create-anpunkit 2.1.0 → 2.2.0

package/template/.claude/anpunkit-manifest.json

@@ -1,21 +1,21 @@
 {
-  "version": "2.1.0",
+  "version": "2.2.0",
   "files": [
     {
       "path": "AGENTS.md",
-      "sha256": "e33c8290f6a5aa15a744721d435944d49552b08428c91f83be4cf02b2a4fbda4"
+      "sha256": "0e4bdc92e8e33355fdfca8d7c3f644bd5f6b91d8b11b1837c65241c25a8dd695"
     },
     {
       "path": "CLAUDE.md",
-      "sha256": "e9d84381044c68d1b7289708de20bc6d2202eca3f39a2f63e7824a36fa18e299"
+      "sha256": "132e64b4a9a5a178deb4db810324f79338c2af65d598fd5e26f183225c2a4d98"
     },
     {
       "path": "README.md",
-      "sha256": "bd33dd8be4b1b20ab4ea9444f60094a8ee125681e6f1073e3ed7f06c1f5a5f4c"
+      "sha256": "ca353eea88978b65dab78355ec304de0b8fb5d8ecb54d4316ee493de4459f002"
     },
     {
       "path": ".gitattributes",
-      "sha256": "51ca20efd556b51644b3fd938cd07ff86a17170edd09f7c9caf718911a56b0a2"
+      "sha256": "5362db7bc5f0639f80bb191f5d6436a2c54b1ca8a398362fba14136eca4014bf"
     },
     {
       "path": "setup.sh",
@@ -27,19 +27,23 @@
     },
     {
       "path": ".claude/agents/e2e-runner.md",
-      "sha256": "4e914d20022be58f3915526f91ac6df54cb5efd4836c12b97fd042cce90e8ddc"
+      "sha256": "c454ad3217d6adc21e0e6cda5746e3094ea299cd7e71f761e1f417a7d6a2391e"
     },
     {
       "path": ".claude/agents/implementer.md",
-      "sha256": "9c2d5e166bac94bfff31a775766094a4275c5a8d1da9bae7823e824f5c307fe6"
+      "sha256": "e6598fdb77657616f821695323653cfdded44db85a428597d1c8074a56bbf816"
     },
     {
       "path": ".claude/agents/infra-provisioner.md",
       "sha256": "52a54a2aaaf7e53d28e261f5e01f2693fd0a4883fd93f844a112a742a91f9149"
     },
+    {
+      "path": ".claude/agents/spec-author.md",
+      "sha256": "3e352514bfd5eb32f966cfa12014d706d17b3a12ad2155e2f826243c03fb7d0c"
+    },
     {
       "path": ".claude/agents/planner.md",
-      "sha256": "b74951f53ddfebba5d2255d164ef4b1b6fa8544f3e8d9ae3ff7d23e2f3198650"
+      "sha256": "a1a2b86aa5a88d8b9fee9af3a8d10c7f1f09e5a2fb32f831dce38b010c507771"
     },
     {
       "path": ".claude/agents/researcher.md",
@@ -51,7 +55,7 @@
     },
     {
       "path": ".claude/agents/test-author.md",
-      "sha256": "d8ccd98ced9a77c7da6c40c12b7b3108f302f4cc5956ea8b516f6384203c9c13"
+      "sha256": "adc53adb326424dcb215a5f074c7df3dfcb6644f2c63ce1e9ed68d2810dc8398"
     },
     {
       "path": ".claude/hooks/cursor-session-start.sh",
@@ -95,11 +99,11 @@
     },
     {
       "path": "commands.src/overview.md",
-      "sha256": "841dad7d2765f4240900d18cd57a6c5a4cbc6c1f19f0568f5e14d4e098f60ab8"
+      "sha256": "85a300dcdd94d95c87c25c84d06619a38b5b3679631f68b511da11d7010e5cb8"
     },
     {
       "path": "commands.src/phase.md",
