atris 2.3.7 → 2.4.0

package/atris/skills/magic-inbox/SKILL.md

@@ -0,0 +1,216 @@
+---
+name: magic-inbox
+description: "Autonomous inbox agent. Scores emails, drafts replies, archives noise, Slack summaries. Uses Gmail + Calendar + Slack + your context. Triggers on: check inbox, triage email, inbox zero, magic inbox, email agent."
+version: 2.0.0
+tags:
+  - inbox
+  - email
+  - productivity
+---
+
+# Magic Inbox
+
+You are an inbox agent. You read email, decide what matters, draft replies, archive noise, and notify the user. You do this using your own intelligence — no separate LLM calls needed. You ARE the model.
+
+## Bootstrap (ALWAYS Run First)
+
+```bash
+#!/bin/bash
+set -e
+
+if [ ! -f ~/.atris/credentials.json ]; then
+  echo "Not logged in. Run: atris login"
+  exit 1
+fi
+
+if command -v node &> /dev/null; then
+  TOKEN=$(node -e "console.log(require('$HOME/.atris/credentials.json').token)")
+elif command -v python3 &> /dev/null; then
+  TOKEN=$(python3 -c "import json,os; print(json.load(open(os.path.expanduser('~/.atris/credentials.json')))['token'])")
+else
+  TOKEN=$(jq -r '.token' ~/.atris/credentials.json)
+fi
+
+echo "Ready."
+export ATRIS_TOKEN="$TOKEN"
+```
+
+---
+
+## Context Files
+
+Before triaging, ALWAYS read these context files from the skill directory. They tell you who matters and how to behave.
+
+- `~/.claude/skills/magic-inbox/contacts.md` — priority contacts and noise patterns
+- `~/.claude/skills/magic-inbox/priorities.md` — current work streams
+- `~/.claude/skills/magic-inbox/voice.md` — how to write replies
+- `~/.claude/skills/magic-inbox/rules.md` — hard rules that override everything
+- `~/.claude/skills/magic-inbox/log.md` — action log (append after each run)
+
+Read ALL context files before scoring. They are your memory.
+
+---
+
+## The Flow
+
+### Step 1: Fetch everything (one call)
+
+```bash
+curl -s "https://api.atris.ai/api/magic-inbox/fetch?max_emails=30" \
+  -H "Authorization: Bearer $ATRIS_TOKEN"
+```
+
+Returns email + calendar + slack in one structured response:
+```json
+{
+  "email": {
+    "messages": [
+      {"id": "...", "thread_id": "...", "from": "...", "subject": "...", "snippet": "...", "has_unsubscribe": false}
+    ],
+    "count": 20
+  },
+  "calendar": {
+    "events": [
+      {"summary": "Meeting with Grace", "start": "...", "attendees": ["grace@pallet.com"]}
+    ],
+    "count": 1
+  },
+  "slack": {
+    "dms": [
+      {"channel_id": "...", "user_id": "...", "messages": [{"text": "...", "user": "...", "ts": "..."}]}
+    ],
+    "count": 3
+  }
+}
+```
+
+### Step 2: Score each email
+
+Using YOUR judgment, score each email:
+
+| Priority | Meaning | Action |
+|----------|---------|--------|
+| 1 | Drop everything | Draft reply immediately |
+| 2 | Today | Draft reply |
+| 3 | This week | Flag for later |
+| 4 | Whenever | Star as read-later |
+| 5 | Noise | Archive |
+
+**Scoring signals:**
+- Check `contacts.md` — is sender a priority contact?
+- Check `priorities.md` — is topic related to current work?
+- Has `has_unsubscribe: true` → almost certainly 4-5
+- Addressed directly (not a list) → lean toward 1-3
+- From a real person at a real company → lean toward 1-3
