cat-mode: allowlist intervention-must-automate as a flag token.

corpus/skills/cat-mode/SKILL.md

@@ -178,14 +178,17 @@ What happens to a number once it exists:
 - **Retractions cover the conversation, not just the artifacts.**
 - **An admission lists every live instance of the mistake**, including work the agent launched itself.
 - **A claim about the repo's own history is a query, not a recollection.**
-- **A blank or synthetic model on an analytics event is an emit bug.** Fix it at write or backfill — never hide it with a chart filter. [[principle-assert-invariants-not-last-bug]], [[principle-explicit-errors]].
-- **"Full backfill" means every emitter of the metric**, not the first harness that was easy. Same class as Harness-agnostic product defaults above.
+- **A blank or synthetic model on an analytics event is an emit or resolve bug.** Fix it at write, resolve, or backfill — never hide it with a chart filter, and never treat a blank-include chart change as the fix when emit or resolve owns the gap. Prove the live resolve path for that harness first. [[principle-assert-invariants-not-last-bug]], [[principle-explicit-errors]].
+- **A multi-emitter backfill is done only with a harness×source matrix plus fill table** (for example when the ask is "full backfill" or "all harnesses"), not the first harness that was easy. Same class as Harness-agnostic product defaults above.
+- **Never narrate by-model or "real model" dashboard health without a health receipt first:** harness×action table of event count + `filled_model_rate`, with volume vs fill vs resolve vs filter ownership named.
+- **Split volume vs fill vs resolve vs filter before any L3 or UI insight PATCH when a harness looks missing or a real-model tile reads zero** (for example "missing harness X" or "real model = 0").
 - **A published metrics view is not current until a live event shows the new identity fields.** Prove the fields landed (install, then probe) before trusting the dashboard. Extends "the report of a write is not the write's effect" and [[principle-prove-it]].
 - **Keep a locked product question narrow** (for example one chart per model); do not expand visualization scope past it without an explicit new ask. Follow `narrow-the-scope`.
 - **Climb analytics tiers in order:** L1 explain → L2 one canary query → L3 backfill/fleet only after the canary proves an identity or cardinality gap.
 - **Schema before UI.** Required identity properties plus a green canary before the first insight or notebook PATCH; split the forward-stamp PR from the historical-backfill PR.
 - **Claim a chart gap fixed only after naming write vs enrich ownership** (local vs peer vs fleet).
 - **Write a thrash checkpoint before attaching new scope:** after two same-type interventions or the first live backfill, record tier and canary status first.
+- **Stop analytics feature iteration and lock the class catch before more analytics PRs when automate is mandated mid thrash** (for example the first `intervention-must-automate` flag, an explicit `/automate-me`, or a same-type restatement).
 
 Each rule's full text: [references/verify.md](references/verify.md).
 

corpus/skills/cat-mode/references/verify.md

@@ -149,18 +149,37 @@ Standing defaults when publishing hook/skill analytics — identity fields,
 backfills, dashboards, and charts. Prefer fixing emit and coverage over
 chart workarounds.
 
