@dzhechkov/p-replicator 1.5.17 → 1.6.0

package/templates/.claude/skills/requirements-validator/references/scoring-system.md

@@ -53,6 +53,34 @@ Total Score = INVEST Score (50%) + SMART Score (30%) + Quality Score (20%)
 | 50-69 | Fair | 🔶 REWORK | Significant clarification needed |
 | **0-49** | **Poor** | **🚫 BLOCKED** | **Requires complete rewrite** |
 
+### Blocking floor (overrides the total, both directions)
+
+**The weakest link decides, never the average.** A requirement is BLOCKED — whatever its total says —
+if either of these is zero:
+
+| Criterion | Zero means | Why it vetoes |
+|-----------|-----------|---------------|
+| `Testable` (INVEST, 8) | no acceptance criteria exist | the gate exists to block untestable requirements |
+| `Completeness` (Quality, 10) | "No AC" on the rubric above | nothing states what "done" is |
+
+Without this floor the total alone lets an untestable requirement through. Worked case: a story with
+NO acceptance criteria and NO test links loses `Testable` 8, `Completeness` 10 and `Traceability` 10,
+keeps everything else, and totals **72/100** — above the 70 line, filed as "fix minor issues, then
+proceed". The floor blocks it on `Testable = 0` and `Completeness = 0`.
+
+**The floor keys on the artifact, not on the number you wrote.** The same agent scores these
+criteria AND is bound by the floor, so a score is not evidence of anything — reporting `Testable = 4`
+("vague AC") on a story with no AC at all evades the veto without lying about the rubric. Therefore:
+
+> A non-zero `Testable` or `Completeness` REQUIRES quoting the acceptance criteria being scored —
+> the actual text, with its document and heading. `Testable = 4` means the AC exist and are vague:
+> quote them. **No quote ⇒ the score is 0 ⇒ the floor applies.**
+
+**The floor is CLOSED at these two.** `Measurable` and `Traceability` are deliberately NOT on it: a
+requirement with no number is often correct ("the user can export the report as PDF" is specific,
+testable and unmeasurable), so vetoing on `Measurable` would turn a false pass into a false block.
+Widening this list needs the same kind of worked case as the one above.
+
 ## Quality Gate Rules
 
 ### BLOCKED (Score < 50)

package/templates/.claude/skills/sparc-prd-mini/SKILL.md

@@ -382,16 +382,24 @@ view("/mnt/skills/user/problem-solver-enhanced/SKILL.md")
 
 **User Story Format:**
 ```
-As a [persona],
+US-<nnn>: As a [persona],
 I want to [action],
 So that [benefit].
 
 Acceptance Criteria:
+[SC-<story-id>-1]
 Given [context]
 When [action]
 Then [expected result]
 ```
 
+Every user story carries an ID `US-<nnn>` — three digits, assigned in order, never reused even after
+a story is deleted. Every acceptance scenario under it carries `SC-<US-id>-<n>`, numbered from 1
+within its story: the scenarios of `US-007` are `SC-US-007-1`, `SC-US-007-2`, and so on. Phase 4
+traces algorithms back to these IDs, and there is nothing to trace to if a scenario has no name — nor
+anything reliable to trace to if two scenarios can end up with the same name, which is what the
+never-reused rule prevents.
+
 **PRD Generation:**
 ```
 view("templates/prd.md")
@@ -437,6 +445,7 @@ type EntityName = {
 ## Core Algorithms
 
 ### Algorithm: [Name]
+REALISES: [SC-… ids this algorithm implements, comma-separated]
 INPUT: [parameters]
 OUTPUT: [result]
 
@@ -471,6 +480,54 @@ Response (4xx/5xx):
 [Error categories and responses]
 ```
 
+**Шаг 4.9 — ПОКРЫТИЕ СЦЕНАРИЕВ (обязательный, до чекпойнта).**
+
+Re-read `Specification.md` and collect every `SC-` scenario ID. Collect every algorithm's `REALISES`
+line from `Pseudocode.md`. Write a `## Scenario Coverage` block into `Pseudocode.md` — **in every
+case, including the one where everything is covered**, because an absent block and a block saying
+"all covered" are indistinguishable to the next reader:
+
+```
+## Scenario Coverage
+
+Scenarios in Specification.md: [N]  ·  claimed by an algorithm: [M]
+
+Not claimed by any algorithm:
+| Scenario | Reason |
+|---|---|
+| SC-… | ui-only |
+
+Claimed by an algorithm but absent from Specification.md:
+| Algorithm | Claimed ID |
+|---|---|
+| [name] | SC-… |
+```
+
+**Both tables are required, and both may be the single word `none`.** A traceability check that runs
+one way only is half a check: without the second table an algorithm can declare `REALISES: SC-US-009-3`
+for a scenario nobody ever wrote, and the dangling reference reads exactly like coverage. `none` is
+written out rather than left blank, because an empty table and a forgotten table look identical.
+
+**Reasons are a CLOSED list of five**, and nothing else is accepted:
+
+| Reason | Means |
+|---|---|
+| `ui-only` | realised entirely in the interface, no algorithm to write |
+| `external-service` | performed by a third party, see `Architecture.md` → External Dependencies |
+| `out-of-mvp-scope` | deliberately not built yet |
+| `data-only` | satisfied by a schema or constraint, not by a procedure |
+| `config-only` | satisfied by OUR OWN configuration — a server setting, a header, a policy file — with no procedure to write |
+
+Free text is NOT a reason, and `N/A` is NOT a reason. A field that accepts anything records nothing:
+the whole value of the list is that an unclaimed scenario has to be one of a small number of
+recognisable things, and if it is none of them, the gap is real and belongs in the algorithms.
+
+**What this establishes, and what it does not.** It establishes that a CLAIM exists and that its two
+ends name each other. It does NOT establish that the algorithm's steps actually perform the check the
+scenario describes — no comparison of names can. So this catches *"nobody wrote anything about this
+scenario"*; it does not catch *"someone wrote a line that mentions it"*. Say so here rather than
+letting a later reader assume the stronger thing.
+
 **[MANUAL] CP4:**
 ```
 ═══════════════════════════════════════════════════════════════
@@ -541,6 +598,51 @@ graph TB
 | Queue | | |
 | Infrastructure | | |
 
+## External Dependencies
+
+Every capability this product needs from someone else's service. One row per capability, not one row
+per vendor: "sends email" and "reports bounces" are two questions, and a provider can do one without
+the other.
