v2: channel isolation model, manage-channels skill, refactored channel skills

- Add three-level isolation model (shared session, same agent, separate agent)
  with agent-shared session mode for cross-channel shared sessions
- Create /manage-channels skill for wiring channels to agent groups
- Refactor all 12 v2 channel skills: lean SKILL.md + VERIFY.md + REMOVE.md
  with structured Channel Info section for platform-specific metadata
- Create /add-discord-v2 skill (was missing)
- Add step 5a to setup SKILL.md invoking /manage-channels after channel install
- Update setup/verify.ts to check all 12 channel token types
- Add docs/v2-isolation-model.md explaining the isolation model
- Update v2-checklist.md and v2-setup-wiring.md to reflect completed work

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.claude/skills/add-linear-v2/REMOVE.md

@@ -0,0 +1,6 @@
+# Remove Linear Channel
+
+1. Comment out `import './linear.js'` in `src/channels/index.ts`
+2. Remove `LINEAR_API_KEY` and `LINEAR_WEBHOOK_SECRET` from `.env`
+3. `npm uninstall @chat-adapter/linear`
+4. Rebuild and restart

.claude/skills/add-linear-v2/SKILL.md

@@ -3,39 +3,31 @@ name: add-linear-v2
 description: Add Linear channel integration to NanoClaw v2 via Chat SDK. Issue comment threads as conversations.
 ---
 
-# Add Linear Channel (v2)
+# Add Linear Channel
 
-This skill adds Linear support to NanoClaw v2 using the Chat SDK bridge. The agent can participate in issue comment threads.
+Adds Linear support to NanoClaw v2 using the Chat SDK bridge. The agent participates in issue comment threads.
 
-## Phase 1: Pre-flight
+## Pre-flight
 
-Check if `src/channels/linear.ts` exists and the import is uncommented in `src/channels/index.ts`. If both are in place, skip to Phase 3.
+Check if `src/channels/linear.ts` exists and the import is uncommented in `src/channels/index.ts`. If both are in place, skip to Credentials.
 
-## Phase 2: Apply Code Changes
-
-### Install the adapter package
+## Install
 
 ```bash
 npm install @chat-adapter/linear
 ```
 
-### Enable the channel
-
 Uncomment the Linear import in `src/channels/index.ts`:
 
 ```typescript
 import './linear.js';
 ```
 
-### Build
-
 ```bash
 npm run build
 ```
 
-## Phase 3: Setup
-
-### Create Linear credentials
+## Credentials
 
 > 1. Go to [Linear Settings > API](https://linear.app/settings/api)
 > 2. Create a **Personal API Key** (or use an OAuth application for team-wide access)
@@ -57,21 +49,17 @@ LINEAR_WEBHOOK_SECRET=your-webhook-secret
 
 Sync to container: `mkdir -p data/env && cp .env data/env/env`
 
-### Build and restart
+## Next Steps
 
-```bash
-npm run build
-launchctl kickstart -k gui/$(id -u)/com.nanoclaw  # macOS
-# systemctl --user restart nanoclaw  # Linux
-```
+If you're in the middle of `/setup`, return to the setup flow now.
 
-## Phase 4: Verify
+Otherwise, run `/manage-channels` to wire this channel to an agent group.
 
-> @mention the bot in a Linear issue comment. The bot should respond within a few seconds.
+## Channel Info
 
-## Removal
-
-1. Comment out `import './linear.js'` in `src/channels/index.ts`
-2. Remove `LINEAR_API_KEY` and `LINEAR_WEBHOOK_SECRET` from `.env`
-3. `npm uninstall @chat-adapter/linear`
-4. Rebuild and restart
+- **type**: `linear`
+- **terminology**: Linear has "teams" containing "issues." Each issue's comment thread is a separate conversation.
+- **how-to-find-id**: The platform ID is your team key (e.g. `ENG`). Find it in Linear under Settings > Teams. Each issue becomes its own thread automatically.
+- **supports-threads**: yes (issue comment threads are native conversations)
+- **typical-use**: Webhook/notification — the agent receives issue comment events and responds in threads
+- **default-isolation**: Typically shares a session with a chat channel (e.g. Slack) so the agent can discuss issues in the same context as team chat. Use a separate agent group if the Linear team tracks sensitive work.

.claude/skills/add-linear-v2/VERIFY.md

@@ -0,0 +1,3 @@
+# Verify Linear Channel
+
+@mention the bot in a Linear issue comment. The bot should respond within a few seconds.