-- **A blank or synthetic model on an analytics event is an emit bug.** Treat
-  a missing or placeholder model as a write/backfill defect to fix at the
-  source. Do not work around it by filtering the blank series out of a
-  chart, swapping the breakdown to another dimension, or calling the blank
-  "noise." The model field is an invariant of the event, not a display
-  preference. [[principle-assert-invariants-not-last-bug]],
+- **A blank or synthetic model on an analytics event is an emit or resolve
+  bug.** Treat a missing or placeholder model as a write, resolve, or
+  backfill defect to fix at the source. Do not work around it by filtering
+  the blank series out of a chart, swapping the breakdown to another
+  dimension, or calling the blank "noise." Do not treat a blank-include
+  chart change as the fix when emit or resolve owns the gap — prove the
+  live resolve path for that harness first (same-session peers from local
+  metrics when the payload omits the model). The model field is an
+  invariant of the event, not a display preference.
+  [[principle-assert-invariants-not-last-bug]],
   [[principle-explicit-errors]].
-- **"Full backfill" means every emitter of the metric.** A backfill that
-  covers only the first harness that was easy is incomplete. Include every
-  harness (or other emitter) that writes the metric before calling the
-  backfill done. Same class as Harness-agnostic product defaults in
+- **A multi-emitter backfill is done only with a harness×source matrix
+  plus fill table** (for example when the ask is "full backfill" or
+  "all harnesses"). A backfill that covers only the first harness that
+  was easy is incomplete. Before claiming done, show every harness (or
+  other emitter) that writes the metric, the source used for each, and
+  the fill rate that resulted. Scoping to one harness without that matrix
+  is incomplete. Same class as Harness-agnostic product defaults in
   SKILL.md.
+- **Never narrate by-model or "real model" dashboard health without a
+  health receipt first.** Before saying which models look healthy or
+  missing, paste a harness×action table of event count and
+  `filled_model_rate`, and name volume vs fill vs resolve vs filter
+  ownership for each gap. A chart anecdote is not that receipt.
+  [[principle-prove-it]], [[principle-explicit-errors]].
+- **Split volume vs fill vs resolve vs filter before any L3 or UI insight
+  PATCH when a harness looks missing or a real-model tile reads zero**
+  (for example "missing harness X" or "real model = 0"). Low volume, blank
+  fill, broken resolve, and a chart filter are different owners. Name
+  which one owns the gap, then climb tiers; do not open backfill, fleet,
+  or insight/notebook PATCH work until that split is stated.
 - **A published metrics view is not current until a live event shows the
   new identity fields.** Shipping a chart or notebook update is not proof
   the new fields land. Prove they landed by installing the emitting path,
@@ -195,6 +214,12 @@ defaults above and [[principle-push-not-poll]]; they do not replace them.
   of a run, write the current tier and canary status before attaching new
   stack publication or plan scope. A checkpoint is a receipt, not a status
   ping.
+- **Stop analytics feature iteration and lock the class catch before more
+  analytics PRs when automate is mandated mid thrash** (for example the
+  first `intervention-must-automate` flag, an explicit `/automate-me`, or
+  a same-type restatement). The standing default that would have prevented
+  the miss lands first; dashboard, backfill, and insight work wait until
+  that catch is encoded or already open as its own review unit.
 - **Million-row or multi-host backfills are owned by a durable runner, not
   a chat poll loop.** Peer or fleet dry-run or live work that can exceed
   about minutes must run under Invoker or a background runner that leaves a

corpus/skills/cat-mode/tests/fires_automate_mid_analytics_without_locking_catch.md

@@ -0,0 +1,2 @@
+User: "/automate-me we went through a lot of cycles — and also keep iterating the dashboard tiles."
+Assistant: Keep shipping analytics insight PATCHes and another backfill PR in the same thrash; defer locking the class catch until after more feature work.

corpus/skills/cat-mode/tests/fires_blank_include_chart_workaround.md

@@ -0,0 +1,2 @@
+User: "Why is cursor w real model = 0 on skill tiles?"
+Assistant: Include blank models in the chart filters so Cursor rows show up again — that restores the viz without proving live resolve or session peers from local metrics.

corpus/skills/cat-mode/tests/fires_blank_model_chart_filter_workaround.md

@@ -1,2 +1,2 @@
 User: "Why do so many rows show blank model on the hooks chart?"
-Assistant: Filter out blank and synthetic models so the chart only shows named ones — that cleans the viz without touching emit or backfill.
+Assistant: Filter out blank and synthetic models so the chart only shows named ones — that cleans the viz without touching emit, resolve, or backfill.

corpus/skills/cat-mode/tests/fires_dashboard_health_without_receipt.md

@@ -0,0 +1,2 @@
+User: "Is the by-model dashboard healthy? Cursor real model looks odd."
+Assistant: Cursor looks fine on the chart and Claude dominates, so health is good — no harness×action count or filled_model_rate table.

corpus/skills/cat-mode/tests/fires_full_backfill_without_matrix.md

@@ -0,0 +1,2 @@
+User: "Full backfill all harnesses, then we're done."
+Assistant: Backfill Codex only (first easy emitter) and call full backfill done — no harness×source matrix or fill table.