+
+| Capability needed | Provider / API | Evidence | Verdict | Requirements relying on it |
+|---|---|---|---|---|
+| [what the product needs it to DO] | [service] | [link to the provider's own docs naming this capability] · checked [YYYY-MM-DD] | CONFIRMED | [REQ ids] |
+
+**Evidence — what counts, and what does not.** Evidence is a link to the PROVIDER'S OWN documentation
+that names the specific capability, plus the date it was checked, plus **a short verbatim QUOTE from
+that page stating the capability**. These do NOT count, and each is a way this check gets faked: a
+landing page or marketing page; a pricing page; recollection — "the model knows this API supports
+it"; and **a URL nobody opened** — a plausible-looking link is the cheapest possible forgery, which
+is exactly why the quote is required and the link alone is not enough. A capability nobody could cite
+is not confirmed, and saying so is the point of the middle verdict.
+
+**Verdicts — exactly three, because two would hide a difference that matters:**
+
+| Verdict | Means | Consequence in Phase 2 |
+|---|---|---|
+| CONFIRMED | cited, and the citation names this capability | none |
+| UNCONFIRMED | nobody could produce a citation | the REQUIREMENTS in that row's last column cannot enter Phase 3 — defer, remove or replace them. Unrelated work continues; the run is 🟡 CAVEATS at best and the row is NAMED in the report |
+| CONTRADICTED | the provider's own docs say it cannot | 🔴 NEEDS WORK — the requirement rests on something that is not there |
+
+`UNCONFIRMED` is not a failure to be hidden; it is the honest state of a project on a machine with no
+web access. Collapsing it into CONFIRMED overstates what is known; collapsing it into CONTRADICTED
+blocks work that may be perfectly fine — and would push people to write a citation that isn't one,
+which is how a gate becomes theatre.
+
+But it does not pass for free either. **The consequence is scoped to the REQUIREMENT, not to the
+run:** the requirements listed in an `UNCONFIRMED` row do not enter Phase 3 until they are deferred,
+removed, or rewritten onto something confirmable. Everything not resting on that capability proceeds.
+Without this scoping an inventory of nothing but `UNCONFIRMED` rows would reach Phase 3 with a
+caveat, and external feasibility would never have to be established at all — the check would be
+optional in practice while looking mandatory on paper.
+
+**If this product has no external dependencies**, write exactly that: *"No external dependencies —
+this product calls no third-party service."* An empty section and an absent section are
+indistinguishable, and only one of them means anything.
+
+Names in the row above are PLACEHOLDERS. Do not copy a real provider or a real capability from any
+example: what an API can do drifts, and a stale fact recorded as evidence is worse than none.
+
 ## Data Architecture
 [Data models, relationships, storage strategy]
 
@@ -551,6 +653,46 @@ graph TB
 [Horizontal/vertical scaling, bottlenecks]
 ```
 
+**Шаг 5.9 — СВЕРКА С ПСЕВДОКОДОМ (обязательный, до чекпойнта).**
+
+Фаза 4 написала модель данных ДО того, как эта фаза выбрала хранилище и технологии, и до сих пор
+ничто их не сверяло. Именно отсюда берутся расхождения, которые всплывают уже в коде: поле осталось
+булевым, когда схема получила перечисление; алгоритм пользуется полем, которого в схеме нет; у
+статуса три значения в одном документе и пять в другом.
+
+Перечитай в `Pseudocode.md` ДВЕ секции — `## Data Structures` и `## Core Algorithms` — и сверь их с
+тем, что выбрано ЗДЕСЬ. Алгоритмы нужны обязательно: расхождение «алгоритм читает поле, которого в
+схеме нет» по одним лишь структурам данных не обнаруживается. Ищи три вида расхождений:
+
+- **смена типа** — поле объявлено одним типом, а хранилище требует другого (булево против перечисления);
+- **отсутствующая колонка** — алгоритм читает или пишет поле, которого в схеме нет;
+- **несовпадение набора значений** — у одного и того же поля разное число допустимых значений.
+
+Какую сторону править — решается по РОЛИ документа, а не по старшинству. `Pseudocode.md` держит
+ЛОГИЧЕСКУЮ модель (что означает поле), `Architecture.md` — ФИЗИЧЕСКУЮ (где и как оно лежит).
+Поэтому: если эта фаза ввела осознанное физическое ограничение (тип хранилища, индекс, длина) —
+правится `Pseudocode.md`; если выбранная технология НАРУШАЕТ требуемую семантику (теряются значения,
+исчезает состояние, которым пользуется алгоритм) — меняется выбор ЗДЕСЬ, потому что требование
+старше удобства реализации. Секция `## Data Architecture` этого документа остаётся на месте, но
+описывает отображение на хранилище и связи, а НЕ пересказывает список полей: второй экземпляр списка
+становится вторым местом, где начинается расхождение.
+
+Результат записывается в `Architecture.md` ВСЕГДА, отдельным блоком:
+
+```markdown
+## Reconciliation with Pseudocode
+
+| Сущность.поле | Вид расхождения | Что сделано |
+|---|---|---|
+| … | смена типа / отсутствующая колонка / несовпадение набора значений | … |
+```
+
+Если сверка не нашла ничего — блок всё равно пишется, и он ОБЯЗАН назвать, что именно
+сверялось: «Расхождений с `Pseudocode.md` не найдено. Сверены сущности: <перечисление>; алгоритмы:
+<перечисление>.» Одна фраза «расхождений нет» без перечня — это церемония, которую модель напишет
+не глядя; перечень делает утверждение проверяемым. Молчание не является результатом сверки: по нему
+нельзя отличить «сверили и чисто» от «не сверяли».
+
 **[MANUAL] CP5:**
 ```
 ═══════════════════════════════════════════════════════════════

package/tests/e2e/lifecycle.test.js

@@ -281,16 +281,24 @@ describe('e2e: unknown command', () => {
 // ---------------------------------------------------------------------------
 
 describe('e2e: --help shows correct component counts', () => {
-  test('mentions 10 skills, 11 commands, 4 agents, 5 rules', () => {
+  test('--help agrees with COMPONENTS for every group', () => {
+    // DERIVED, not hardcoded. This assertion has now gone stale twice for the same reason — the
+    // comment above records "cli.js used to say 1 rule while EXPECTED_RULES had 2 entries", and
+    // adding the docker-ports rule broke it again with a literal 5. cli.js:57 already computes the
+    // numbers from COMPONENTS; a test that re-types them is a second source of truth, which is the
+    // very defect it was written to catch.