-      "sha256": "de910c499acf6f3d27353b2594a4ff8d7b650ee90b35ceb8dabf1e3244f4851b"
+      "sha256": "60a0e6442c2a3945afc4aec991cd44d48705eb8c142f3c2284db7095bb5441d9"
     },
     {
       "path": "commands.src/quick.md",
@@ -135,11 +139,11 @@
     },
     {
       "path": ".claude/commands/overview.md",
-      "sha256": "841dad7d2765f4240900d18cd57a6c5a4cbc6c1f19f0568f5e14d4e098f60ab8"
+      "sha256": "85a300dcdd94d95c87c25c84d06619a38b5b3679631f68b511da11d7010e5cb8"
     },
     {
       "path": ".claude/commands/phase.md",
-      "sha256": "de910c499acf6f3d27353b2594a4ff8d7b650ee90b35ceb8dabf1e3244f4851b"
+      "sha256": "60a0e6442c2a3945afc4aec991cd44d48705eb8c142f3c2284db7095bb5441d9"
     },
     {
       "path": ".claude/commands/quick.md",
@@ -175,11 +179,11 @@
     },
     {
       "path": ".cursor/commands/overview.md",
-      "sha256": "8cd54af27fa63ccfa714c7ecfa48476664fa3407b46cb708ddbc4ad2ebbb0a58"
+      "sha256": "9ee65f44d44362aaa37e5df7ed95eb7d386cec6e2045a2f87a81b80da343ac00"
     },
     {
       "path": ".cursor/commands/phase.md",
-      "sha256": "693e4edca20374441c876ac58994863949fb8f364e72e8a0dc32670d4550fc69"
+      "sha256": "5a2bac0d8dc36892256e49ddfd6bccac36e1d71dbc4cc0602ac337e398a0733e"
     },
     {
       "path": ".cursor/commands/quick.md",
@@ -229,17 +233,33 @@
       "path": "scripts/regression.sh",
       "sha256": "711bf59c9a1aa66846e1efd4a2127476edd8d92010207807e11e4080d430006e"
     },
+    {
+      "path": "scripts/spec-staleness.sh",
+      "sha256": "1a2b2cad55ba0500c84ce8c2e582ccc4b735bb2fc7d7152969e37c6653297de4"
+    },
+    {
+      "path": "scripts/spec-conformance.sh",
+      "sha256": "932be0e02c47dba0d56bc3600cc8ad80031e54a13e65ba4e474fd957bab9f9fa"
+    },
+    {
+      "path": "tests/helpers/spec-assert.py",
+      "sha256": "dd63f979cecdfa54e808ace01da038f44acb3a29ea65c928bf0458fd2d44c8d8"
+    },
+    {
+      "path": "tests/helpers/spec-assert.ts",
+      "sha256": "feda86755bb58af7f75323e182136eb4e5d43e813358ed1a3d712bbc4e069069"
+    },
     {
       "path": "create-anpunkit/package.json",
-      "sha256": "4b16cdfd4d9a22379147338664530fd7ce7f0e7566bf63d097f7b8f8f76dcdd8"
+      "sha256": "e283531b788e94cf9ca604a119e9d581e9cede3e1276770087f2c4874927e567"
     },
     {
       "path": "create-anpunkit/bin/cli.js",
-      "sha256": "129dae04923b6d380d3ca4601b5dcd2baa6ad4c51c827dddae3e43ea6a9c50e2"
+      "sha256": "f96460757110e6a0f81cef750c5b39442ea5589f53ae83b69951555632cce7ec"
     },
     {
       "path": "create-anpunkit/build.sh",
-      "sha256": "01fb6d1bb8866db54b0942d341b43e3f0ef96b97f7904909d77393fec49dbb58"
+      "sha256": "3a5062e46ba09ff23736de08545cefd1c0f30b216c3820bd2ada22e3d0db5b79"
     },
     {
       "path": "create-anpunkit/README.md",