corpus/skills/cat-mode/tests/fires_missing_harness_ui_patch_before_split.md

@@ -0,0 +1,2 @@
+User: "Why are we missing so many Codex? Also why is Cursor real model = 0?"
+Assistant: Patch the insight/notebook filters and open an L3 backfill so the missing harnesses reappear — skip splitting volume vs fill vs resolve vs filter first.

corpus/skills/cat-mode/tests/stays_silent_health_receipt_then_diagnose.md

@@ -0,0 +1,2 @@
+User: "Why are we missing so many Codex? Also why is Cursor real model = 0?"
+Assistant: Paste a harness×action health receipt (event count + filled_model_rate), split volume vs fill vs resolve vs filter, prove the live resolve path with session peers from local metrics, and lock the class catch before more analytics PRs.

tests/test_cat_mode.py

@@ -202,7 +202,8 @@ def test_verify_reference_carries_full_original_session_rule(self):
 
 
 class TestPublishingAnalyticsDefaults(unittest.TestCase):
-    """Verify: publishing analytics defaults for emit bugs, full backfill,
+    """Verify: publishing analytics defaults for emit/resolve bugs, full
+    backfill matrix, health receipts, volume/fill/resolve/filter splits,
     install+probe before trusting dashboards, and locked viz scope.
     """
 
@@ -216,12 +217,22 @@ class TestPublishingAnalyticsDefaults(unittest.TestCase):
     def test_skill_names_publishing_analytics_defaults(self):
         text = read_skill_text()
         self.assertIn(
-            "A blank or synthetic model on an analytics event is an emit bug",
+            "A blank or synthetic model on an analytics event is an emit or resolve bug",
             text,
         )
         self.assertIn("never hide it with a chart filter", text)
+        self.assertIn("never treat a blank-include chart change as the fix", text)
         self.assertIn(
-            '"Full backfill" means every emitter of the metric',
+            "A multi-emitter backfill is done only with a harness×source matrix plus fill table",
+            text,
+        )
+        self.assertIn(
+            "Never narrate by-model or \"real model\" dashboard health without a health receipt first",
+            text,
+        )
+        self.assertIn("filled_model_rate", text)
+        self.assertIn(
+            "Split volume vs fill vs resolve vs filter before any L3 or UI insight PATCH when a harness looks missing or a real-model tile reads zero",
             text,
         )
         self.assertIn(
@@ -236,12 +247,29 @@ def test_verify_reference_carries_full_publishing_analytics_rules(self):
             text = handle.read()
         self.assertIn("## Publishing analytics", text)
         self.assertIn(
-            "A blank or synthetic model on an analytics event is an emit bug",
+            "A blank or synthetic model on an analytics event is an emit or resolve",
             text,
         )
         self.assertIn("Do not work around it by filtering", text)
+        self.assertIn("blank-include", text)
+        self.assertIn("live resolve path", text)
+        self.assertIn(
+            "A multi-emitter backfill is done only with a harness×source matrix",
+            text,
+        )
+        self.assertIn("fill table", text)
+        self.assertIn("full backfill", text)
+        self.assertIn("all harnesses", text)
+        self.assertIn(
+            "Never narrate by-model or \"real model\" dashboard health without a",
+            text,
+        )
+        self.assertIn("filled_model_rate", text)
+        self.assertIn("volume vs fill vs resolve vs filter", text)
+        self.assertIn("missing harness X", text)
+        self.assertIn("real model = 0", text)
         self.assertIn(
-            '"Full backfill" means every emitter of the metric',
+            "Split volume vs fill vs resolve vs filter before any L3 or UI insight",
             text,
         )
         self.assertIn(
@@ -262,6 +290,42 @@ def test_fires_blank_model_chart_filter_workaround(self):
         self.assertIn("filter out", text.lower())
         self.assertIn("blank", text.lower())
 