+    const { COMPONENTS } = require(path.join(PKG_DIR, 'src', 'utils.js'));
     const dir = tmpDir();
     try {
       const r = runCli(['--help'], dir);
       assert.equal(r.exitCode, 0);
-      assert.match(r.stdout, /10\s+skills/i, 'should mention 10 skills');
-      assert.match(r.stdout, /11\s+commands/i, 'should mention 11 commands (post v1.4)');
-      assert.match(r.stdout, /4\s+agents/i, 'should mention 4 agents');
-      assert.match(r.stdout, /5\s+rules/i,
-        'should say "5 rules" (post v1.4: + 3 generic rules)');
+      for (const group of ['skills', 'commands', 'agents', 'rules']) {
+        const n = Object.keys(COMPONENTS[group].items).length;
+        // singular/plural: cli.js prints "1 rule" but "6 rules"
+        const word = n === 1 ? group.replace(/s$/, '') : group;
+        assert.match(r.stdout, new RegExp(n + '\\s+' + word, 'i'),
+          '--help must say "' + n + ' ' + word + '" to match COMPONENTS.' + group);
+      }
     } finally { rmRf(dir); }
   });
 });
@@ -440,8 +448,10 @@ describe('e2e: v1.4.1 cross-platform hooks', () => {
         assert.doesNotMatch(cmd, /\|\|\s*true/,
           `bash-specific || true in: ${cmd}`);
         // Each command should invoke node + a script
-        assert.match(cmd, /node\s+\.claude[/\\]hooks/,
-          `expected 'node .claude/hooks/<script>.cjs', got: ${cmd}`);
+        // Anchored at the project root, not the drifting cwd (PR-013): still node + the exact
+        // script, and now additionally the anchor — strictly stronger than the old assertion.
+        assert.match(cmd, /node\s+"\$\{CLAUDE_PROJECT_DIR\}\/\.claude\/hooks\/[A-Za-z0-9._-]+\.cjs"/,
+          `expected 'node "\${CLAUDE_PROJECT_DIR}/.claude/hooks/<script>.cjs"', got: ${cmd}`);
       }
     } finally { rmRf(dir); }
   });
@@ -599,8 +609,9 @@ describe('e2e: v1.5.0 statusline dashboard', () => {
       );
       assert.ok(settings.statusLine, 'statusLine field should be present in settings.json');
       assert.equal(settings.statusLine.type, 'command');
-      assert.match(settings.statusLine.command, /node\s+\.claude[/\\]hooks[/\\]statusline\.cjs/,
-        'should invoke statusline.cjs via node');
+      assert.match(settings.statusLine.command,
+        /node\s+"\$\{CLAUDE_PROJECT_DIR\}\/\.claude\/hooks\/statusline\.cjs"/,
+        'should invoke statusline.cjs via node, anchored at the project root (PR-013)');
     } finally { rmRf(dir); }
   });
 

package/tests/snapshot/baseline.json

@@ -1,10 +1,10 @@
 {
-  "generatedAt": "2026-07-19T15:43:12.046Z",
-  "totalFiles": 119,
+  "generatedAt": "2026-08-27T09:01:34.335Z",
+  "totalFiles": 136,
   "files": {
-    ".claude/agents/doc-validator.md": "a46651637239b4f078b5c3022ea2bf9ef4fb84ab2eb529cdc41273c42deaddf5",
+    ".claude/agents/doc-validator.md": "e57950758cd4764b2cb54b3f1905567e9dbc1ed20ac6ecd30998614894689f4f",
     ".claude/agents/harvest-coordinator.md": "70fa884057669902e18744915305705cf9e45e738a83d7bb5ab011a3b72d683c",
-    ".claude/agents/product-discoverer.md": "ea341407faa6f31a152508945b24e650c5a71459bbc9e1f91cdab7621660a54d",
+    ".claude/agents/product-discoverer.md": "f74683fe91b4357d6fb4024ed47b4d5a129ea6375ca6b223dee97176d74acf1c",
     ".claude/agents/replicate-coordinator.md": "e86060110ab188109cf908878206543f414993e14dad01f8dc19f041ee6497a7",
     ".claude/commands/deploy.md": "27f5424ee217163c55e5e6b9322a1f0858159407bd24ebd6d6588d6c22a5f890",
     ".claude/commands/docs.md": "be03592cb3f1d61b60dc96d3e26d71281ad4eb2d4626012c080ce609a32c96e4",
@@ -12,23 +12,25 @@
     ".claude/commands/go.md": "655dc9cad37b61a9f283cef15e435c492ee7cbc88a6ce59295ac32c975dee858",
     ".claude/commands/harvest.md": "c074fe7799f594dda44c5f8166da707f25cee51b12f758dea562a8c1e6ac5dcd",
     ".claude/commands/myinsights.md": "2e73e822384f976383d9c3313940888b9853f1781d2c39a2fb89825f221149dc",
-    ".claude/commands/next.md": "c417f86626a91d716cb9b5ed98e1445a0820055b22947da33fc90fc65fe974b2",
+    ".claude/commands/next.md": "1e4984306c3aa80dfc8734dc1c975dfe5fdf2cf6396ddd759e4c7635646107b8",
     ".claude/commands/plan.md": "6fef889f51168981bf4a98b8392a0d595e3d199e1cfaa8e08c0a181ec6c440e4",
-    ".claude/commands/replicate.md": "27fb978d1b4f19169d48795c5ce1a8ad4e5b6a03e9ae478b64857cdeb9d8b4bb",
+    ".claude/commands/replicate.md": "13f5e2ebe109f33b63cbcd75e3cf1b94224ab066aba1b0cb10cf34f668144a8a",
     ".claude/commands/run.md": "87144dfe8c56c15ba7c117daa544d8a08b84d7205f21dafcc48d27c6c3995059",
-    ".claude/commands/start.md": "8ebd4393caf6fb453bf607022e6209b963847dd61cb95a78e7bb5f98e039c774",
