diff --git a/docs/pr-discussions/PR-3694-fix-b-0545-adopt-b-0498-collision-renumber.md b/docs/pr-discussions/PR-3694-fix-b-0545-adopt-b-0498-collision-renumber.md
new file mode 100644
index 000000000..3ca9f4239
--- /dev/null
+++ b/docs/pr-discussions/PR-3694-fix-b-0545-adopt-b-0498-collision-renumber.md
@@ -0,0 +1,99 @@
+---
+pr_number: 3694
+title: "fix(b-0545): adopt B-0498 collision renumber"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-16T02:53:21Z"
+merged_at: "2026-05-16T02:55:42Z"
+closed_at: "2026-05-16T02:55:42Z"
+head_ref: "codex/b0545-b0498-renumber-adopt-20260516"
+base_ref: "main"
+archived_at: "2026-05-16T03:14:35Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #3694: fix(b-0545): adopt B-0498 collision renumber
+
+## PR description
+
+## Summary
+
+- adopts the existing Otto B-0498 collision-renumber fix onto current main without rewriting Otto's branch
+- renumbers the Riven cursor-terminal backlog row to B-0549 and preserves breadcrumbs
+- regenerates docs/BACKLOG.md so the generated index matches the row rename
+
+## Verification
+
+- git diff --check
+- bun tools/hygiene/audit-backlog-items.ts --enforce-duplicate-ids
+- bun tools/backlog/generate-index.ts --check
+
+## Coordination
+
+This unblocks PR #3674's factory-wide duplicate-ID gate once merged.
+
+## Reviews
+
+### COMMENTED — @copilot-pull-request-reviewer (2026-05-16T02:55:55Z)
+
+## Pull request overview
+
+Adopts the existing duplicate backlog ID collision fix by renumbering the Riven cursor-terminal backlog row from **B-0498 → B-0549**, updating cross-references, and regenerating the generated backlog index so it matches the per-row files.
+
+**Changes:**
+- Updated the Riven cursor-terminal research design doc to reference **B-0549** (with renumber breadcrumb).
+- Updated backlog row files to reflect the renumber (frontmatter + breadcrumbs) and updated the collision-sweep row to point at the new ID.
+- Regenerated `docs/BACKLOG.md` to drop the old B-0498 entry and add B-0549.
+
+### Reviewed changes
+
+Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.
+
+| File | Description |
+| ---- | ----------- |
+| docs/research/2026-05-15-riven-cursor-terminal-loop-design.md | Updates the referenced backlog ID to B-0549 with renumber context. |
+| docs/backlog/P2/B-0545-b0498-collision-renumber-sweep-2026-05-15.md | Records the collision/renumber sweep and links to the new B-0549 row. |
+| docs/backlog/P1/B-0549-riven-cursor-terminal-background-loop-ide-native-autonomous-gate-2026-05-15.md | Renumbers the row to B-0549 and adds `renumbered_from` / `renumbered_per` breadcrumbs. |
+| docs/BACKLOG.md | Regenerates the index to reflect the renumbered row. |
+
+
+
+Comments suppressed due to low confidence (2)
+
+**docs/backlog/P2/B-0545-b0498-collision-renumber-sweep-2026-05-15.md:10**
+* Per `tools/backlog/README.md` the `last_updated` frontmatter field is required and must be updated on every content edit. This row's frontmatter is missing `last_updated` entirely; add it (likely `2026-05-16` given this edit).
+```
+status: done
+created: 2026-05-15
+completed: 2026-05-16
+filed_by: otto-cli
+completed_by: otto-cli
+```
+**docs/backlog/P2/B-0545-b0498-collision-renumber-sweep-2026-05-15.md:96**
+* This new “Resolution” section states the renumber target is B-0549, but earlier in the same document the “Next free ID” / “Sweep scope” sections still describe renumbering to B-0546. Please update those earlier sections (or explicitly label them as historical/estimates) to avoid leaving contradictory guidance in a single row file.
+```
+## Resolution (2026-05-16)
+
+Renumber executed in this same PR:
+
+- Renamed `docs/backlog/P1/B-0498-riven-cursor-terminal-*-2026-05-15.md` → `docs/backlog/P1/B-0549-riven-cursor-terminal-*-2026-05-15.md`
+```
+
+
+## Review threads
+
+### Thread 1: docs/backlog/P2/B-0545-b0498-collision-renumber-sweep-2026-05-15.md:6 (unresolved)
+
+**@copilot-pull-request-reviewer** (2026-05-16T02:55:55Z):
+
+`status: done` is not a valid backlog-row status (schema allows `open`/`closed`/`superseded-by-*`/`deferred`/`decomposed`). It will also render as unchecked in the generated `docs/BACKLOG.md` because the generator only treats `closed`/`superseded-by-*` as closed. Use `status: closed` here if the intention is to mark B-0545 complete.
