Pre-action authority receipts for Claude Code multi-agent teams

[rpelevin]

Hi maintainers/users - I am testing an authority-before-action receipt pattern for multi-agent Claude Code teams and delegated coding workflows.

The narrow question is: when one agent delegates work or moves a task toward execution, can the workflow prove who had authority, what exact action was authorized, what evidence/policy applied, and where the runtime must stop or ask for review?

I put a credential-free dry-run benchmark here:

https://github.com/neurarelay/relay-action-card

For this repo, the closest starting path is:

npm run benchmark:agent-authority -- --dry-run --json --source=github_discussion --campaign=agent_authority_week --surface=oh_my_claudecode_multi_agent_authority

This is not an oh-my-claudecode approval, endorsement, integration, partnership, listing, pass, or fail claim. It is a proposed authority-before-action boundary for multi-agent coding workflows.

Question for maintainers/users here: is a pre-action authority receipt useful for multi-agent Claude Code workflows, or would the better insertion point be somewhere else in the execution lifecycle?