Once installed, you have three commands inside Claude Code:
152
+ /ship
153
+ ... commits with message "Add user profile with avatar upload", pushes to GitHub ...
98
154
 
99
- ### `/dream` — Build from scratch
155
+ /status
156
+ ... shows: 12 files changed, all tests passing, suggests adding unit tests ...
100
157
 
101
- ```
102
- /dream e-commerce platform with React, Express, MongoDB, and Stripe
158
+ /level-up
159
+ ... scans environment, shows Level 5, offers to build Level 6 (hooks & automation) ...
103
160
  ```
104
161
 
105
- Analyzes your idea. Detects the tech stack. Builds Levels 1 through 5 automatically.
106
- Works with any stack — React, Vue, Angular, Next.js, FastAPI, Django, Rails,
107
- Go, Rust, mobile, monorepos, whatever you throw at it.
162
+ ---
163
+
164
+ ## The 10 Levels
108
165
 
109
- ### `/level-up` See where you are, build what's next
166
+ Most Claude Code users are stuck at Level 0-1. The gap between levels isn't knowledge — it's setup.
110
167
 
111
168
  ```
112
- /level-up
169
+ Level 0 Terminal Tourist You type prompts and hope for the best
170
+ Level 1 Foundation CLAUDE.md + .gitignore
171
+ Level 2 Connected MCP servers (GitHub, databases, APIs)
172
+ Level 3 Skilled Custom skills + slash commands
173
+ Level 4 Remembering Memory system — project learns over time
174
+ Level 5 Multi-Agent Specialist agents working together
175
+ Level 6 Automated Hooks (auto-format on save) + permissions
176
+ Level 7 Extended Advanced MCP + agents scoped to servers
177
+ Level 8 Orchestrated Pipeline agents, background work, safe experiments
178
+ Level 9 Workflow Multi-step commands: /deploy, /sprint, /refactor
179
+ Level 10 Self-Evolving Agents that improve other agents
113
180
  ```
114
181
 
115
- Scans your actual environment. Shows your current level. Explains what the next
116
- level unlocks. Offers to build it right there. No overwhelm just the next step.
182
+ Every level creates only native Claude Code files (markdown + JSON).
183
+ No bash scripts. No cron jobs. **Works on Windows, Mac, and Linux identically.**
117
184
 
118
- ### `/evolve` Auto-improve everything
185
+ `/dream` builds you to **Level 5** by default.
186
+ `/level-up` takes you higher, one step at a time.
187
+ `/evolve` strengthens what you already have.
188
+
189
+ ---
190
+
191
+ ## What Gets Generated
192
+
193
+ After running `/dream`, your project gets a complete AI development environment:
119
194
 
120
195
  ```
121
- /evolve
196
+ your-project/
197
+ CLAUDE.md Project conventions (Claude reads this first)
198
+ .gitignore Configured for your stack
199
+ .mcp.json MCP server connections
200
+ .devteam/
201
+ blueprint.json Project analysis
202
+ .claude/
203
+ settings.json Hooks & permissions (Level 6+)
204
+ agents/
205
+ dev-frontend.md Frontend specialist (sonnet)
206
+ dev-backend.md Backend specialist (sonnet)
207
+ dev-tester.md Testing specialist (sonnet, background)
208
+ dev-reviewer.md Code reviewer (opus, read-only)
209
+ dev-pipeline.md Multi-agent workflows (Level 8+)
210
+ dev-experiment.md Safe experiments in worktree (Level 8+)
211
+ loop-controller.md Self-improvement engine (Level 10)
212
+ skills/
213
+ react-patterns/SKILL.md Frontend patterns for YOUR stack
214
+ fastapi-patterns/SKILL.md Backend patterns for YOUR stack
215
+ project-conventions/SKILL.md Your project's rules and style
216
+ commands/
217
+ add.md Add a feature by describing it
218
+ test.md Run tests, explain results
219
+ review.md Code review
220
+ deploy.md Deployment pipeline (Level 9+)
221
+ sprint.md Plan & execute work (Level 9+)
222
+ memory/
223
+ MEMORY.md Master knowledge base (auto-loaded)
224
+ codebase-map.md Every module indexed
225
+ patterns.md Discovered patterns
226
+ antipatterns.md Known pitfalls
227
+ decisions.md Architecture decisions
122
228
  ```
123
229
 
124
- Runs a gap analysis on your agents, skills, commands, and memory. Finds what's
125
- weak or missing. Fixes it automatically. Shows you the before/after score.
230
+ Everything is tailored to YOUR project. Not templates. Not generic. **Real, specific infrastructure.**
126
231
 