+- Cold outreach from unknown `.info`/`.xyz` domain → 5
+- Calendar shows meeting with sender today → bump priority up
+
+### Step 3: Take action (one call)
+
+```bash
+curl -s -X POST "https://api.atris.ai/api/magic-inbox/act" \
+  -H "Authorization: Bearer $ATRIS_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "drafts": [
+      {"to": "sender@email.com", "subject": "Re: Subject", "body": "Reply text", "thread_id": "..."}
+    ],
+    "archive": ["msg_id_1", "msg_id_2"],
+    "star": ["msg_id_3"],
+    "mark_read": ["msg_id_4"]
+  }'
+```
+
+Returns:
+```json
+{
+  "status": "ok",
+  "drafts_created": 2,
+  "archived": 16,
+  "starred": 6,
+  "read": 0,
+  "details": { ... }
+}
+```
+
+### Step 4: Present the briefing
+
+Show the user a clean summary (see format below).
+
+### Step 5: Update the log
+
+Append to `~/.claude/skills/magic-inbox/log.md` what you did this run.
+
+---
+
+## Summary Format
+
+```
+Inbox Triage — 23 emails processed
+
+Needs you (2):
+  - Suhas (via Maya) — FDE candidate intro. Draft ready. [check drafts]
+  - Michelle at Stripe — Build Day March 4, demo opportunity. Draft ready.
+
+This week (1):
+  - Kim (angel, 9x founder) — intro.co intro. Worth a call.
+
+Handled (20):
+  - 12 archived (newsletters, marketing)
+  - 5 starred as read-later (events, notifications)
+  - 3 npm/transactional archived
+
+Inbox: 3 emails remaining.
+```
+
+Rules for summary:
+- Use real names, not email addresses
+- Include WHY something is important (from context files)
+- For drafts, tell the user to check Gmail drafts
+- Be concise — this is a briefing, not a report
+- Show the count reduction (was X, now Y)
+
+---
+
+## Draft Style
+
+Follow `voice.md`. General rules:
+
+- Casual, direct, no fluff
+- No "I hope this email finds you well"
+- No "Just circling back" or "Per my last email"
+- Short — 2-4 sentences max
+- Match the energy of the incoming email
+- For intros: be warm, suggest a time, keep it to 2 sentences
+- For RSVPs: be enthusiastic, confirm attendance
+- For business: be specific about next steps
+
+---
+
+## Rules (from rules.md)
+
+Hard rules that override everything:
+1. NEVER auto-send. Always save as draft for user review.
+2. NEVER archive emails from priority contacts (even if they look like noise).
+3. NEVER reply to emails with List-Unsubscribe header.
+4. Always show the user what you did — no silent actions.
+5. If unsure about priority, err toward keeping it (don't archive).
+6. Log every action to log.md.
+
+---
+
+## API Quick Reference
+
+```bash
+# Get token (bootstrap does this)
+TOKEN=$(node -e "console.log(require('$HOME/.atris/credentials.json').token)")
+
+# Fetch inbox (email + calendar + slack)
+curl -s "https://api.atris.ai/api/magic-inbox/fetch?max_emails=30" -H "Authorization: Bearer $TOKEN"
+
+# Execute actions (drafts + archive + star)
+curl -s -X POST "https://api.atris.ai/api/magic-inbox/act" -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" -d '{"drafts":[...],"archive":[...],"star":[...]}'
+
+# Read a specific email (when snippet isn't enough)
+curl -s "https://api.atris.ai/api/integrations/gmail/messages/{id}" -H "Authorization: Bearer $TOKEN"
+```