+
+This issue also appears in the following locations of the same file:
+- line 6
+- line 92
+
+## General comments
+
+### @chatgpt-codex-connector (2026-05-16T02:53:24Z)
+
+You have reached your Codex usage limits for code reviews. You can see your limits in the [Codex usage dashboard](https://chatgpt.com/codex/cloud/settings/usage).
diff --git a/docs/pr-discussions/PR-3695-shard-tick-2026-05-16t02-52z-audit-filter-triage-17-10-basel.md b/docs/pr-discussions/PR-3695-shard-tick-2026-05-16t02-52z-audit-filter-triage-17-10-basel.md
new file mode 100644
index 000000000..6987fcd2f
--- /dev/null
+++ b/docs/pr-discussions/PR-3695-shard-tick-2026-05-16t02-52z-audit-filter-triage-17-10-basel.md
@@ -0,0 +1,58 @@
+---
+pr_number: 3695
+title: "shard(tick): 2026-05-16T02:52Z \u2014 audit filter triage (17\u219210) + baseline-cleanup question"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-16T02:54:23Z"
+merged_at: "2026-05-16T03:02:45Z"
+closed_at: "2026-05-16T03:02:45Z"
+head_ref: "shard/tick-0252z-otto-cli-2026-05-16"
+base_ref: "main"
+archived_at: "2026-05-16T03:14:34Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #3695: shard(tick): 2026-05-16T02:52Z — audit filter triage (17→10) + baseline-cleanup question
+
+## PR description
+
+Tick 8 substantive landing: filter improvement on PR #3692's audit script (`isPlaceholderTarget` skips ellipsis/paren/identifier placeholders), reducing baseline 17 → 10 findings. The 10 remaining are real wrong-depth `..` bugs in 2 shards.
+
+Open question for next tick: tick-shard immutability discipline strict vs pragmatic — can the 10 be edited in-place (treat as bug-fix), or do they need a grandfather mechanism (Stryker-baseline-style)?
+
+GraphQL rate-limit still 0; resets 02:55:28Z. 3 PRs queued un-armed: #3690 #3692 #3693.
+
+Co-Authored-By: Claude
+
+## Reviews
+
+### COMMENTED — @copilot-pull-request-reviewer (2026-05-16T02:56:42Z)
+
+## Pull request overview
+
+This PR adds a new tick shard documenting the 02:52Z audit-filter triage work, including the PR #3692 placeholder-target filter improvement and the remaining baseline-cleanup decision.
+
+**Changes:**
+- Records the 17→10 audit finding reduction after placeholder filtering.
+- Documents the open strategy question for tick-shard relative-path baseline cleanup.
+- Captures current PR queue state and next-tick candidates.
+
+## Review threads
+
+### Thread 1: docs/hygiene-history/ticks/2026/05/16/0252Z.md:4 (resolved)
+
+**@copilot-pull-request-reviewer** (2026-05-16T02:56:42Z):
+
+P1: This new shard links to `0249Z.md`, but that file is not present in `docs/hygiene-history/ticks/2026/05/16/` on this branch, so the parent-tick link will be broken if this PR lands before or without the separate 0249Z shard PR.
+
+### Thread 2: docs/hygiene-history/ticks/2026/05/16/0252Z.md:96 (resolved)
+
+**@copilot-pull-request-reviewer** (2026-05-16T02:56:42Z):
+
+P1: The next-tick guidance computes the B-0545 claim expiry as roughly one hour after a 01:44Z claim, but the claim rule says bus claim envelopes have a 24h TTL by default. This would send the next tick to treat an active claim as expired about 23 hours too early, risking duplicate work on the same backlog row.
+
+### Thread 3: docs/hygiene-history/ticks/2026/05/16/0252Z.md:53 (resolved)
+
+**@copilot-pull-request-reviewer** (2026-05-16T02:56:42Z):
+
+P1: This cites an `ID allocation discipline` section in `.claude/rules/claim-acquire-before-worktree-work.md`, but that section does not exist in the rule, and the searched rule text does not contain the referenced tick-shard immutability language. The open decision is therefore grounded on an unverifiable cross-reference.