package/template/.claude/commands/overview.md

@@ -119,6 +119,18 @@ Store the round-1 answers as working context — do NOT write OVERVIEW.md yet.
      interactive element the phase introduces (not "page renders 200").
    - Map each phase to the DATAFLOW transitions it is expected to make reachable.
 
+   The planner ALSO writes the up-front SKELETON spec files (v2.2, §5.44/§5.51):
+   one `docs/spec-phase-<n>.md` per public-surface phase (skip Phase 0 + pure
+   infra/config/doc phases), enumerating the case NAMES — happy path, each named
+   edge, each named failure + error code — for every `dataflow:` transition and
+   every `acceptance` criterion, with `TBD` values. The generated header transcludes
+   that phase's `acceptance:` line + in-scope `DATAFLOW.md` transition rows verbatim.
+
+8b. STAMP each skeleton's staleness hash: for every `docs/spec-phase-<n>.md` the
+   planner wrote, run `bash scripts/spec-staleness.sh stamp <n>`. This embeds the
+   hash of the transcluded acceptance line + transition rows so phase-time
+   `/phase` can detect upstream drift. (Values are filled per phase by `spec-author`.)
+
 9. Create docs/STATE.md:
 ```
 
@@ -144,6 +156,11 @@ blocker: none
  ```
 
 Then stop and show me PLAN.md + DATAFLOW.md for approval before any phase starts.
+EXTEND the approval surface (v2.2, §5.51 — one confirmation, no new gate): for each
+public-surface phase, list the transition/acceptance ids it covers and the enumerated
+case NAMES (no values). I confirm the case-name set is COMPLETE here — these names
+are the up-front behavioral contract; values get filled + reviewed per phase at
+`/phase` SPEC REVIEW.
 
 Remind me: "Run `/infra` next to provision the Azure environment (Phase 0) and
 run the one-time AUTH PROOF before starting Phase 1."

package/template/.claude/commands/phase.md

@@ -1,10 +1,10 @@
 ---
-description: Run one phase end-to-end. TDD phases run SCAFFOLD -> RED -> TEST REVIEW -> GREEN; non-TDD phases run IMPLEMENT -> TEST. Both with the debug circuit breaker and the regression + dataflow + evidence guards at CLOSE.
+description: Run one phase end-to-end. TDD phases run SPEC fill -> SPEC REVIEW -> SCAFFOLD -> RED -> conformance -> GREEN -> boundary/E2E; non-TDD phases run IMPLEMENT -> TEST. Both with the debug circuit breaker and the regression + dataflow + evidence guards at CLOSE.
 argument-hint: [phase number]
 ---
 
 Caveman ULTRA mode. You are the ORCHESTRATOR. Route work to subagents —
-you do NOT implement or debug yourself.
+you do NOT implement, fill specs, or debug yourself.
 
 Note: subagents cannot talk to the user. Only YOU can.
 
@@ -29,20 +29,21 @@ b. PHASE STATE CHECK: Read docs/STATE.md and docs/PLAN.md.
 c. FINAL PHASE CHECK: Read docs/PLAN.md. Is this the last phase (no further
    pending phases after this one)? Record this as IS_FINAL_PHASE=true/false.
 
-d. AUTH LIVENESS GATE (hard rule 16 — replaces the old soft nudge): if this phase
-   will run a real/E2E suite, confirm every credential it needs is live NOW.
+d. AUTH LIVENESS GATE (hard rule 16): if this phase will run a boundary/E2E suite,
+   confirm every credential it needs is live NOW.
    - If INFRA.md has no `AUTH PROOF: PASS` marker -> STOP: "Auth never proven
      reusable. Run `/infra` first."
    - Run `scripts/auth-setup.sh --check` (Entra token obtainable + not expired)
      and, for each external system this phase touches (docs/DATAFLOW.md external
      rows + docs/ENDPOINTS.md auth column), confirm its credential is obtainable
-     headlessly. Any failure -> real/E2E is BLOCKED; tell me what to run; the
+     headlessly. Any failure -> boundary/E2E is BLOCKED; tell me what to run; the
      MOCK suite may still proceed.
 
 e. FRONTEND TRIGGER (hard rule 13): read docs/OVERVIEW.md `has_frontend` + the
    frontend root. Set FRONTEND_PHASE=true iff `has_frontend: true` AND this
    phase's `changes` (docs/PLAN.md) include any path under the frontend root.
-   This is a PATH MATCH, not a judgment call. Record FRONTEND_PHASE for the GATE.
+   This is a PATH MATCH, not a judgment call. Record FRONTEND_PHASE — it gates the
+   `ui` boundary run + evidence at CLOSE.
 
 ---
 
@@ -57,8 +58,9 @@ datasource, compare what it touches to the confirmed BASELINE in
 docs/research/datasource-<name>.md. If it touches a NEW table/column beyond the
 baseline -> surface my understanding of just that delta as a falsifiable claim;
 WAIT for confirm; append it to datasource-<name>.md. If it touches only confirmed
-data -> proceed with a one-line note, no stop. Real/E2E against an UNCONFIRMED
-datasource is HARD-BLOCKED (mock still runs).
+data -> proceed with a one-line note, no stop. Boundary/E2E against an UNCONFIRMED
+datasource is HARD-BLOCKED (mock still runs). The confirmed baseline is what
+`spec-author` grounds fixtures in.
 