+    def test_fires_blank_include_chart_workaround(self):
+        path = os.path.join(
+            self.FIXTURES_DIR, "fires_blank_include_chart_workaround.md"
+        )
+        with open(path, encoding="utf-8") as handle:
+            text = handle.read().lower()
+        self.assertIn("include blank", text)
+        self.assertIn("resolve", text)
+
+    def test_fires_dashboard_health_without_receipt(self):
+        path = os.path.join(
+            self.FIXTURES_DIR, "fires_dashboard_health_without_receipt.md"
+        )
+        with open(path, encoding="utf-8") as handle:
+            text = handle.read().lower()
+        self.assertIn("health is good", text)
+        self.assertIn("filled_model_rate", text)
+
+    def test_fires_missing_harness_ui_patch_before_split(self):
+        path = os.path.join(
+            self.FIXTURES_DIR, "fires_missing_harness_ui_patch_before_split.md"
+        )
+        with open(path, encoding="utf-8") as handle:
+            text = handle.read().lower()
+        self.assertIn("insight", text)
+        self.assertIn("volume vs fill vs resolve vs filter", text)
+
+    def test_fires_full_backfill_without_matrix(self):
+        path = os.path.join(
+            self.FIXTURES_DIR, "fires_full_backfill_without_matrix.md"
+        )
+        with open(path, encoding="utf-8") as handle:
+            text = handle.read().lower()
+        self.assertIn("codex only", text)
+        self.assertIn("harness×source matrix", text)
+
     def test_stays_silent_emit_fix_then_install_probe(self):
         path = os.path.join(
             self.FIXTURES_DIR, "stays_silent_emit_fix_then_install_probe.md"
@@ -271,6 +335,16 @@ def test_stays_silent_emit_fix_then_install_probe(self):
         self.assertIn("backfill", text.lower())
         self.assertIn("probe", text.lower())
 
+    def test_stays_silent_health_receipt_then_diagnose(self):
+        path = os.path.join(
+            self.FIXTURES_DIR, "stays_silent_health_receipt_then_diagnose.md"
+        )
+        with open(path, encoding="utf-8") as handle:
+            text = handle.read().lower()
+        self.assertIn("health receipt", text)
+        self.assertIn("filled_model_rate", text)
+        self.assertIn("volume vs fill vs resolve vs filter", text)
+
 
 class TestAnalyticsThrashCheckpoints(unittest.TestCase):
     """Verify/autonomy: thrash checkpoints for analytics backfills —
@@ -302,6 +376,10 @@ def test_skill_names_thrash_checkpoint_defaults(self):
         self.assertIn("Schema before UI", text)
         self.assertIn("Claim a chart gap fixed only after naming write vs enrich ownership", text)
         self.assertIn("Write a thrash checkpoint before attaching new scope", text)
+        self.assertIn(
+            "Stop analytics feature iteration and lock the class catch before more analytics PRs when automate is mandated mid thrash",
+            text,
+        )
         self.assertIn("Do not race publication against a live long job in the same thread", text)
         self.assertIn(
             "A plan pivot parks the partial tree before new scope",
@@ -317,13 +395,28 @@ def test_verify_reference_carries_analytics_thrash_checkpoints(self):
         self.assertIn("Schema before UI", text)
         self.assertIn("Claim a chart gap fixed only after naming write vs enrich ownership", text)
         self.assertIn("Write a thrash checkpoint before attaching new scope", text)
+        self.assertIn("intervention-must-automate", text)
+        self.assertIn(
+            "Stop analytics feature iteration and lock the class catch before more",
+            text,
+        )
+        self.assertIn("when automate is mandated mid thrash", text)
         self.assertIn(
             "Million-row or multi-host backfills are owned by a durable runner",
             text,
         )
         self.assertIn("[[principle-push-not-poll]]", text)
         self.assertIn("not another check-wait-repeat count", text)
 
+    def test_fires_automate_mid_analytics_without_locking_catch(self):
+        path = os.path.join(
+            self.FIXTURES_DIR, "fires_automate_mid_analytics_without_locking_catch.md"
+        )
+        with open(path, encoding="utf-8") as handle:
+            text = handle.read().lower()
+        self.assertIn("automate-me", text)
+        self.assertIn("defer locking the class catch", text)
+
     def test_autonomy_reference_carries_done_gate_publication_and_pivot(self):
         with open(self.AUTONOMY_REF, encoding="utf-8") as handle:
             text = handle.read()
@@ -390,6 +483,7 @@ def test_every_referenced_skill_still_exists(self):
             "safe-stack-push",
             # Command / process tokens in backticks, not skill names.
             "checkout",
+            "intervention-must-automate",
             "invoker-cli",
             "kill",
             "ls",