Reports out of the workplan number space

The workplan list read as though GROUND-WP-0002, 0003 and 0005 each
existed twice. They did not: three inbound clay-borg finding reports were
filed in workplans/ borrowing the number of the workplan they bear on, and
each was registered in State Hub as a workplan.

A report is correspondence, not a unit of work. The three move to
reports/YYMMDD-<slug>.md with their own id space (GROUND-RPT-0001..0003),
keeping type: report, status: informational and the extends: link to the
workplan they relate to. Their state_hub_workstream_id bindings are
dropped and the hub registrations archived, so the hub's workplan list
matches the files.

Five workplans, one file per number.

AGENTS.md records the convention, since the reports arrive regularly and
nothing in the repo said where they go.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

AGENTS.md

@@ -130,6 +130,18 @@ read/cache/index layer that rebuilds from files.
 `workplans/archived/YYMMDD-GROUND-WP-NNNN-<slug>.md`. The `YYMMDD` prefix is
 the completion/archive date; the frontmatter `id` does not change.
 
+**Reports are not workplans.** An inbound finding report — clay-borg
+measured something and told us — is correspondence, not a unit of work. It
+lives in `reports/YYMMDD-<slug>.md` with its own id space
+(`GROUND-RPT-NNNN`), `type: report`, `status: informational`, and
+`extends: GROUND-WP-NNNN` naming the workplan it bears on.
+
+**It is not registered in State Hub as a workplan** and carries no
+`state_hub_workstream_id`. Three of them were, which put two files in the
+`GROUND-WP-0002/0003/0005` slots each and made the workplan list read as
+though it had duplicates. The workplan number space has one file per
+number; a report borrowing that number is what caused the confusion.
+
 **Ad Hoc Tasks:** small opportunistic fixes discovered during a session use
 `workplans/ADHOC-YYYY-MM-DD.md` with task ids `ADHOC-YYYY-MM-DD-T01`, etc. Use
 this only for low-risk work completed directly; create a normal workplan for

WORK-RECORDS.md

@@ -11,6 +11,7 @@
 | workplan | GROUND-WP-0001 | done | — | workplans/GROUND-WP-0001-statehub-bootstrap.md |
 | workplan | GROUND-WP-0002-REPORT-260805 | informational | — | workplans/GROUND-WP-0002-clay-borg-report-260805.md |
 | workplan | GROUND-WP-0002 | finished | — | workplans/GROUND-WP-0002-rulings-clay-borg-is-blocked-on.md |
+| workplan | GROUND-WP-0003-REPORT-260807 | informational | — | workplans/GROUND-WP-0003-clay-borg-attack-and-modes-260807.md |
 | workplan | GROUND-WP-0003 | ready | — | workplans/GROUND-WP-0003-playtest-semi-and-coalitions.md |
 | workplan | GROUND-WP-0004 | finished | — | workplans/GROUND-WP-0004-the-threshold-ruling-rests-on-a-bad-premise.md |
 | workplan | GROUND-WP-0005-REPORT-260805 | informational | — | workplans/GROUND-WP-0005-clay-borg-difficulty-260805.md |

reports/260805-clay-borg-difficulty.md

@@ -1,5 +1,5 @@
 ---
-id: GROUND-WP-0005-REPORT-260805
+id: GROUND-RPT-0002
 type: report
 title: "clay-borg difficulty measurement, 2026-08-05 — and a retraction of what we nearly sent instead"
 domain: consumer
@@ -9,7 +9,6 @@ owner: bernd
 topic_slug: whynot
 created: "2026-08-05"
 extends: GROUND-WP-0005
-state_hub_workstream_id: "61cabf31-88a8-4ca6-9383-55b8fccddecf"
 ---
 
 # clay-borg difficulty report — 2026-08-05

reports/260805-clay-borg-findings.md

@@ -1,5 +1,5 @@
 ---
-id: GROUND-WP-0002-REPORT-260805
+id: GROUND-RPT-0001
 type: report
 title: "clay-borg finding report, 2026-08-05 — one withdrawal, and ten rulings we had not collected"
 domain: consumer
@@ -9,7 +9,6 @@ owner: bernd
 topic_slug: whynot
 created: "2026-08-05"
 extends: GROUND-WP-0002
-state_hub_workstream_id: "09350395-f628-4d8e-8c36-3cea330a8b6f"
 ---
 
 # clay-borg finding report — 2026-08-05

reports/260807-clay-borg-attack-and-modes.md

@@ -1,5 +1,5 @@
 ---
-id: GROUND-WP-0003-REPORT-260807
+id: GROUND-RPT-0003
 type: report
 title: "clay-borg: GR-E03 and GR-E04 played to the end, and what ATTACK is worth in each"
 domain: consumer