-    ".claude/hooks/autocommit-insights.cjs": "36fa95a1cfa74098f2f222ee7038d1bd22478a42070746614eb9e2d8514cad61",
-    ".claude/hooks/autocommit-plans.cjs": "ac831fa835557e268a73e7a039977194c638689c3c65ce8cba427535d88ec3b2",
-    ".claude/hooks/autocommit-roadmap.cjs": "ab78ae2f163400865bee520b73b7624094bf6c32c63478dfd5d6a1715ca7f135",
-    ".claude/hooks/session-insights.cjs": "cbb60842149fb90aaa968576f99d0695c92628377c3ca3120d28c5ff0bc692f2",
-    ".claude/hooks/state-update.cjs": "39a20e59278e457f4ec4eadd66f3699fee43c79695934a44a4cdca0c18f6cec2",
-    ".claude/hooks/statusline.cjs": "7e3e230f68b2ba76908127887e7f75428599dbd62826be62ed626fc054ca1e65",
+    ".claude/commands/start.md": "4aaebc10ca8d607d4b2b43883d82392e9788c2f183878a49fc0d1ed54d07ee95",
+    ".claude/hooks/autocommit-insights.cjs": "5e7cef87b24d457f25315d79fe15f0dfaf94d9269495d638817f0faee2593c6f",
+    ".claude/hooks/autocommit-plans.cjs": "9bb404b7f4fda5de03e6c2f16bf8939a79ec1944538767b04bcccc6cf50cc03d",
+    ".claude/hooks/autocommit-roadmap.cjs": "f4dcc9ffd9a3aed91dd56e011e699fcf8af903cc81594e4ab1ef61e5432a36ad",
+    ".claude/hooks/check-ports.cjs": "e5f2d2bd8899df27c2dfedf76128467becae1868210eb8525a1bad2869a8c78f",
+    ".claude/hooks/session-insights.cjs": "46f8357e3886a6d54db1ab4af969b9b8643ae5937ba59038a5651ffbcfd0d30e",
+    ".claude/hooks/state-update.cjs": "47146a76b768ac2273abe8f2f017856a0e28b45afaf90048148da417dd19604e",
+    ".claude/hooks/statusline.cjs": "1eca683baf67a17874dc5db6dfe38eb11944f550c66f46330bce0f794732245f",
+    ".claude/rules/docker-ports.md": "bef41c25c875479341f68783c2d64572800d4710f55401e55519245f03d22efb",
     ".claude/rules/feature-lifecycle.md": "f9ddc8c889ab7938a7207b36ae46c36be05e9b870956ef16617bf31b2f78c758",
     ".claude/rules/git-workflow.md": "7d8d2ded47fcc0fb95da3dc226efa6cb3c80d6adf7296977588c181dfce20192",
     ".claude/rules/insights-capture.md": "488d694caffe7a32915b0ec1beb7a84b223fe602722c5bb91ab8bf2785626387",
-    ".claude/rules/replicate-pipeline.md": "2eaa40ece405b506f0b94818013e2e235be6c9fb3bd73e964dd675afc34b6535",
+    ".claude/rules/replicate-pipeline.md": "b65e802d32a1e50bdfcd0cfc79c78e9234eac48a94f0cd1f5647cf4fea6c0162",
     ".claude/rules/skill-interface-protocol.md": "fe18fcb9217002572f462f3a7f38de22cdd7ba0dd4e906fdcd0c0e8cfed9f2aa",
-    ".claude/settings.json": "1afea754d42e3b2aa7cee0a17a8347ba594427b40daa293ce7b21f3dfd0607c3",
+    ".claude/settings.json": "b1df6cf834ccfa227f3318a70862115c17838ab31253e9d8d89381b7763e61fd",
     ".claude/skills/brutal-honesty-review/evals/brutal-honesty-review.yaml": "855c155d55575e12aab23fb3a5fb2fada74d93974ff755dfedac6f2d5bd41f13",
     ".claude/skills/brutal-honesty-review/README.md": "2a026b4af50b21456e50424fbfa089cb983fbbaa0c68024c8c17c695bea25a57",
     ".claude/skills/brutal-honesty-review/resources/assessment-rubrics.md": "dac09c91c765e2211799cc230738fb72a966f47511edb872306a906e49640cbe",
@@ -38,8 +40,8 @@
     ".claude/skills/brutal-honesty-review/scripts/assess-tests.sh": "8c6444bdb5ce97e49223cdaa6b1c58ac8fcec710cd6ee8d56de9bc677379bd88",
     ".claude/skills/brutal-honesty-review/scripts/validate-config.json": "7418284839f89735d01f50eefdb488b013e0076f6003a67683062429c14984c6",
     ".claude/skills/brutal-honesty-review/SKILL.md": "21e41129dac8e99485b501dcb3767d5f4461ce527782fa7bc71f89dabe5bd2bd",
-    ".claude/skills/cc-toolkit-generator-enhanced/modules/01-detect-parse.md": "45441d525ff5092766b9ab743e783dbf3b25e9f9515bdda888c8ca1cc3e0a6f0",
-    ".claude/skills/cc-toolkit-generator-enhanced/modules/02-analyze-map.md": "231ac3c42b800e26d035562633da79abd77ea90540e8d9245cc9360867dc91ab",
+    ".claude/skills/cc-toolkit-generator-enhanced/modules/01-detect-parse.md": "85c72f6daa5af88b4a7ff520a387f47a7c92b81cb1f0757550c8b58100a97be6",
+    ".claude/skills/cc-toolkit-generator-enhanced/modules/02-analyze-map.md": "5939f3fe6ae542fabb8e665dc373a20410d8de917362fcb3ecac504286f41836",
     ".claude/skills/cc-toolkit-generator-enhanced/modules/03-generate-p0.md": "b093a5d66663e2dfd6415afef7c7444409f03379f857001b811685ded410038b",
     ".claude/skills/cc-toolkit-generator-enhanced/modules/04-generate-p1.md": "081284d3858c5dd89b45fc8a2b83bbc0477843f864cbceb6d9f8c3629b198a0a",
     ".claude/skills/cc-toolkit-generator-enhanced/modules/05-generate-p2p3.md": "9535eaa5fa1be0804369aa4e8ee6f6f580839ea2c3c7b7aa51584e298a928093",
@@ -49,32 +51,47 @@
     ".claude/skills/cc-toolkit-generator-enhanced/modules/09-cross-project-learning.md": "c395bc42a40ed14c0b8fe274df516082db0490228c82aba6a56f23b8f41d3d43",
     ".claude/skills/cc-toolkit-generator-enhanced/modules/README.md": "9dbcc9c0978d06cbe31caffa909741fdb3a38d3cd1e6e98addf95628ec8394a0",
