Repository navigation
docs(agents): transparent agent-byline standard for public review artifacts - #420
Merged
Merged
Conversation
… artifacts Complements the no-AI-co-author-trailer rule with its positive-disclosure counterpart, prompted by an external review of the XenoComm vetting charge: public-facing agent work (issues, review docs, external reports) discloses authorship as the named agent persona under human-in-the-loop — 'Reviewed by <persona> — autonomous agent, human-in-the-loop' — naming the accountable persona while omitting the vendor/tool trailer. Agent provenance is disclosed, not concealed.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds the positive-disclosure complement to the existing "no AI co-author trailers" rule in
AGENTS.md.Prompted by: an external model review of the XenoComm external-vetting charge, which read the attribution rule as "review laundering." The premise was a misread — we attribute to named autonomous agents, which discloses AI authorship — but the constructive fix (a standardized, explicit provenance header) genuinely strengthens transparency.
The standard: public-facing agent work (issues, review docs, external vetting reports, substantive review PR bodies) carries
Reviewed by <Agent Persona> — autonomous agent, human-in-the-loop(two co-signers:Reviewed by <A> and <B> — independently authorized agents, human-in-the-loop). The accountable persona is named; the substrate (Claude Code / model / vendor) is not. Agent provenance is disclosed, not concealed.This is consistent with prior practice (e.g. the MCR issue byline "Reviewed by Chimera and Leibniz, two independently authorized agents") — it just makes the form canonical.