127
232
  ---
128
233
 
129
- ## CLI Reference
234
+ ## Every Claude Code Feature — Configured Automatically
130
235
 
131
- ```bash
132
- npx claude-dreamteam init # Install globally (all projects)
133
- npx claude-dreamteam init --force # Reinstall, overwrite modified files
134
- npx claude-dreamteam init-local # Install in current project only
135
- npx claude-dreamteam status # Check what's installed
136
- npx claude-dreamteam uninstall # Remove everything
137
- npx claude-dreamteam --version # Show version
138
- ```
236
+ Dream Team doesn't reinvent anything. It configures what Claude Code already has:
237
+
238
+ | Claude Code Feature | What Dream Team does with it |
239
+ |---------|------------------------------|
240
+ | **CLAUDE.md** | Generates project conventions, architecture, agent routing |
241
+ | **Agents** | Creates specialists with full frontmatter (model, permissions, skills, MCP, hooks) |
242
+ | **Skills** | Builds patterns with progressive disclosure (SKILL.md + references/), pushy descriptions for reliable triggering |
243
+ | **Commands** | 7 global + project-specific commands generated from your stack |
244
+ | **Memory** | Persistent knowledge base — codebase map, patterns, antipatterns, decisions |
245
+ | **MCP Servers** | Auto-detects from your stack, scopes per agent via `mcpServers:` |
246
+ | **Hooks** | Auto-format on file saves, agent completion notifications |
247
+ | **Model routing** | `opus` for thinking, `sonnet` for building, `haiku` for simple tasks |
248
+ | **Permission modes** | `acceptEdits` for builders, `plan` for reviewers — no permission spam |
249
+ | **Background agents** | `background: true` on testers for concurrent work |
250
+ | **Worktree isolation** | `isolation: worktree` for safe experiments that can't break your code |
251
+ | **Tool scoping** | `disallowedTools: Write, Edit` on reviewers — read-only by design |
252
+ | **Agent chaining** | Pipeline agents that delegate to specialists via Agent tool |
253
+
254
+ **You get all of this without knowing any of it exists.**
139
255
 
140
256
  ---
141
257
 
142
258
  ## What Gets Installed
143
259
 
144
- The package is tiny. It installs 4 files into your `~/.claude/` directory:
260
+ The package itself is tiny. 8 files into `~/.claude/`:
145
261
 
146
262
  ```
147
263
  ~/.claude/
148
264
  agents/
149
- orchestrator.md The brain — one agent that builds everything
265
+ orchestrator.md The brain — one agent that knows all 10 levels
150
266
  commands/
151
- dream.md /dream command
152
- level-up.md /level-up command
153
- evolve.md /evolve command
267
+ dream.md /dream — build from a project idea
268
+ level-up.md /level-up — grow to the next level
269
+ evolve.md /evolve — auto-improve environment
270
+ fix.md /fix — describe a bug, get it fixed
271
+ ship.md /ship — commit and push changes
272
+ explain.md /explain — plain English explanations
273
+ status.md /status — project health check
154
274
  ```
155
275
 
156
- That's it. No dependencies. No background processes. No config files to maintain.
157
-
276
+ No dependencies. No background processes. No config files.
158
277
  The orchestrator generates everything else dynamically based on your project.
159
278
 
160
279
  ---
161
280
 
162
- ## How It Works Under the Hood
163
-
164
- The orchestrator is a single Claude Code agent file that carries the knowledge of all 10 levels.
165
-
166
- When you run `/dream`, it:
167
-
168
- 1. Creates a **blueprint** (`.devteam/blueprint.json`) analyzing your project
169
- 2. Builds each level sequentially — CLAUDE.md, then MCP, then skills, then memory, then agents
170
- 3. Runs a **quality check** after each level — verifies cross-references, fixes inconsistencies
171
- 4. Presents a summary of everything created
172
-
173
- When you run `/level-up`, it:
174
-
175
- 1. **Scans** your environment for what exists at each level
176
- 2. Calculates your **current level** (cumulative — can't be Level 5 without 1-4)
177
- 3. Shows you what the **next level** unlocks
178
- 4. Builds it if you say yes
179
-
180
- When you run `/evolve`, it:
281
+ ## CLI Reference
181
282
 
182
- 1. Analyzes **gaps** in your agents, skills, commands, and memory
183
- 2. Scores each area (1-10)
184
- 3. Fixes the top 5 weaknesses
185
- 4. Reports the improvement
283
+ ```bash
284
+ npx claude-dreamteam init # Install globally (all projects)
285
+ npx claude-dreamteam init --force # Reinstall, overwrite modified files
286
+ npx claude-dreamteam init-local # Install in current project only
287
+ npx claude-dreamteam status # Check what's installed
288
+ npx claude-dreamteam uninstall # Remove everything
289
+ npx claude-dreamteam --version # Show version
290
+ ```
186
291
 