package/atris/skills/x-search/SKILL.md

@@ -1,144 +1,234 @@
 ---
 name: x-search
 description: "X/Twitter search via xAI Grok API. Use when user wants to search tweets, monitor topics, find viral posts, or run social listening. Costs 5 credits per search. Triggers on x search, tweet search, twitter search, social listening, revenue intel, viral tweets."
-version: 1.0.0
+version: 2.0.0
 tags:
   - x-search
   - social
   - research
 ---
 
-# x-search
+# X Search
+
+> Drop this in `~/.claude/skills/x-search/SKILL.md` and Claude Code becomes your X/Twitter intelligence tool.
+
+## Bootstrap (ALWAYS Run First)
+
+Before any X search operation, run this bootstrap to ensure everything is set up:
+
+```bash
+#!/bin/bash
+set -e
+
+# 1. Check if atris CLI is installed
+if ! command -v atris &> /dev/null; then
+  echo "Installing atris CLI..."
+  npm install -g atris
+fi
+
+# 2. Check if logged in to AtrisOS
+if [ ! -f ~/.atris/credentials.json ]; then
+  echo "Not logged in to AtrisOS."
+  echo ""
+  echo "Option 1 (interactive): Run 'atris login' and follow prompts"
+  echo "Option 2 (non-interactive): Get token from https://atris.ai/auth/cli"
+  echo "                           Then run: atris login --token YOUR_TOKEN"
+  echo ""
+  exit 1
+fi
+
+# 3. Extract token
+if command -v node &> /dev/null; then
+  TOKEN=$(node -e "console.log(require('$HOME/.atris/credentials.json').token)")
+elif command -v python3 &> /dev/null; then
+  TOKEN=$(python3 -c "import json,os; print(json.load(open(os.path.expanduser('~/.atris/credentials.json')))['token'])")
+elif command -v jq &> /dev/null; then
+  TOKEN=$(jq -r '.token' ~/.atris/credentials.json)
+else
+  echo "Error: Need node, python3, or jq to read credentials"
+  exit 1
+fi
+
+# 4. Quick auth check
+STATUS=$(curl -s "https://api.atris.ai/api/me" \
+  -H "Authorization: Bearer $TOKEN")
+
+if echo "$STATUS" | grep -q "Token expired\|Not authenticated\|Unauthorized"; then
+  echo "Token expired. Please re-authenticate:"
+  echo "  Run: atris login --force"
+  exit 1
+fi
+
+echo "Ready. X Search is available (5 credits per search)."
+export ATRIS_TOKEN="$TOKEN"
+```
+
+---
 
-Search X/Twitter via xAI's Grok API. 5 credits per search action. Returns tweets with full text, author, engagement metrics, and citations.
+## API Reference
 
-## Quick Search
+Base: `https://api.atris.ai/api/x-search`
 
-```python
-cd backend
-source ../venv/bin/activate
+All requests require: `-H "Authorization: Bearer $TOKEN"`
+
+### Get Token (after bootstrap)
+```bash
+TOKEN=$(node -e "console.log(require('$HOME/.atris/credentials.json').token)")
 ```
 
-```python
-import asyncio
-from dotenv import load_dotenv
-load_dotenv('.env')
+### Search X/Twitter
+```bash
+curl -s -X POST "https://api.atris.ai/api/x-search/search" \
+  -H "Authorization: Bearer $TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "query": "\"CRM is dead\" OR \"Salesforce alternative\"",
+    "limit": 10
+  }'
+```
 
-from clients.xai import XAIClient, bill_xai_action
+**With date filter** (last N days only):
+```bash
+curl -s -X POST "https://api.atris.ai/api/x-search/search" \
+  -H "Authorization: Bearer $TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "query": "AI agents replacing SaaS",
+    "limit": 10,
+    "days_back": 7
+  }'
+```
 
-# 1. Bill the user (5 credits)
-bill = await bill_xai_action(USER_ID, "x_search")
-if not bill["ok"]:
-    print(f"Insufficient credits: {bill['error']}")
+**Response:**
+```json
+{
+  "status": "success",
+  "credits_used": 5,
+  "credits_remaining": 995,
+  "data": {
+    "content": "1. @levelsio: AI agents are replacing...",
+    "citations": ["https://x.com/levelsio/status/..."],
+    "usage": {"prompt_tokens": 200, "completion_tokens": 800}
+  }
+}
+```
 
-# 2. Search
-client = XAIClient()
-result = await client.search_x('"CRM is dead" OR "Salesforce is dead"', limit=10)
-print(result["content"])
-print(f"Usage: {result['usage']}")
+### Research a Person
+```bash
+curl -s -X POST "https://api.atris.ai/api/x-search/research-person" \
+  -H "Authorization: Bearer $TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "name": "Leah Bonvissuto",
+    "handle": "leahbon",
+    "company": "Presentr",
+    "context": "Interested in revenue intelligence and AI for GTM"
+  }'
 ```
 
-## Date-Constrained Search (last N days)
+**Response:**
+```json
+{
+  "status": "success",
+  "credits_used": 5,
+  "credits_remaining": 990,
+  "data": {
+    "content": "### 1. Profile\n**Name:** Leah Bonvissuto\n...",
+    "citations": ["https://x.com/..."],
+    "usage": {"prompt_tokens": 300, "completion_tokens": 1200}
+  }
+}
+```
 
