You describe what you need
  --> Terminal reads source files
  --> Terminal calls forge_propose_tools
  --> You review and modify the proposal
  --> Terminal calls forge_generate_tools
  --> Terminal calls compose to merge everything
  --> Done: deployable agent

> Read my source code in src/monitoring/ and propose tools for a monitoring agent.

I found 8 exported functions across 3 files. Here are the proposed tools:

  1. check_service_health    — Ping a service endpoint and return status
  2. list_active_alerts      — Query all unresolved alerts
  3. acknowledge_alert       — Mark an alert as acknowledged
  4. get_alert_history       — Fetch alert history for a monitor
  5. create_maintenance_window — Schedule a maintenance window
  6. list_monitors           — List all configured monitors
  7. enable_monitor          — Enable a disabled monitor
  8. disable_monitor         — Disable a monitor temporarily

Should I generate tools for all of these, or would you like to modify the list?

> Remove create_maintenance_window and get_alert_history.
> Rename check_service_health to ping_service.
> Add a tool called escalate_alert that creates a PagerDuty incident from an alert.

> Now generate those tools.

Generated 7 tools in ./tools/:
  - monitoring.tool-spec.yaml
  - monitoring.capabilities.ts

The escalate_alert tool calls PagerDuty's incident creation API.
All other tools delegate to your existing functions in src/monitoring/.

> Combine the monitoring and slack tools into a single agent called ops-bot.

Composed ops-bot with 10 tools from 2 domains:

  monitoring: ping_service, list_active_alerts, acknowledge_alert,
              escalate_alert, list_monitors, enable_monitor, disable_monitor
  slack:      send_message, send_alert_card, list_channels

Generated standalone project in ./ops-bot/:
  - server.ts
  - .env.template
  - package.json
  - Dockerfile
  - tsconfig.json
  - capabilities/monitoring.ts
  - capabilities/slack.ts

> Actually, add a schedule trigger that checks all monitors every 5 minutes.

Added schedule trigger "check_all_monitors" with cron "*/5 * * * *" to the monitoring spec.
Regenerated ops-bot with the new trigger wired in server.ts.