187
292
  ---
188
293
 
189
- ## Requirements
294
+ ## How It Works
295
+
296
+ The orchestrator is a single Claude Code agent (~1000 lines) that carries the knowledge of all 10 levels.
190
297
 
191
- - **[Claude Code](https://docs.anthropic.com/en/docs/claude-code)** installed and authenticated
192
- - **Node.js** >= 16
298
+ **`/dream`** analyzes your project idea, creates a blueprint, then builds each level sequentially. It delegates to sub-agents for each level, runs quality checks, and presents everything created.
193
299
 
194
- ### Platform Notes
300
+ **`/level-up`** scans your environment file by file, calculates your current level, shows what the next level unlocks, and builds it.
195
301
 
196
- - **macOS / Linux** everything works natively
197
- - **Windows** — the orchestrator works fully. Scripts generated at Level 6+ (headless runner,
198
- cron jobs, git hooks) require Git Bash or WSL to run.
302
+ **`/evolve`** runs a gap analysis across all agents, skills, commands, and memory. Scores each area 1-10. Fixes the top 5 weaknesses. Reports the improvement.
199
303
 
200
304
  ---
201
305
 
202
306
  ## FAQ
203
307
 
204
308
  **Does this work with any tech stack?**
205
- Yes. The orchestrator analyzes whatever you describe and generates project-specific infrastructure.
206
- React, Vue, Angular, Svelte, Next.js, FastAPI, Django, Express, Rails, Go, Rust, Flutter, React Native — anything.
309
+ Yes. React, Vue, Angular, Svelte, Next.js, FastAPI, Django, Express, Rails, Go, Rust, Flutter, React Native, and anything else. The orchestrator analyzes whatever you describe.
207
310
 
208
311
  **Does it generate actual code for my app?**
209
- No. It generates the Claude Code *infrastructure* (agents, skills, commands, memory) that then helps
210
- you build your app faster. Think of it as building your AI dev team, not building your app.
312
+ No. It generates the Claude Code *infrastructure* (agents, skills, commands, memory) that helps you build your app faster. Think of it as hiring an AI dev team, not building your app.
211
313
 
212
314
  **Can I customize what it generates?**
213
- Everything it creates is plain markdown files. Edit any agent, skill, or command after generation.
214
- The orchestrator creates the starting point — you own everything from there.
315
+ Everything is plain markdown files. Edit any agent, skill, or command after generation. The orchestrator creates the starting point — you own it from there.
215
316
 
216
317
  **What model does it use?**
217
- The orchestrator runs on Opus for deep analysis. Generated dev agents default to Sonnet for
218
- fast implementation. Reviewers use Opus. You can change any agent's model after generation.
318
+ The orchestrator uses Opus for deep analysis. Generated agents use smart routing: Opus for architecture and review, Sonnet for implementation, Haiku for simple tasks. You can change any agent's model.
219
319
 
220
320
  **Will it overwrite my existing files?**
221
- The CLI protects modified files if you edited orchestrator.md, `init` will skip it unless
222
- you pass `--force`. The orchestrator never deletes user-created files during builds.
321
+ The CLI protects modified files. If you edited a file, `init` skips it unless you pass `--force`. The orchestrator never deletes user-created files.
322
+
323
+ **Does it work on Windows?**
324
+ Yes. Every level uses only native Claude Code files (markdown + JSON). No bash scripts, no cron, no OS-specific tools. Windows, Mac, Linux — identical.
325
+
326
+ **How is this different from Claude Code's built-in /init?**
327
+ Claude Code's `/init` generates a basic CLAUDE.md. That's Level 1. Dream Team builds Levels 1-10: agents, skills, commands, memory, MCP, hooks, pipelines, and a self-improving loop.
328
+
329
+ **Is this free?**
330
+ The package is free. You need a Claude Code subscription (which uses your own API credits).
223
331
 
224
332
  ---
225
333
 
226
334
  ## License
227
335
 
228
336
  MIT
337
+
338
+ ---
339
+
340
+ Built by [@haytamAroui](https://github.com/haytamAroui)
package/bin/cli.js CHANGED
@@ -97,6 +97,10 @@ function install(mode, force = false) {
97
97
  { file: 'dream.md', desc: '/dream — describe your project, get everything built' },
98
98
  { file: 'level-up.md', desc: '/level-up — check your level, build the next one' },
99
99
  { file: 'evolve.md', desc: '/evolve — auto-improve your environment' },
100
+ { file: 'fix.md', desc: '/fix — describe a bug, get it fixed' },
101
+ { file: 'ship.md', desc: '/ship — commit and push your changes' },
102
+ { file: 'explain.md', desc: '/explain — explain code/errors in plain English' },
103
+ { file: 'status.md', desc: '/status — quick project health check' },
100
104
  ];
101
105
 