-```python
-from xai_sdk.chat import user as xai_user
+---
 
-client = XAIClient()
-tools = client._get_tools()
+## Workflows
+
+### "Search X for tweets about a topic"
+1. Run bootstrap
+2. Search: `POST /x-search/search` with `{query, limit}`
+3. Display results: tweet text, author, engagement, links
+
+### "Find tweets from the last week about X"
+1. Run bootstrap
+2. Search with date filter: `POST /x-search/search` with `{query, limit, days_back: 7}`
+3. Display results sorted by engagement
+
+### "Research a person before a meeting"
+1. Run bootstrap
+2. Research: `POST /x-search/research-person` with `{name, handle, company, context}`
+3. Display profile, background, talking points
+
+### "Monitor keyword clusters for revenue intel"
+1. Run bootstrap
+2. Run multiple searches across keyword clusters:
+   - `"CRM is dead" OR "Salesforce is dead" OR "HubSpot sucks"`
+   - `"revenue operations" (broken OR frustrated OR replacing)`
+   - `(founder OR CEO) "tech stack" (consolidating OR ripping out)`
+3. Each search costs 5 credits
+4. Combine results, rank by engagement, draft replies
+
+### "Find viral tweets in my industry"
+1. Run bootstrap
+2. Search with engagement filter: `POST /x-search/search` with query including `min_faves:50`
+3. Display top tweets sorted by likes/retweets
 
-chat = client._get_client().chat.create(
-    model="grok-4-1-fast",
-    tools=[tools.x_search()],
-)
+---
 
-chat.append(xai_user(f"""Search X/Twitter for: "your query here"
+## Query Tips
 
-IMPORTANT: Only return tweets posted within the last 7 days.
-Return the 10 most relevant posts with:
-- Full tweet text (quoted exactly)
-- Author handle
-- Exact date/time
-- Engagement (likes, retweets, views)
+| Goal | Query Example |
+|------|--------------|
+| Specific phrase | `"revenue operations"` |
+| OR logic | `"CRM is dead" OR "Salesforce alternative"` |
+| From a user | `from:levelsio` |
+| High engagement | `"AI agents" min_faves:50` |
+| Exclude retweets | `"your query" -is:retweet` |
+| Multiple keywords | `(founder OR CEO) ("AI adoption" OR "AI native")` |
 
-Prioritize posts with high engagement (likes > 5, views > 1000)."""))
+---
 
-content = ""
-for response, chunk in chat.stream():
-    if chunk.content:
-        content += chunk.content
-print(content)
-```
+## Billing
 
-## Revenue Intel Digest (multi-cluster)
+- Every search costs **5 credits** (flat)
+- 1 credit = $0.01, so 1 search = $0.05
+- Research person also costs 5 credits
+- Credits are deducted server-side before the search runs
+- If insufficient credits, returns `402 Insufficient credits`
 
-```python
-from atris.team.gtm.skills.revenue_intel import run_digest, format_for_slack
+---
 
-# Runs 5 keyword clusters, drafts replies for top 5 items
-# Cost: 5 credits per cluster = 25 credits total
-result = await run_digest(
-    days_back=1,
-    user_id=USER_ID,
-    draft_count=5,
-)
+## Error Handling
 
-print(result["digest"])      # Ranked results by cluster
-print(result["drafts"])      # Reply options A/B per item
-print(result["credits_used"])
+| Error | Meaning | Solution |
+|-------|---------|----------|
+| `401 Not authenticated` | Invalid/expired token | Run `atris login` |
+| `402 Insufficient credits` | Not enough credits | Purchase credits at atris.ai |
+| `502 Search failed` | xAI API issue | Retry in a few seconds |
 
-# Format for Slack delivery
-slack_msg = await format_for_slack(result)
-```
+---
 
-## Custom Keyword Clusters
+## Quick Reference
 
-```python
-my_clusters = {
-    "competitors": '"Competitor Name" (review OR complaint OR switching OR alternative)',
-    "industry_pain": '"your industry" (frustrated OR broken OR replacing OR ripping out)',
-    "thought_leaders": '(founder OR CEO OR CTO) ("your topic" OR "related topic") min_faves:10',
-}
+```bash
+# Setup (one time)
+npm install -g atris && atris login
 
-result = await run_digest(clusters=my_clusters, user_id=USER_ID, days_back=7)
-```
+# Get token
+TOKEN=$(node -e "console.log(require('$HOME/.atris/credentials.json').token)")
 
-## Billing
+# Search tweets
+curl -s -X POST "https://api.atris.ai/api/x-search/search" \
+  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
+  -d '{"query": "AI agents", "limit": 10}'
 