     ".claude/skills/cc-toolkit-generator-enhanced/references/claude-md-strategy.md": "88cdab1687096d58dc4450cdf81d24d00fdb493b2cc4960030b30fd57d1ca2da",
-    ".claude/skills/cc-toolkit-generator-enhanced/references/enhanced-recommendations.md": "0a828ed5302a3436ab9c21cdeeb2ebf47329031106dfb242517ca04f226033dd",
-    ".claude/skills/cc-toolkit-generator-enhanced/references/extended-mapping.md": "0c906fe8622ffa147a09af592ab75a8b1034b7634501e576da58e858477c3141",
+    ".claude/skills/cc-toolkit-generator-enhanced/references/enhanced-recommendations.md": "657e35db0cb77d3a9d1a4d01215a9b8d50441dd863593bee3a84f62aad8b00bc",
+    ".claude/skills/cc-toolkit-generator-enhanced/references/extended-mapping.md": "5e87c91956eabc70b4a1084b47b2c9a20ede18bb245735812ead956eafabf3af",
     ".claude/skills/cc-toolkit-generator-enhanced/references/maturity-integration.md": "aa4e743bcd0281525336a298d0489c31481f69ff1a534e1ed1d262d888937deb",
     ".claude/skills/cc-toolkit-generator-enhanced/references/security-patterns-library.md": "5f1d650c426cbd2c9536b385306605ea62a5a520ee4566d23ca7254409c672a5",
     ".claude/skills/cc-toolkit-generator-enhanced/references/templates/automation-commands.md": "23b8204fdc70b5afc5430cbe503af709a04b26716d2d2e07889283a755858fee",
-    ".claude/skills/cc-toolkit-generator-enhanced/references/templates/ddd-agents.md": "208619880fe6fea47b25f5f31a7fc5ef27f2a80b2235c2f8c1aa2b4140f48363",
+    ".claude/skills/cc-toolkit-generator-enhanced/references/templates/ddd-agents.md": "c91f81da197a072b57378fd0018eea26c35d909a558bdca6f070eb60153c97b3",
     ".claude/skills/cc-toolkit-generator-enhanced/references/templates/ddd-hooks-commands.md": "d70a0c4977d322602c35c53bf04880177b5dd8f0de2b339d68a0f55993903745",
-    ".claude/skills/cc-toolkit-generator-enhanced/references/templates/ddd-skills.md": "9cbdbc251026297ba30dca8b4311906a85ba7a8bf85fd35c41aa1dc358ec7574",
-    ".claude/skills/cc-toolkit-generator-enhanced/references/templates/enhanced-claude-md.md": "6121b4bec44fa726a8b70d6680c17ecf428fdf937bb3e13d9ee7e3b56ad33913",
+    ".claude/skills/cc-toolkit-generator-enhanced/references/templates/ddd-skills.md": "2f1019d5da7d695983aee79186a47fcefccbfa24db48219c04f9bb9feb757d3a",
+    ".claude/skills/cc-toolkit-generator-enhanced/references/templates/enhanced-claude-md.md": "db6898b7202b84965cbff9195a6ce780cadd6aeb64adae3fbfd951443a6bc43d",
     ".claude/skills/cc-toolkit-generator-enhanced/references/templates/feature-lifecycle-ent.md": "eb9025b687f0408b33280bf5fcc6c8be9b1670a544dd90b510557b89ae6cc123",
     ".claude/skills/cc-toolkit-generator-enhanced/references/templates/feature-lifecycle.md": "c537b47e7a4ff2d692767f4aac130e2ae9b1923782106750218696e87f515feb",
-    ".claude/skills/cc-toolkit-generator-enhanced/references/templates/feature-suggestions.md": "455fd4e4147f15175e1bb2dbfeda53d6ae0a4ac3f8d985544d0db5d24eba935d",
+    ".claude/skills/cc-toolkit-generator-enhanced/references/templates/feature-suggestions.md": "3b1c20d2394e180720447416767fbfae99168cf9ca846bf64907f6fe5cd906da",
     ".claude/skills/cc-toolkit-generator-enhanced/references/templates/insights-system.md": "244c2ef5f417c5d0097accf5ccfffd9de93d167efbfc6818cb9a8196139e096e",
     ".claude/skills/cc-toolkit-generator-enhanced/references/templates/mcp.md": "63d1e6dabf5bb29534e6fa11d9dd531ec55a48cda661f0faf7a29dad6f49296f",
-    ".claude/skills/cc-toolkit-generator-enhanced/references/templates/start-command.md": "67cf259f8d22c1b94c5242c6fd48d557e97581beb162cf176eb2e6851bab1962",
+    ".claude/skills/cc-toolkit-generator-enhanced/references/templates/start-command.md": "e037a7e73e65e5216f95f27a255009c4c2b95f0f2d6b7c575d70813efac34438",
     ".claude/skills/cc-toolkit-generator-enhanced/SKILL.md": "26fb1a3c0961fbb1f5f7e81ec5134bbe49ba0f99175c394cdf0c6b8a35568be2",
     ".claude/skills/explore/references/questioning-techniques.md": "ec0dd00871d3abe950f9cf375216a43043827897166c4165c3fa581839851195",
     ".claude/skills/explore/references/task-brief-templates.md": "4e9292479e120afce944b747bb7b4a7226c41e9880708d620de3ea4fa4ef0249",
-    ".claude/skills/explore/SKILL.md": "c755a7bcdfe97fb7cb0bcd7bf3b1fd8a2d238ef082967fbf87740fc808302542",
+    ".claude/skills/explore/SKILL.md": "2473e7961845db0d64566cd42627b374d1830664b9e302058a1b1aa466bc7361",
     ".claude/skills/goap-research-ed25519/references/ed25519-verification.md": "2742f14b472bff69c83f24d9bac5bf023bd7f9ecc3e659742ac3152a239dd68f",
     ".claude/skills/goap-research-ed25519/references/research-actions.md": "156d2f8ce342f7013bc758fe7c0d3ad3041b4f67f30dbcf8d59e091cb70d9a9c",
