
GitHub Copilot cloud agent
The six pillars
Each bar is the score; the bracket is its 95% range.
Can you see what it costs?
Can you see how much it's used?
Can you tie cost to one agent?
Can an agent on it report out?
Can you control spend and access?
Does it work on small plans?
Where the evidence comes from
Once three independent fleets report on a pillar, desk research counts for at most a third of it. FleetRegistry's own fleets never count.
Controls on record
Price changes: ToS: price increases notified at least 30 days before taking effect, applied at end of payment term
Budgets per enterprise, org, cost center or user (incl. bundled AI credit budgets with universal, cost-center and individual user overrides) can 'stop usage when budget limit is reached' (default only alerts/emails); fine-grained PATs are listed and revoked via org REST endpoints and GitHub Apps are scoped; enterprise audit log streams to S3, Azure, Datadog, GCS, Splunk and Purview (Copilot agent session events) with an Audit log API. SAML/OIDC+SCIM via Enterprise Managed Users on Enterprise Cloud; individual Copilot plans lack org controls.
History
Run agents on GitHub Copilot cloud agent?
Give each one a permanent number, a named person who answers for it, and a record of what it can touch and what it costs. Free.