 Then classify the phase:
 
@@ -66,63 +68,105 @@ Then classify the phase:
   exported function/class, CLI command, message contract) assertable from the
   acceptance spec. Size is NOT the criterion.
 
-- Clear public surface -> `TDD_PHASE=true` -> run the TDD path (§2 → §3a → §3r → §3b).
+- Clear public surface -> `TDD_PHASE=true` -> run the TDD path (§2 → §3 → §4 → §5 → §6 → §7).
 - Pure infra/config/doc, no public surface -> `TDD_PHASE=false` -> run the
   non-TDD path (§2N → §3N).
 - AMBIGUOUS -> default `TDD_PHASE=true`, but STATE the classification + the reason
-  to me, so I can override to non-TDD BEFORE SCAFFOLD fires. (Hard rule 11: never
-  downgrade a TDD phase just to dodge the RED gate.)
+  to me, so I can override to non-TDD BEFORE SPEC fill fires. (Hard rule 11: never
+  downgrade a TDD phase just to dodge the gates.)
 
 =====================================================================
 ## TDD PATH  (TDD_PHASE=true)
 =====================================================================
 
-## 2. SCAFFOLD
+## 2. SPEC FILL + STALENESS
+
+a. SKELETON CHECK: confirm docs/spec-phase-<n>.md exists (planner generated it at
+   /overview). If MISSING (planner classified it non-TDD, or it's a new phase from
+   /replan): generate the skeleton NOW from this phase's PLAN.md `acceptance` +
+   `dataflow:` transitions in the planner skeleton format (generated header + named
+   `TBD` rows), then `bash scripts/spec-staleness.sh stamp <n>` to stamp its hash.
+
+b. Dispatch `spec-author`. It fills each case row with a real input payload
+   (`fixtures/<case-id>-input.json`), concrete expected output
+   (`fixtures/<case-id>-expected.json`), matcher tokens for volatile fields,
+   `error-code` for failures, and `selector/assert/value` `ui` descriptors —
+   grounded in the RESEARCH findings + the confirmed datasource baseline.
+
+c. CASE-SET-DIVERGENCE (hard re-entry, hard rule 12 / §5.52): if `spec-author`
+   returns `CASE-SET-DIVERGENCE` (a required case can't be filled from real facts,
+   or research revealed an unlisted/contradicted case) -> STOP. Surface the finding.
+   I amend the up-front case-name contract in the skeleton; you re-stamp
+   (`bash scripts/spec-staleness.sh stamp <n>`); then re-dispatch `spec-author` to
+   re-fill from scratch. AI never amends the case-name set — I own the contract.
+
+d. STALENESS (hard rule 17): run `bash scripts/spec-staleness.sh <n>`. Nonzero
+   (upstream PLAN acceptance line / DATAFLOW rows drifted since the skeleton was
+   stamped, e.g. via /replan) -> regenerate the skeleton header from current
+   PLAN/DATAFLOW, re-stamp, re-dispatch `spec-author`. Do NOT hand-edit the hash.
+
+## 3. SPEC REVIEW — human gate (hard rule 12)
+
+STOP. Surface the FILLED cases to me as FALSIFIABLE CLAIMS in plain language, e.g.:
+  - "POST /orders/submit with an empty line-item list → 422 EMPTY_ORDER."
+  - "Successful submit of a 3-line order → 201; order.id is a UUID; order.status is
+    'submitted'."
+Re-run `bash scripts/spec-staleness.sh <n>` at entry (nonzero -> back to §2d).
+SCAFFOLD cannot begin until I confirm. Classify any rejection WITH me (§5.50):
+  - WRONG EXPECTED -> fix the case row + `fixtures/<case-id>-expected.json`; no
+    re-research. (You may patch the fixture directly per my correction.)
+  - WRONG INPUT SHAPE -> re-dispatch `spec-author` with the correction.
+  - NEW CASE or CONTRADICTED CASE -> hard re-entry (§2c): I amend the skeleton, you
+    re-stamp, re-confirm the amended case(s) + any case sharing their `covers` id
+    (the staleness hash certifies the unchanged remainder — not re-read), re-fill.
+Loop until I approve. Unskippable on TDD phases.
+
+## 4. SCAFFOLD
 
 Dispatch `implementer` in SCAFFOLD mode: interface stubs only (signatures +
-types; bodies raise NotImplementedError / return 501); NO logic, NO tests.
-Returns the stub files + the interface surface.
+types; bodies raise NotImplementedError / return 501); NO logic, NO tests, NO
+edits to the spec or fixtures. Returns the stub files + the interface surface.
 