     ".claude/skills/goap-research-ed25519/references/source-evaluation.md": "d6a19abb6be64dc9e1f539903080029125d2d899da4de3063e75e1afb7e4906f",
-    ".claude/skills/goap-research-ed25519/scripts/ed25519_verifier.py": "dc9edc4d7907d13b28dfa74cc86b30a27a41de707ce72f39aca0ae08f07b5703",
-    ".claude/skills/goap-research-ed25519/scripts/goap_planner.py": "2ec359e1ddc52ca3118144532ed483dcc609e856a04b29bb191b875c60ff4260",
-    ".claude/skills/goap-research-ed25519/scripts/test_ed25519_verifier.py": "ea6d888ac53bac3a0fe236c101f90a984edbac044d787d73c8414f1c4fc540d3",
-    ".claude/skills/goap-research-ed25519/SKILL.md": "e23770a81922103571eb2645fb82509f7046bc7dd407a33b06f67ad2e709b9b4",
+    ".claude/skills/goap-research-ed25519/scripts/check_report_evidence.py": "5053e677f11d00b4dd8365a81eafa1d2c961eebd25c33f72b02455573a934a32",
+    ".claude/skills/goap-research-ed25519/scripts/ed25519_verifier.py": "f4a2ac9e6473201583643fe8abf47560863cec600344dad5c9df06091b4298f5",
+    ".claude/skills/goap-research-ed25519/scripts/evidence_fetch.py": "5f4d7cb5d6fb3106d64130b6606582eb55a4f633ef969cf7890b1de1c179345b",
+    ".claude/skills/goap-research-ed25519/scripts/fixture_legacy_v1_fact.json": "e613de4737145cbfb5f349fbf9f1122801ce3508b62c3a18e2e0cba26b9da5b0",
+    ".claude/skills/goap-research-ed25519/scripts/fixture_legacy_v2_fact.json": "3f552b47c3864e4ff7ae8c72516e98c188592c7f4f7703d09ce88b39f586ad9d",
+    ".claude/skills/goap-research-ed25519/scripts/fixtures_field_cases.json": "e2ee619732ab4a1b57285e57b4349f96b4158b231a5624e5264fadf69edb8983",
+    ".claude/skills/goap-research-ed25519/scripts/goap_planner.py": "f5cbf4784106710b363e7f29bfa538b75f488cb25e1c273ae40de9f4c2a6710b",
+    ".claude/skills/goap-research-ed25519/scripts/learning_bridge.py": "74f8842978ba945ff78c2bd54702415dd87122e61919571e12a19c3cf1e56131",
+    ".claude/skills/goap-research-ed25519/scripts/population_match.py": "bbd1d3346a6fb75d0e8526cb5d2fc8bc8613bb31ab63ffb0958d436d5e009054",
+    ".claude/skills/goap-research-ed25519/scripts/risk_statement.py": "320ffece816e875f65624583846f44dc99461f672a0de7cda42be5ddf29d6de5",
+    ".claude/skills/goap-research-ed25519/scripts/source_tiers.py": "e1aae76fad01693ab35b51466fc4369c04a5ac64230fd307e7b798dc5beeff7a",
+    ".claude/skills/goap-research-ed25519/scripts/test_ed25519_verifier.py": "dcba1ce538ff946d6928f30a7c5cbcc37fddf712b6181f91f94c76e20c117ac5",
+    ".claude/skills/goap-research-ed25519/scripts/test_evidence_provenance.py": "292bfcdcc086934905c77f1543d8400ee483166ff3ce26c79bb526c204320dbb",
+    ".claude/skills/goap-research-ed25519/scripts/test_goap_planner.py": "7942ada069048b7e97bf2b6e920898a58517ccec090069f347399dbf1fc37731",
+    ".claude/skills/goap-research-ed25519/scripts/test_population_match.py": "f33f72c0ba6305af1644e6b1a7f7635d3f33273344f19c14e7dbd2f819af0e7f",
+    ".claude/skills/goap-research-ed25519/scripts/test_risk_absolute.py": "ab353db189650551c374cb772ba4a3a6929e3a2618f2f5c112eca4c3f69e46b6",
+    ".claude/skills/goap-research-ed25519/scripts/test_signature_v3.py": "a04259296df104c9497c7b31d29556cb9a7ad4dd3339cbe3d8d32a4f53950d25",
+    ".claude/skills/goap-research-ed25519/scripts/test_suite_completeness.py": "727c5d5b0dad215957012276ebc146397178255077e762ed7b88a60d8178d2ab",
+    ".claude/skills/goap-research-ed25519/SKILL.md": "404cb696d537d29585ec35f97a86173a582cd6fcf8d5f172a4f5bbd75ec971a8",
     ".claude/skills/knowledge-extractor/examples/rate-limiting-extraction.md": "fab68772135532aaa7675dfca4ec068cfa68a847f964f872f201f08fb9ee4034",
     ".claude/skills/knowledge-extractor/modules/01-agent-review.md": "53883f182c26c710190399a23193cddb4a94b0f35bb42169a353f354aae4083a",
     ".claude/skills/knowledge-extractor/modules/02-classify.md": "3b6a59cde451fc89e2e683b7cd35f5535d12cc6072cd40ca35cf7d5f61eb78aa",
@@ -97,13 +114,13 @@
     ".claude/skills/pipeline-forge/templates/command-template.md": "b91a4ef084ba542801154c8b1fb2a086a6b404c3f7ee809ceb6ea633e2b55245",
     ".claude/skills/pipeline-forge/templates/pipeline-template.md": "952d2e1f050558dacbf86d2b2ad2c9bc671b1ce2809ce430593434998103a27c",
     ".claude/skills/pipeline-forge/templates/skill-template.md": "b92775b4d181fc70ae393645999472ddb64f7419392c12d86b4182b49308df65",
-    ".claude/skills/problem-solver-enhanced/SKILL.md": "530623c986dee931d47314c22195ea9de50a75f2a0daecfc469fb015c3dd3415",
+    ".claude/skills/problem-solver-enhanced/SKILL.md": "031378aa2e10c98928e35de07d454135e73550cd0c49f0cd886d53e4208d6b9f",
     ".claude/skills/requirements-validator/assets/templates/bdd-feature-template.feature": "5b1e47f10447ce574d0eb3917b69e2613b6e3f9c48b30ff5f4cfb57758c99a1d",
