Authority receipts before Codex-side effects

[rpelevin]

Hi maintainers/users - I am testing an authority-before-action receipt pattern for coding agents that can change files, run commands, prepare releases, or move work toward deployment.

The narrow question is: before a coding agent crosses a consequential boundary, can the workflow produce a pre-action receipt with actor/runtime/tool/action/target refs, authority refs, policy/evidence refs, a decision route, and a developer-owned execution boundary?

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=openai_codex_coding_authority

This is not an OpenAI approval, endorsement, integration, partnership, listing, pass, or fail claim. It is a proposed boundary pattern for consequential coding-agent side effects.

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