-## 3a. RED
+## 5. RED
 
-Dispatch `test-author` to write the REAL API suite (+ mock) BLIND against the
-stubs + acceptance, AND emit docs/test-plan-phase-<n>.md (acceptance criteria →
-test names, plus a mandatory "NOT covered / assumptions" section). Place
-contract/ENDPOINTS/DATAFLOW-transition tests in `tests/regression/`, phase-local
-tests in `tests/phase-<n>/`. Run the suite.
+Dispatch `test-author` to EMIT the boundary harness from the locked spec `data`
+rows: one deep-equality assertion per case against `fixtures/<case-id>-expected.json`
+via the kit comparator `tests/helpers/spec-assert.*`, each citing its case with a
+`# spec: <case-id>` comment. It does NOT author assertions — it generates them from
+the spec. Place contract/ENDPOINTS/transition tests in `tests/regression/`,
+phase-local in `tests/phase-<n>/`.
 
-RED GATE = every acceptance test COLLECTS cleanly AND FAILS (assertion /
-NotImplemented).
-- Any test PASSES on stubs -> STOP (spec trivial or test wrong); show me.
+If FRONTEND_PHASE (and the phase has `ui` cases): also dispatch `e2e-runner` to EMIT
+Playwright assertions from each `ui` case's `fixtures/<case-id>-ui.json` descriptor,
+each citing `// spec: <case-id>`. Run the suites.
+
+RED GATE = every case test COLLECTS cleanly AND FAILS (assertion / NotImplemented).
+- Any test PASSES on stubs -> STOP (spec trivial or emitter wrong); show me.
 - Collection / import / syntax error -> stub mismatch; re-dispatch SCAFFOLD to
   fix SIGNATURES (not logic); re-run.
-- UNDERSPEC -> STOP; ask me to sharpen the acceptance spec.
 
-## 3r. TEST REVIEW — human gate (hard rule 12)
+## 6. CONFORMANCE GATE (hard rule 18) — replaces the v2.1 human TEST REVIEW
 
-STOP. Surface docs/test-plan-phase-<n>.md to me: what each acceptance criterion
-maps to, and the "NOT covered / assumptions" section. GREEN cannot begin until I
-approve. On rejection, classify with me:
-  - MISREAD of an adequate spec -> re-dispatch `test-author` with my feedback as
-    added constraint; re-run RED; re-present the test plan.
-  - UNDERSPEC (the acceptance spec itself is too vague) -> sharpen the acceptance
-    spec in docs/PLAN.md, then re-dispatch `test-author` fresh.
-Loop until I approve. This gate is unskippable on TDD phases.
+Run `bash scripts/spec-conformance.sh <n>`. It loud-fails (and BLOCKS GREEN) if:
+  - any `TBD` marker remains in docs/spec-phase-<n>.md or a referenced fixture, OR
+  - any case-id in the spec table has no boundary test citing it (`# spec: <case-id>`).
+Nonzero -> fix the gap (re-dispatch `spec-author` for a stray TBD, or `test-author`/
+`e2e-runner` for a missing citation) and re-run. GREEN cannot start until it passes.
 
-## 3b. GREEN
+## 7. GREEN + BOUNDARY/E2E
 
-Dispatch `implementer` in FILL mode with the phase spec + research + the test
-file paths (it MAY read the tests — frozen before logic, no overfit — but must
-NOT edit them). Fill to green. Budget 3, WARN@2, STUCK@3.
+Dispatch `implementer` in FILL mode with the FILLED docs/spec-phase-<n>.md + its
+fixtures + research + the generated test file paths (it MAY read the tests — frozen
+before logic, no overfit — but must NOT edit tests, spec, or fixtures). Fill to
+green against the spec. Budget 3, WARN@2, STUCK@3.
 