     ".claude/skills/requirements-validator/references/bdd-patterns.md": "04611a8c52c81f3a6d4fc2f9661ebc56159a125b6fb44a4d18b432e2b82de6e3",
     ".claude/skills/requirements-validator/references/invest-criteria.md": "ac6976adf776b9b60c784e1a0f6a0d96dd3332b16f4c12b72d3e59f9325bb626",
-    ".claude/skills/requirements-validator/references/scoring-system.md": "79d421c79ab2cc594e685c27178368495774a1154e2b65cdbcd2a94cc28e9dbb",
+    ".claude/skills/requirements-validator/references/scoring-system.md": "49afe072f31f5b4f9a33f6b59487244f494b0f5587b6cc10c797c4de59510114",
     ".claude/skills/requirements-validator/references/smart-criteria.md": "619a33fdb6bc336872fdf9f1fc91924f8ccd3c2ebef023912124756692b45aef",
-    ".claude/skills/requirements-validator/SKILL.md": "baa5cf7257de711ad64d4233ff5a26eb4573fb75a3392fda9a75c2c2e5a73ef9",
+    ".claude/skills/requirements-validator/SKILL.md": "e50c5269ad181966a81c14ef596946cea67cbf4b8f8f648c90fd66ecad948933",
     ".claude/skills/reverse-engineering-unicorn/examples/noom-cjm-example.md": "01d33586e26bf093a57a7a1082bf3bdba3af801bb8348a685c0418f76987a0b0",
     ".claude/skills/reverse-engineering-unicorn/examples/noom-module1-example.md": "7009cf2e2624a1254913ad2e1ff554e7ff675358b0b99bc0632f2e12132663a3",
     ".claude/skills/reverse-engineering-unicorn/modules/01-intelligence.md": "4af16873637c26baba0d30728748108c79f5b96765de08d54fc65fe1008f4280",
@@ -116,9 +133,9 @@
     ".claude/skills/reverse-engineering-unicorn/references/blue-ocean-canvas.md": "9256455b4b0f2c8c5aecb472e69cfbeda38bed8239120b45b46beec27571f8f9",
     ".claude/skills/reverse-engineering-unicorn/references/industry-benchmarks.md": "d377f4d9e84b8b65860fb4d20ce67d928f8a8fc8ef333658f88c8c54674eed71",
     ".claude/skills/reverse-engineering-unicorn/references/jtbd-canvas.md": "7938e657af631109ca7b4752002c21ac84a7dad3a35cc522be088f814d102773",
-    ".claude/skills/reverse-engineering-unicorn/SKILL.md": "ad667aa11254dcd0612689efc3bccd95db537720f5e5846583efe21c631a9375",
+    ".claude/skills/reverse-engineering-unicorn/SKILL.md": "20d6b667971f9749d091c1d47e2f75df957f259647cbb861ac54174280096c71",
     ".claude/skills/sparc-prd-mini/references/sparc-methodology.md": "9c93dafe8149590809ff6b27508d7df52c8efa7f31f8e8f8052b7124a6561fee",
-    ".claude/skills/sparc-prd-mini/SKILL.md": "2555c4de0edce73f6c2f637db1d839900c7fa27a7d25ca88ec0cf5a70a47325d",
+    ".claude/skills/sparc-prd-mini/SKILL.md": "50e829635b828b444487e4b04219518a595dbd4b94f91b66fb03ddf4a7b21712",
     ".claude/skills/sparc-prd-mini/templates/CLAUDE.md": "9eeb66752cc4dec5c3c3fa5a8f7cfc3dd282f75d245bd36835f690a945b534ed",
     ".claude/skills/sparc-prd-mini/templates/prd.md": "7b4497bc76bb421fae7a07ecb46af01e021412180a394a5487a3c3c42dc004b6"
   }

package/tests/snapshot/update-baseline.js

@@ -44,7 +44,8 @@ function sha256(filePath) {
 function main() {
   if (!fs.existsSync(TEMPLATES)) {
     console.error(`[snapshot] templates/ not found at ${TEMPLATES}`);
-    console.error('[snapshot] Run prepublishOnly first: node scripts/sync-templates.js');
+    console.error('[snapshot] templates/ ships with this package — a missing one means a broken');
+    console.error('[snapshot] checkout, not a missing build step. Restore it from git.');
     process.exit(1);
   }
 

package/tests/unit/adr-decision-coverage.test.js

@@ -0,0 +1,137 @@
+'use strict';
+
+// /replicate writes docs/ADR.md in Phase 1 — commands/replicate.md:243, "(if applicable)" — and
+// nothing ever reads it again. A decision could be written down, agreed, and quietly not built.
+//
+// This cannot be a script: MEASURED, `find templates -name '*.mjs' -o -name 'check*.js'` returns
+// nothing — the templates carry no executable gate at all. It is a mandatory prose step held by this
+// test, the shape that shipped for scenario coverage the day before.
+//
+// TWO TRAPS INHERITED VERBATIM from that sibling, both found the expensive way:
+//   - PLACEMENT. A step inside the fenced [MANUAL] checkpoint block is skipped by an AUTO run, so a
+//     "mandatory" step would run in half of runs. "Precedes the checkpoint text" and "outside the
+//     MANUAL-only block" are two different facts and only the second is the property.
+//   - BOTH DIRECTIONS. A one-way check lets a reference to a decision nobody wrote read exactly like
+//     coverage.
+//
+// WHAT THIS CLAIMS, and the artifact says so itself: a decision is NAMED downstream. NOT that it was
+// implemented — no comparison of identifiers can establish that. The nearest precedent, the K2 gate,
+// records the same limit about its own coverage check in its own source.