diff --git a/docs/pr-discussions/PR-3697-shard-tick-2026-05-16t02-58z-graphql-reset-arm-wave-8-thread.md b/docs/pr-discussions/PR-3697-shard-tick-2026-05-16t02-58z-graphql-reset-arm-wave-8-thread.md
new file mode 100644
index 000000000..e9b01ea39
--- /dev/null
+++ b/docs/pr-discussions/PR-3697-shard-tick-2026-05-16t02-58z-graphql-reset-arm-wave-8-thread.md
@@ -0,0 +1,75 @@
+---
+pr_number: 3697
+title: "shard(tick): 2026-05-16T02:58Z \u2014 GraphQL reset \u2192 arm wave + 8-thread cleanup"
+author: "AceHack"
+state: "MERGED"
+created_at: "2026-05-16T03:02:57Z"
+merged_at: "2026-05-16T03:04:32Z"
+closed_at: "2026-05-16T03:04:32Z"
+head_ref: "shard/tick-0258z-otto-cli-2026-05-16"
+base_ref: "main"
+archived_at: "2026-05-16T03:14:33Z"
+archive_tool: "tools/pr-preservation/archive-pr.ts"
+---
+
+# PR #3697: shard(tick): 2026-05-16T02:58Z — GraphQL reset → arm wave + 8-thread cleanup
+
+## PR description
+
+Tick 9 (post-GraphQL-reset). Arm wave on 4 queued PRs (#3693 already merged by AceHack 16s after reset; #3690 #3692 #3695 armed). 8 unresolved threads investigated:
+
+- #3690 (1): table-pipe complaint = Copilot false positive (verified by awk inspection). No-op resolve.
+- #3692 (4): ALL real (sonarjs disable, main+import.meta.main guard, generic URI scheme, --files validation). Fixed via commit d299c7d.
+- #3695 (3): 2 real prose errors fixed via commit e0828b5; 1 stale link self-resolved when sibling PR merged.
+
+Discipline reinforced: verify-before-fixing applies to Copilot reviewer output too (same table-pipe hallucination as #3685 from tick 6).
+
+Co-Authored-By: Claude
+
+## Reviews
+
+### COMMENTED — @copilot-pull-request-reviewer (2026-05-16T03:06:10Z)
+
+## Pull request overview
+
+Adds a new tick-history shard documenting the 2026-05-16T02:58Z autonomous-loop tick, focused on the post-GraphQL-reset auto-merge arming wave and cleanup of 8 previously-unresolved PR review threads.
+
+**Changes:**
+- Adds tick shard `0258Z.md` describing actions taken on PRs #3690/#3692/#3695 and recording outcomes.
+- Captures lessons learned about “verify before fixing” when handling reviewer feedback.
+- Records operational state (GraphQL budget, queue status) and next-tick candidates.
+
+
+
+Comments suppressed due to low confidence (1)
+
+**docs/hygiene-history/ticks/2026/05/16/0258Z.md:66**
+* P2 (documentation): Same table-format issue here: `||` creates an empty leading column. Prefer a single leading `|` so this renders as a 3-column table and stays consistent with the surrounding markdown-table style used in other shards.
+```
+| Step | Tick | Commit |
+|------|------|--------|
+| 1. Discovery (the bug class shipped in #3676 + #3679) | 3 | n/a |
+```
+
+
+## Review threads
+
+### Thread 1: docs/hygiene-history/ticks/2026/05/16/0258Z.md:3 (unresolved)
+
+**@copilot-pull-request-reviewer** (2026-05-16T03:06:10Z):
+
+P1 (codebase_conventions): This tick shard starts with an ATX heading, but the documented tick-shard schema requires the first non-empty line to be a 6-column `| ... |` row (docs/hygiene-history/ticks/README.md:53-57) and the validator `tools/hygiene/check-tick-history-shard-schema.ts` will flag this file as a violation. Consider prepending the canonical schema row as line 1 (hybrid pattern: schema row first, rich body below) so existing tooling can parse/collate shards reliably.
+
+### Thread 2: docs/hygiene-history/ticks/2026/05/16/0258Z.md:4 (unresolved)
+
+**@copilot-pull-request-reviewer** (2026-05-16T03:06:10Z):
+
+P1 (bug/xref): The parent-tick link points to `0252Z.md`, but there is no `docs/hygiene-history/ticks/2026/05/16/0252Z.md` in this PR/branch. If this PR merges before the parent shard PR, `Parent tick` becomes a broken relative link on `main`. Either include the parent shard in this PR or link to an already-present shard (or an immutable permalink) so the reference is valid at merge time.
+
+### Thread 3: docs/hygiene-history/ticks/2026/05/16/0258Z.md:12 (unresolved)
+
+**@copilot-pull-request-reviewer** (2026-05-16T03:06:10Z):
+
+P2 (documentation): These table rows start with `||`, which renders as an empty first column and is inconsistent with other tick shards’ tables (single leading `|`). Dropping the extra leading pipe will make the table render as the intended 3-column table and avoid confusion with the earlier “double-pipe table” discussion.
+
+This issue also appears on line 64 of the same file.