-If FRONTEND_PHASE (from PRE-FLIGHT e): dispatch `e2e-runner` — MANDATORY, not
-optional (hard rule 13). It reads INFRA.md target, runs `scripts/e2e-stack.sh up`
-/ Playwright / `down`, and captures a screenshot at EACH UI-existence assertion
-regardless of pass/fail to docs/evidence/e2e-phase-<n>/, with a summary in
-docs/research/e2e-<slug>.md. Acceptance spec has no UI-existence criterion ->
-e2e-runner returns UNDERSPEC -> STOP, sharpen the spec.
+Run the BOUNDARY suite (real HTTP/CLI/message; `TEST_MODE=real`). If FRONTEND_PHASE,
+`e2e-runner` runs its emitted `ui` specs — MANDATORY (hard rule 13) — reads INFRA.md
+target, runs `scripts/e2e-stack.sh up` / Playwright / `down`, and captures a
+screenshot at EACH UI-existence assertion regardless of pass/fail to
+docs/evidence/e2e-phase-<n>/, with a summary in docs/research/e2e-<slug>.md.
 
-PHASE GATE (rule 5) -> go to §4/§5/§6 (see GATE below).
+PHASE GATE (rule 5) -> go to §8/§9/§10 (see GATE below).
 
 =====================================================================
 ## NON-TDD PATH  (TDD_PHASE=false)
@@ -137,18 +181,19 @@ includes "deployed URL" before proceeding.
 
 ## 3N. TEST (blind)
 
-Dispatch `test-author`. It writes MOCK + REAL API suites from the acceptance
-spec — never reads the logic. (No TEST REVIEW gate on the non-TDD path — no
-public surface to mis-test. e2e-runner only if FRONTEND_PHASE.)
+Dispatch `test-author`. It writes MOCK + boundary suites from the acceptance
+spec — never reads the logic. (No spec file, SPEC REVIEW, or conformance gate on
+the non-TDD path — no public surface to contract. e2e-runner only if FRONTEND_PHASE.)
 
 =====================================================================
 
 ## GATE (both paths)
 
-PHASE GATE = current-phase REAL API suite passes AND (FRONTEND_PHASE) E2E passes
-WITH evidence captured AND the accumulated mock regression corpus stays green AND
-every docs/ENDPOINTS.md entry has a regression test AND every REACHABLE
-docs/DATAFLOW.md transition has a regression test (all checked at CLOSE).
+PHASE GATE = current-phase BOUNDARY suite passes AND (FRONTEND_PHASE) the `ui`
+boundary passes WITH evidence captured AND the accumulated mock regression corpus
+stays green AND every docs/ENDPOINTS.md entry has a regression test AND (TDD)
+`spec-conformance.sh` passed AND every REACHABLE docs/DATAFLOW.md transition has a
+filled case in the phase spec (all checked at CLOSE).
 - GATE PASS -> go to CLOSE.
 - GATE BLOCKED (SERVICE UNAVAILABLE, STACK NOT READY, AZURE UNAVAILABLE, FLAKE)
   -> tell me, wait. Not a code bug. For AZURE UNAVAILABLE: suggest `/infra verify`.
@@ -156,17 +201,17 @@ docs/DATAFLOW.md transition has a regression test (all checked at CLOSE).
 
 ---
 
-## 4. FIX
+## 8. FIX
 
 Dispatch `debugger` (isolated context) on the specific failure.
-- FIXED -> re-run TEST (and the regression corpus).
+- FIXED -> re-run the boundary suite (and the regression corpus).
 - SERVICE UNAVAILABLE -> tell me, wait. Suggest `/infra verify` if Azure.
 - WARN (2 attempts failed) -> relay immediately, then let debugger finish attempt 3.
 - STUCK -> go to ESCALATE.
 
 ---
 
-## 5. ESCALATE — circuit breaker. Mode B.
+## 9. ESCALATE — circuit breaker. Mode B.
 
 FIRST STUCK: STOP. Present to me: the problem, 3 failed hypotheses, the
 debugger's recommendation, the debug file path. Ask what to do. Wait. Options:
@@ -179,20 +224,22 @@ what to try next. Hand control to me.
 
