claude-code-team 0.1.7 → 0.1.9

package/README.md

@@ -105,12 +105,17 @@ my-project/
 5. **Leads** aggregate worker results, write to root `.outputs/`
 6. **Orchestrator** reads Lead outputs, responds to User
 
-## Workers vs Subagents
+## Session Types
 
-| Type | Command | Use When |
-|------|---------|----------|
-| Worker | `claude -p "TASK" &` | One-shot, no Q&A |
-| Subagent | `claude --session-id $ID -p "TASK"` | Need iteration |
+| Type | How Created | By Whom |
+|------|-------------|---------|
+| User session | `claude` (interactive) | Human |
+| CCT session | `claude --session-id $ID -p "TASK"` | Orchestrator/Lead |
+
+- **Orchestrator** runs in user session (you talk to it)
+- **Leads** and **Workers** run as CCT sessions (created programmatically)
+- CCT sessions can be resumed with `-r $ID` for Q&A
+- Only **Workers** do actual work
 
 ## License
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-code-team",
-  "version": "0.1.7",
+  "version": "0.1.9",
   "description": "Claude Code Team - orchestrate multiple Claude sessions",
   "bin": {
     "cct": "./bin/cct.js"

package/templates/lead.md

@@ -9,31 +9,6 @@ You are a **Team Lead** — a coordinator for your domain.
 - You **aggregate results** and report back to Orchestrator
 - You do NOT do the work yourself — you delegate to workers
 
-## CRITICAL: Workers vs Subagents
-
-| Type | How to Run | Use When |
-|------|-----------|----------|
-| **Worker** | `claude -p "TASK: ..." &` | One-shot task, no Q&A needed |
-| **Subagent** | `claude --session-id $ID -p "..."` | Need to ask questions, iterate |
-
-### Worker (одноразовый)
-```bash
-claude --dangerously-skip-permissions -p "TASK: Write market analysis" &
-```
-- Runs once, produces output, exits
-- Cannot ask questions
-- Use for well-defined tasks
-
-### Subagent (с сессией)
-```bash
-WORKER_ID=$(uuidgen)
-echo "$WORKER_ID" > .outputs/analyst.id
-claude --dangerously-skip-permissions --session-id "$WORKER_ID" -p "TASK: Research competitors"
-```
-- Can be resumed with `-r $WORKER_ID`
-- Can receive follow-up instructions
-- Use when you might need to clarify or iterate
-
 ## Your Structure
 
 ```
@@ -42,11 +17,24 @@ leads/<your_name>/
 ├── .outputs/           # Your workers' outputs
 └── workers/            # Your workers (you create them)
     ├── worker_1/
-    │   └── CLAUDE.md
-    └── worker_2/
-        └── CLAUDE.md
+    ├── worker_2/
+    ├── worker_3/
+    └── ...              # Create as many workers as needed!
 ```
 
+## Worker Count
+
+**Create as many workers as needed for the task.** There is NO limit on workers.
+
+Guidelines:
+- **Simple task**: 1-2 workers
+- **Medium task**: 3-5 workers
+- **Complex task**: 5-10+ workers
+- **Research project**: One worker per research question/area
+
+Break down the task and create a worker for each independent piece of work.
+Launch workers in parallel for maximum efficiency.
+
 ## Capabilities Catalog
 
 **IMPORTANT**: Before creating workers, check the catalog at `../../features/`:
@@ -115,19 +103,11 @@ EOF
 
 ### 5. Launch Worker
 
-**For one-shot task (worker):**
-```bash
-cd workers/<name>
-claude --dangerously-skip-permissions -p "TASK: <specific task>" &
-cd ../..
-```
-
-**For iterative task (subagent):**
 ```bash
 cd workers/<name>
 WORKER_ID=$(uuidgen)
 echo "$WORKER_ID" > ../../.outputs/<name>.id
-claude --dangerously-skip-permissions --session-id "$WORKER_ID" -p "TASK: <task>"
+claude --dangerously-skip-permissions --session-id "$WORKER_ID" -p "TASK: <specific task>" &
 cd ../..
 ```
 
@@ -137,12 +117,21 @@ cd ../..
 # Check status
 ls .outputs/*.status 2>/dev/null
 
+# Check for questions
+ls .outputs/*.question 2>/dev/null
+
 # Read outputs
 cat .outputs/*.md
+```
+
+## Answering Worker Questions
 
-# Resume subagent if needed
+When worker writes a question to `.outputs/<name>.question`:
+
+```bash
 WORKER_ID=$(cat .outputs/<name>.id)
-claude -r "$WORKER_ID" -p "Additional instruction..."
+claude -r "$WORKER_ID" -p "ANSWER: <your answer>"
+rm .outputs/<name>.question
 ```
 
 ## When All Workers Done
@@ -185,6 +174,5 @@ fi
 1. **Check catalog first** — `../../features/` has available roles and tools
 2. **Read project context** — `../../.context/project.md`
 3. **Delegate everything** — don't do work yourself
-4. **Choose worker vs subagent** — one-shot vs iterative
-5. **Aggregate results** — combine worker outputs into cohesive report
-6. **Signal when done** — so Orchestrator knows
+4. **Aggregate results** — combine worker outputs into cohesive report
+5. **Signal when done** — so Orchestrator knows