-1. Every xAI action costs **5 credits** (flat)
-2. 1 credit = $0.01, so 1 search = $0.05
-3. `bill_xai_action(user_id, action_name)` checks balance and deducts before the call
-4. Returns `{"ok": False, "error": "Insufficient credits"}` if balance < 5
-5. Transaction logged as `txn_type="xai_action"` in `credit_transactions`
-
-| Plan | Monthly Credits | Searches/Month |
-|------|----------------|----------------|
-| Free | 50 | 10 |
-| Pro ($20/mo) | 1,000 | 200 |
-| Max ($200/mo) | unlimited | unlimited |
-| Credit pack ($10) | 1,000 | 200 |
-
-## Cost Breakdown
-
-| Component | Cost to us | What it does |
-|-----------|-----------|--------------|
-| xAI x_search tool | $0.005/call | Searches X, returns batch of tweets |
-| grok-4-1-fast tokens | ~$0.003/call | Processes and formats results |
-| Total per search | ~$0.008 | Raw cost |
-| We charge | $0.05 (5 credits) | 84% margin |
-
-## Key Files
-
-| File | What |
-|------|------|
-| `backend/clients/xai.py` | XAIClient + bill_xai_action() |
-| `atris/team/gtm/skills/revenue_intel.py` | Multi-cluster digest pipeline |
-| `backend/tools/core/reply_guy_tool.py` | Reply generation tool (bills 5 credits) |
-| `backend/tools/integrations/research_tweet_tool.py` | Research + tweet tool (bills 5 credits) |
-
-## Rules
-
-1. Always bill before searching — never search without `bill_xai_action()`
-2. Date filtering is prompt-based, not API-level — include explicit date cutoff in prompt
-3. Use `min_faves:N` in queries to filter low-engagement noise
-4. Never auto-post tweets — always require user approval
-5. Internal usage (no user_id) skips billing — platform absorbs cost
+# Search last 7 days only
+curl -s -X POST "https://api.atris.ai/api/x-search/search" \
+  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
+  -d '{"query": "AI agents", "limit": 10, "days_back": 7}'
+
+# Research a person
+curl -s -X POST "https://api.atris.ai/api/x-search/research-person" \
+  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
+  -d '{"name": "John Doe", "handle": "johndoe", "company": "Acme"}'
+```

package/atris/team/_template/MEMBER.md

@@ -0,0 +1,16 @@
+---
+name: template-member
+role: Replace with role title
+description: Replace with one-line description of what this member does.
+version: 1.0.0
+
+skills: []
+
+permissions:
+  can-read: true
+  approval-required: []
+
+tools: []
+---
+
+# Insert persona, workflow, and rules below

package/atris/team/brainstormer/MEMBER.md

@@ -4,13 +4,18 @@ role: Idea Shaper
 description: Shape ideas, explore possibilities, adapt to user depth
 version: 1.0.0
 
-skills: []
+skills:
+  - idea-shaping
+  - reality-mapping
 
 permissions:
   can-read: true
   can-plan: false
   can-execute: false
   can-approve: false
+  approval-required: []
+
+tools: []
 ---
 
 # Brainstormer — Idea & Reality Shaper

package/atris/team/executor/MEMBER.md

@@ -4,13 +4,18 @@ role: Builder
 description: Execute from build specs, one step at a time
 version: 1.0.0
 
-skills: []
+skills:
+  - code-writer
+  - test-runner
 
 permissions:
   can-read: true
   can-plan: false
   can-execute: true
   can-approve: false
+  approval-required: [delete, refactor-outside-scope]
+
+tools: []
 ---
 
 # Executor — Builder

package/atris/team/launcher/MEMBER.md

@@ -4,7 +4,9 @@ role: Closer
 description: Document, capture learnings, publish, celebrate
 version: 1.0.0
 
-skills: []
+skills:
+  - doc-writer
+  - publish-helper
 
 permissions:
   can-read: true
@@ -12,6 +14,9 @@ permissions:
   can-execute: false
   can-approve: false
   can-ship: true
+  approval-required: []
+
+tools: []
 ---
 
 # Launcher — The Closer

package/atris/team/navigator/MEMBER.md

@@ -4,13 +4,18 @@ role: Planner
 description: Transform messy human intent into precise execution plans
 version: 1.0.0
 