+
+const { test, describe } = require('node:test');
+const assert = require('node:assert/strict');
+const fs = require('node:fs');
+const path = require('node:path');
+
+const REPLICATE = path.join(__dirname, '..', '..', 'templates', '.claude', 'commands',
+  'replicate.md');
+const read = () => fs.readFileSync(REPLICATE, 'utf-8');
+
+/** Phase 2, from its heading to Phase 3's. */
+function phase2(src) {
+  const start = src.indexOf('### Phase 2: VALIDATION');
+  const end = src.indexOf('### Phase 3', start + 1);
+  assert.ok(start > 0 && end > start, 'replicate.md must have a Phase 2 before Phase 3');
+  return { start, end, text: src.slice(start, end) };
+}
+
+describe('a recorded decision cannot be quietly left unbuilt (PR-007 G5)', () => {
+  test('P1 — the step is INSIDE Phase 2 and OUTSIDE the [MANUAL] checkpoint block', () => {
+    const src = read();
+    const { text } = phase2(src);
+    const step = text.indexOf('**Шаг 2.9 — ПОКРЫТИЕ РЕШЕНИЙ');
+    assert.ok(step > 0, 'the coverage step must live inside Phase 2');
+
+    const checkpoint = text.indexOf('**Checkpoint:**');
+    assert.ok(checkpoint > step,
+      'and BEFORE the checkpoint, not after it: ' + step + ' vs ' + checkpoint);
+
+    // The checkpoint's body is a fenced block an AUTO run may skip. The step must not be in it —
+    // and this is asserted from the FENCE, not inferred from the ordering above, because those are
+    // two different facts and the sibling feature shipped the weaker one first.
+    const fenceStart = text.indexOf('```', checkpoint);
+    const fenceEnd = text.indexOf('```', fenceStart + 3);
+    assert.ok(fenceStart > 0 && fenceEnd > fenceStart, 'the checkpoint must have a fenced body');
+    assert.ok(step < fenceStart || step > fenceEnd,
+      'the step sits inside the MANUAL-only fenced block, where an AUTO run skips it');
+  });
+
+  test('P2 — the reconciliation runs BOTH ways, and both may say none', () => {
+    const { text } = phase2(read());
+    assert.match(text, /Recorded but named nowhere:/,
+      'decisions nobody mentions must be listed');
+    assert.match(text, /Named downstream but absent from docs\/ADR\.md:/,
+      'and references matching no decision — without this, a dangling ADR-009 reads as coverage');
+    assert.match(text, /Both tables are required, and both may be the single word `none`/,
+      'an empty table and a forgotten table look identical');
+  });
+
+  test('P3 — the block is required in EVERY case, including all-covered', () => {
+    const { text } = phase2(read());
+    assert.match(text, /## Decision Coverage/,
+      'the required output block must be named, or "reconcile" is advice');
+    assert.match(text, /in every case\*\*, including\s+the one where everything is covered/,
+      'an absent block and a block saying "all covered" are indistinguishable to the next reader');
+  });
+
+  test('P4 — three states of the ADR file, each with its own line', () => {
+    // Cross-family QE found two defects here. The first version had ONE empty case, so an ADR file
+    // that exists but records no ids was unclassified. And its sentence claimed the project "recorded
+    // no architectural decisions" — which absence of one FILE cannot establish; decisions may live
+    // where this step does not look, and asserting otherwise is a false claim in a generated report.
+    const { text } = phase2(read());
+    assert.match(text, /Three states of the ADR file/, 'all three must be enumerated');
+    assert.match(text, /docs\/ADR\.md is absent, so no decision ids were collected from it/,
+      'the absent case must say what is absent — the FILE — and nothing more');
+    assert.ok(!/recorded no architectural decisions/.test(text),
+      'the step must not claim what it cannot see: decisions may live elsewhere');
+    assert.match(text, /exists but records no decision ids/,
+      'a present-but-empty ADR is a third state, not the same as an absent file');
+    assert.match(text, /In all three states the second table\s*\n?still runs/,
+      'a dangling reference is a defect whether or not an ADR file was ever written');
+  });
+
+  test('P7 — the searched files are ENUMERATED, and the two self-defeating ones excluded', () => {
+    // The finding that mattered most: "across the SPARC documents" did not exclude docs/ADR.md, whose
+    // own headings contain every id — so every decision appeared named and the check passed BY
+    // CONSTRUCTION, on any project. And docs/validation-report.md is where this step WRITES, so
+    // counting it would let the previous run's output satisfy the next one.
+    const { text } = phase2(read());
+    assert.match(text, /Where to look, named file by file/,
+      'the search set must be enumerated, not described');
+    for (const f of ['docs/PRD.md', 'docs/Specification.md', 'docs/Architecture.md']) {
+      assert.ok(text.includes(f), 'the search set must name: ' + f);
+    }
+    assert.match(text, /Two files are EXCLUDED/, 'and the exclusions must be explicit');
+    assert.match(text, /the check would pass by construction/,
+      'with the reason for excluding the ADR file itself');
+    assert.match(text, /the check would start proving itself/,
+      'and for excluding the report this step writes');
+  });
+
+  test('P8 — a mention is DEFINED, and a superseded decision has a policy', () => {
+    const { text } = phase2(read());
+    assert.match(text, /The exact token `ADR-<nnn>`, case-sensitive/,
+      '"mention" must be defined, or every reader draws a different line');
+    assert.match(text, /Not a title, not a paraphrase/,
+      'and what does NOT count must be named too');
+    assert.match(text, /A superseded decision needs no current mention/,
+      'an id that outlives its decision needs a stated policy, or it reads as a permanent gap');
+  });
+
+  test('P5 — the artifact states its own limit', () => {
+    // A coverage block LOOKS like proof of implementation. The backlog item demanded this restraint
+    // explicitly, and the limit belongs in the template a reader sees, not only in a feature report.
+    const { text } = phase2(read());
+    assert.match(text, /It does NOT establish that the decision was implemented/,
+      'the limit must be written into the artifact');
+    assert.match(text, /the decision was written down and then forgotten/,
+      'and the class it DOES catch must be named, so the claim is bounded on both sides');
+  });
+
+  test('P6 — the decision id has a defined form, or there is nothing to trace on', () => {
+    const { text } = phase2(read());
+    assert.match(text, /`ADR-<nnn>` — three digits, assigned in order, never\s+reused/,
+      'an id without a form and a uniqueness rule is an intention, not an identifier');
+  });
+});