Session Handoff [auto-1826]: Say the Hub Commits the Audit Report Wherever Done-Means-Audited Is Stated per #1826 #2407

Next steps, in priority order

1. Fix Say the Hub Commits the Report Wherever Done-Means-Audited Is Stated #1826: reword every passage that names the audited repository as the holder of its committed reports/<repo>/audit.md, so each says the hub commits that report under its own reports/, matching AUDIT.md section 8 and the Fleet Bootstrap. The issue names GOVERNANCE.md "Repository Onboarding and Conformance" ("Definition of done is the audit"), AUDIT.md section 1, STANDUP.md section 5, the standup-a-repo skill, and the "its own audit report" wording in docs/reusable-workflows.md and TODO.md. Re-derive the live set with a search for carries a committed, reports/<repo>/audit.md, and its own audit report before editing, and leave alone any passage that already names the hub, such as the audit-a-repo skill writing the report from a hub checkout. Edit skill text only under .agents/skills/ and regenerate the distributions with scripts/build_dist.py, per skill-lifecycle. Done looks like: no passage reads as telling an audited repository to write or carry its own report, the prose gate, spec/validate.py, and build_dist.py --check pass, and the local strict review is clean.
2. Drive the pull request into develop with Closes on promotion: #1826 in its body, scope develop.

External blockers

None known.

Internal dependencies

None.

State

No branch or worktree yet. Base the work on develop, per repo-worktree. Re-derive open pull requests touching AUDIT.md, GOVERNANCE.md, STANDUP.md, or the standup-a-repo skill before starting.

The parked decision queue

None for this lane.

What the last round did

Nothing yet. The unattended picker created this lane from the open backlog.

What not to repeat

Nothing yet. Keep each rewrite to naming who commits the report. Adding a justifying clause to a carried passage is where review findings concentrate.

New learnings

None yet.