-skills: []
+skills:
+  - codebase-scout
+  - feature-spec
 
 permissions:
   can-read: true
   can-plan: true
   can-execute: false
   can-approve: false
+  approval-required: []
+
+tools: []
 ---
 
 # Navigator — Planner

package/atris/team/researcher/MEMBER.md

@@ -4,13 +4,18 @@ role: Deep Researcher
 description: Find ground truth on any topic — competitors, standards, technologies, markets
 version: 1.0.0
 
-skills: []
+skills:
+  - deep-search
+  - source-verification
 
 permissions:
   can-read: true
   can-execute: false
   can-plan: false
   can-approve: false
+  approval-required: []
+
+tools: []
 ---
 
 # Researcher — Deep Researcher

package/atris/team/validator/MEMBER.md

@@ -4,7 +4,9 @@ role: Reviewer
 description: Validate execution, run tests, ensure quality before shipping
 version: 1.0.0
 
-skills: []
+skills:
+  - test-runner
+  - doc-updater
 
 permissions:
   can-read: true
@@ -12,6 +14,9 @@ permissions:
   can-execute: false
   can-approve: true
   can-ship: true
+  approval-required: []
+
+tools: []
 ---
 
 # Validator — Reviewer

package/commands/init.js

@@ -475,24 +475,53 @@ function initAtris() {
   });
 
 
-  // Copy team members (MEMBER.md format — directory per member)
-  const members = ['navigator', 'executor', 'validator', 'launcher', 'brainstormer'];
+  // Copy team members (MEMBER.md format — directory per member with skills/tools/context)
+  const members = ['navigator', 'executor', 'validator', 'launcher', 'brainstormer', 'researcher'];
   members.forEach(name => {
     const sourceFile = path.join(__dirname, '..', 'atris', 'team', name, 'MEMBER.md');
-    const targetDir = path.join(teamDir, name);
-    const targetFile = path.join(targetDir, 'MEMBER.md');
+    const targetMemberDir = path.join(teamDir, name);
+    const targetFile = path.join(targetMemberDir, 'MEMBER.md');
     const legacyFile = path.join(teamDir, `${name}.md`);
 
     // Skip if already exists (either format)
     if (fs.existsSync(targetFile) || fs.existsSync(legacyFile)) return;
 
     if (fs.existsSync(sourceFile)) {
-      fs.mkdirSync(targetDir, { recursive: true });
+      fs.mkdirSync(targetMemberDir, { recursive: true });
+      fs.mkdirSync(path.join(targetMemberDir, 'skills'), { recursive: true });
+      fs.mkdirSync(path.join(targetMemberDir, 'tools'), { recursive: true });
+      fs.mkdirSync(path.join(targetMemberDir, 'context'), { recursive: true });
       fs.copyFileSync(sourceFile, targetFile);
-      console.log(`✓ Created team/${name}/MEMBER.md`);
+      console.log(`✓ Created team/${name}/ (MEMBER.md + skills/ + tools/ + context/)`);
     }
   });
 
+  // Copy MEMBER.md template for creating custom members
+  const templateSourceDir = path.join(__dirname, '..', 'atris', 'team', '_template');
+  const templateTargetDir = path.join(teamDir, '_template');
+  if (!fs.existsSync(templateTargetDir)) {
+    fs.mkdirSync(templateTargetDir, { recursive: true });
+    const templateContent = `---
+name: template-member
+role: Replace with role title
+description: Replace with one-line description of what this member does.
+version: 1.0.0
+
+skills: []
+
+permissions:
+  can-read: true
+  approval-required: []
+
+tools: []
+---
+
+# Insert persona, workflow, and rules below
+`;
+    fs.writeFileSync(path.join(templateTargetDir, 'MEMBER.md'), templateContent);
+    console.log('✓ Created team/_template/MEMBER.md');
+  }
+
   // Detect project context and generate profile
   const profile = detectProjectContext(process.cwd());
   const profileFile = path.join(targetDir, '.project-profile.json');

package/commands/member.js

@@ -233,6 +233,9 @@ skills: []
 
 permissions:
   can-read: true
+  approval-required: []
+
+tools: []
 ---
 
 # ${role}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "atris",
-  "version": "2.3.7",
+  "version": "2.4.0",
   "description": "atrisDev (atris dev) - CLI for AI coding agents. Works with Claude Code, Cursor, Windsurf. Make any codebase AI-navigable.",
   "main": "bin/atris.js",
   "bin": {