 ---
 
-## 6. CLOSE
+## 10. CLOSE
 
 REGRESSION + COVERAGE GATES (before closing — all FAIL HARD, do not close):
-- Run `scripts/regression.sh` (mock corpus). A failure BLOCKS close -> route to FIX.
+- Run `bash scripts/regression.sh` (mock corpus). A failure BLOCKS close -> route to FIX.
 - ENDPOINTS COVERAGE: every `docs/ENDPOINTS.md` entry MUST have >=1 test in
   `tests/regression/`. Zero coverage -> FAIL HARD.
-- DATAFLOW COVERAGE (hard rule 14): every `docs/DATAFLOW.md` transition whose
-  trigger is REACHABLE in the code shipped so far MUST have >=1 test in
-  `tests/regression/`. Zero coverage on a reachable transition -> FAIL HARD.
-  Unreachable transitions list as PENDING (not failed). IF IS_FINAL_PHASE: any
-  transition still PENDING -> FAIL HARD (everything must be live by the last phase).
+- DATAFLOW COVERAGE (hard rule 14, re-seamed v2.2): every `docs/DATAFLOW.md`
+  transition whose trigger is REACHABLE in the code shipped so far MUST have >=1
+  FILLED CASE in docs/spec-phase-<n>.md. Zero coverage on a reachable transition ->
+  FAIL HARD. Unreachable transitions list as PENDING (not failed). IF
+  IS_FINAL_PHASE: any transition still PENDING -> FAIL HARD. (The case→test half is
+  already enforced by `spec-conformance.sh` at §6 — every case-id is cited by a
+  boundary test, which by placement lands in tests/regression/.)
 - EVIDENCE (FRONTEND_PHASE only, hard rule 13): docs/evidence/e2e-phase-<n>/ must
   contain at least the per-UI-existence-assertion screenshots. Empty -> FAIL HARD.
-- IF IS_FINAL_PHASE: additionally run `scripts/regression.sh --real` (full real
+- IF IS_FINAL_PHASE: additionally run `bash scripts/regression.sh --real` (full real
   corpus). A failure blocks close.
 
 Mark phase `done` in docs/PLAN.md.
@@ -202,7 +249,7 @@ ARCHITECTURE / DATAFLOW SELF-CHECK:
   workflow rule? YES -> run `/log-decision`. NO -> state why not.
 - Did this phase add/change an object's STATE LIFECYCLE? YES -> update
   docs/DATAFLOW.md (hard rule 9) in this CLOSE, and confirm new reachable
-  transitions are covered. NO -> state why not.
+  transitions are covered by a filled case. NO -> state why not.
 
 IF IS_FINAL_PHASE — FINAL CLOSE sequence:
 

package/template/.cursor/commands/overview.md

@@ -115,6 +115,18 @@ Store the round-1 answers as working context — do NOT write OVERVIEW.md yet.
      interactive element the phase introduces (not "page renders 200").
    - Map each phase to the DATAFLOW transitions it is expected to make reachable.
 
+   The planner ALSO writes the up-front SKELETON spec files (v2.2, §5.44/§5.51):
+   one `docs/spec-phase-<n>.md` per public-surface phase (skip Phase 0 + pure
+   infra/config/doc phases), enumerating the case NAMES — happy path, each named
+   edge, each named failure + error code — for every `dataflow:` transition and
+   every `acceptance` criterion, with `TBD` values. The generated header transcludes
+   that phase's `acceptance:` line + in-scope `DATAFLOW.md` transition rows verbatim.
+
+8b. STAMP each skeleton's staleness hash: for every `docs/spec-phase-<n>.md` the
+   planner wrote, run `bash scripts/spec-staleness.sh stamp <n>`. This embeds the
+   hash of the transcluded acceptance line + transition rows so phase-time
+   `/phase` can detect upstream drift. (Values are filled per phase by `spec-author`.)
+
 9. Create docs/STATE.md:
 ```
 
@@ -140,6 +152,11 @@ blocker: none
  ```
 
 Then stop and show me PLAN.md + DATAFLOW.md for approval before any phase starts.
+EXTEND the approval surface (v2.2, §5.51 — one confirmation, no new gate): for each
+public-surface phase, list the transition/acceptance ids it covers and the enumerated
+case NAMES (no values). I confirm the case-name set is COMPLETE here — these names
+are the up-front behavioral contract; values get filled + reviewed per phase at
+`/phase` SPEC REVIEW.
 
 Remind me: "Run `/infra` next to provision the Azure environment (Phase 0) and
 run the one-time AUTH PROOF before starting Phase 1."