run-bridgelisted

# Run & verify the bridge Use this to actually run the project and observe its output — the core of verifying your own work. Do not claim a change works at runtime without doing this. Throughout, **"the bridge"** means the local Slack-Claude Bridge process (`npm run dev`), never the AI assistant. ## 1. Preconditions ```bash test -f .env || echo "MISSING .env — copy .env.example and ask the user to fill credentials" npm install # if node_modules is absent ``` The bridge needs valid `SLACK_BOT_TOKEN`, `SLACK_APP_TOKEN`, `SLACK_SIGNING_SECRET` in `.env`. If they are missing, you cannot fully verify Slack behavior — say so explicitly. ## 2. Static gate first ```bash npm run verify # typecheck + lint + test ``` Fix failures before running. There is no point booting code that doesn't compile. ## 3. Start the bridge ```bash mkdir -p logs npm run dev # tsx watch; hot-reloads on change # or, for a built artifact: npm run build && npm start ``` Run it in the background (or a separate shell) so you can inspect logs while it runs. ## 4. Observe output — what "working" looks like Tail the log and confirm the expected sequence: ```bash npm run bridge:logs # tail -f logs/bridge.log ``` Look for, in order: - Slack Socket Mode connection established. - Event received for a mapped channel/thread. - Workspace routed (correct directory for the mapping). - Claude Code invoked inside that workspace. - Response posted back to the correct location (chann