102
106
  for (const cmd of commands) {
@@ -136,6 +140,10 @@ function showUsage() {
136
140
  log(` ${C.cyan}/dream${C.reset} ${C.dim}"your idea"${C.reset} Build entire project from description`);
137
141
  log(` ${C.cyan}/level-up${C.reset} See your level, build the next one`);
138
142
  log(` ${C.cyan}/evolve${C.reset} Auto-improve your environment`);
143
+ log(` ${C.cyan}/fix${C.reset} ${C.dim}"what's broken"${C.reset} Describe a bug, get it fixed`);
144
+ log(` ${C.cyan}/ship${C.reset} Commit and push your changes`);
145
+ log(` ${C.cyan}/explain${C.reset} ${C.dim}"anything"${C.reset} Explain code/errors in plain English`);
146
+ log(` ${C.cyan}/status${C.reset} Quick project health check`);
139
147
  log('');
140
148
  }
141
149
 
@@ -145,6 +153,10 @@ function uninstall() {
145
153
  path.join(HOME_CLAUDE, 'commands', 'dream.md'),
146
154
  path.join(HOME_CLAUDE, 'commands', 'level-up.md'),
147
155
  path.join(HOME_CLAUDE, 'commands', 'evolve.md'),
156
+ path.join(HOME_CLAUDE, 'commands', 'fix.md'),
157
+ path.join(HOME_CLAUDE, 'commands', 'ship.md'),
158
+ path.join(HOME_CLAUDE, 'commands', 'explain.md'),
159
+ path.join(HOME_CLAUDE, 'commands', 'status.md'),
148
160
  ];
149
161
 
150
162
  log(`${C.dim} Removing Dream Team files...${C.reset}`);
@@ -166,6 +178,10 @@ function uninstall() {
166
178
  path.join(process.cwd(), '.claude', 'commands', 'dream.md'),
167
179
  path.join(process.cwd(), '.claude', 'commands', 'level-up.md'),
168
180
  path.join(process.cwd(), '.claude', 'commands', 'evolve.md'),
181
+ path.join(process.cwd(), '.claude', 'commands', 'fix.md'),
182
+ path.join(process.cwd(), '.claude', 'commands', 'ship.md'),
183
+ path.join(process.cwd(), '.claude', 'commands', 'explain.md'),
184
+ path.join(process.cwd(), '.claude', 'commands', 'status.md'),
169
185
  ];
170
186
 
171
187
  for (const file of localLocations) {
@@ -194,6 +210,10 @@ function status() {
194
210
  { path: path.join(HOME_CLAUDE, 'commands', 'dream.md'), label: '/dream command (global)' },
195
211
  { path: path.join(HOME_CLAUDE, 'commands', 'level-up.md'), label: '/level-up command (global)' },
196
212
  { path: path.join(HOME_CLAUDE, 'commands', 'evolve.md'), label: '/evolve command (global)' },
213
+ { path: path.join(HOME_CLAUDE, 'commands', 'fix.md'), label: '/fix command (global)' },
214
+ { path: path.join(HOME_CLAUDE, 'commands', 'ship.md'), label: '/ship command (global)' },
215
+ { path: path.join(HOME_CLAUDE, 'commands', 'explain.md'), label: '/explain command (global)' },
216
+ { path: path.join(HOME_CLAUDE, 'commands', 'status.md'), label: '/status command (global)' },
197
217
  ];
198
218
 
199
219
  let installed = 0;
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "claude-dreamteam",
3
- "version": "1.0.0",
3
+ "version": "1.1.0",
4
4
  "description": "One command to build your entire Claude Code development environment. Level 0 to 10.",
5
5
  "bin": {
6
6
  "claude-dreamteam": "./bin/cli.js"
@@ -17,7 +17,13 @@
17
17
  "skills",
18
18
  "orchestrator"
19
19
  ],
20
+ "author": "haytamAroui",
20
21
  "license": "MIT",
22
+ "repository": {
23
+ "type": "git",
24
+ "url": "https://github.com/haytamAroui/claude-dreamteam.git"
25
+ },
26
+ "homepage": "https://github.com/haytamAroui/claude-dreamteam#readme",
21
27
  "files": [
22
28
  "bin/",
23
29
  "templates/"