Automation library · Customer support

Assess GitHub bus-factor risk in GitHub with Claude and Slack

Started by another system calling it, and works across Slack. It hands the judgement calls to Claude. 22 steps, 1 branch: large, and worth reading before you trust it with anything live.

LargeCalls a model: Claude

22 stepsLarge: read it before trusting it with anything live
1Branch: places the flow splits
0Loops or waits
1Service it connects to

The flow

Starts it 4Model 2Logic 10Service 6

The steps in the order they run, from what starts it.

  1. 1On GitHub Push EventWebhookStarts it
  2. 2On Pull Request MergedWebhookStarts it
  3. 3Every Contributor Baseline ScanSchedule triggerStarts it
  4. 4Every Batch Processing WindowSchedule triggerStarts it
  5. 5Claude Bus-Factor ModelLm Chat AnthropicModel
  6. 6Normalize Push SignalCodeLogic
  7. 7Normalize Review SignalCodeLogic
  8. 8Fetch Org RepositoriesHttp RequestService
  9. 9Fetch Buffered Ownership SignalsHttp RequestService
  10. 10AI Bus-Factor Risk AgentAgentModel
  11. 11Merge Normalized Ownership SignalsMergeLogic
  12. 12Fetch Contributor StatsHttp RequestService
  13. 13Compute Bus-Factor Risk ScoresCodeLogic
  14. 14Apply AI Risk ResolutionCodeLogic
  15. 15Post Signal to Ownership BufferHttp RequestService
  16. 16Normalize Contributor SignalCodeLogic
  17. 17Check for Ambiguous ClustersIfLogic
  18. 18Merge Risk ResultsMergeLogic
  19. 19Pass Clear Risk ClustersCodeLogic
  20. 20Build Knowledge-Transfer TasksCodeLogic
  21. 21Post to Ticketing SystemHttp RequestService
  22. 22Send Slack NotificationSlackService

How it's built

Starts on
Another system calling it
Steps
22, with 1 branch
Size
Large: read it before trusting it with anything live
Connects to
Slack
Model
Claude

Questions

What does it need to run?

An n8n account, plus your own Slack account, and a key for Claude. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls Claude. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 22 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

Before you run it

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 22 steps before you point it at anything that matters.