@bonesofspring/ai-rules 0.2.19 → 0.2.21

package/presets/cursor/next/hooks/chain-team-phases.sh

@@ -138,6 +138,14 @@ const DEFAULT_ARTIFACT_OUTPUT_IDS = {
   'mockup-reviewer': 'mockup-review',
   'api-contract-reviewer': 'api-contract-review',
   'tech-writer': 'documentation',
+  'openspec-author': 'openspec-change',
+  'qa-tester': 'qa',
+  'unit-test-planner': 'unit-test-plan',
+  'unit-test-generator': 'unit-test-spec',
+  'unit-test-healer': 'unit-test-heal',
+  'playwright-test-planner': 'e2e-plan',
+  'playwright-test-generator': 'e2e-spec',
+  'playwright-test-healer': 'e2e-heal',
 };
 function artifactOutputIdFor(step, agent) {
   if (step && typeof step.artifactOutputId === 'string') return step.artifactOutputId;
@@ -244,7 +252,17 @@ function recordSkippedStep(step, stepIndex) {
 function writeStatus(next) {
   status = { ...status, ...next, slug, updatedAt: now };
   const temporary = `${statusPath}.${process.pid}.${Date.now()}.tmp`;
-  fs.writeFileSync(temporary, JSON.stringify(status, null, 2) + '\n');
+  // Open + write + fsync + rename so the durable file lands on disk before
+  // the orchestrator reads it. Closes the race window where a subagent that
+  // completed milliseconds before writeStatus() could otherwise invoke the
+  // next step on a stale status (in particular the human-gate write).
+  const fd = fs.openSync(temporary, 'w');
+  try {
+    fs.writeSync(fd, JSON.stringify(status, null, 2) + '\n');
+    try { fs.fsyncSync(fd); } catch {}
+  } finally {
+    fs.closeSync(fd);
+  }
   fs.renameSync(temporary, statusPath);
 }
 
@@ -341,6 +359,12 @@ const AGENT_HANDOFF = {
     `Use playwright MCP when available. Follow playwright-agents.mdc and debug-investigation. Upsert the owned terminal receipt in artifact-manifest.json; do not mutate status.json lifecycle fields.`,
   'tech-writer': (s) =>
     `Invoke tech-writer for slug "${s}". Write documentation.md from task artifacts. Upsert the owned terminal receipt in artifact-manifest.json; do not mutate status.json lifecycle fields.`,
+  'openspec-author': (s, scope) =>
+    `Invoke openspec-author for slug "${s}"${scope ? ` (scope: ${scope})` : ''}. ` +
+    `Read openspec/config.yaml schema + rules; if openspec/** is absent, emit blocked ("openspec/** not initialized"). ` +
+    `Author openspec/changes/<change-id>/{proposal.md, design.md, tasks.md, .openspec.yaml} and the capability spec delta per phase (explore|propose|apply|archive). ` +
+    `Run \`openspec validate <change-id> --type change --strict\` and \`openspec validate --specs --strict\` (Phase 3); surface FAIL output verbatim. ` +
+    `Upsert the owned terminal receipt (artifactOutputId \`openspec-change\`) in artifact-manifest.json with validator exit code + evidence paths; do not mutate status.json lifecycle fields. `,
 };
 
 const REVIEW_AGENTS = new Set([
@@ -514,9 +538,37 @@ if (!fs.existsSync(pipelinePath)) {
 }
 
 let pipeline;
+let pipelineParseError = null;
 try {
   pipeline = JSON.parse(fs.readFileSync(pipelinePath, 'utf8'));
-} catch {
+} catch (error) {
+  pipelineParseError = error;
+}
+// Modern pipelines carry an `intent` field. If pipeline.json is present but
+// unparseable, surface the error so the orchestrator can stop and report
+// instead of falling back to legacyFlow() — which silently drops modern
+// roles like `openspec-author`, `qa-tester`, and the test-planner trio.
+if (pipelineParseError) {
+  if (fs.existsSync(pipelinePath)) {
+    const raw = fs.readFileSync(pipelinePath, 'utf8');
+    const hasModernIntent = /"intent"\s*:/.test(raw);
+    appendMetric({
+      eventId: `${status.metricsRunId || slug}:pipeline_parse_error:${Date.now()}`,
+      type: 'pipeline_parse_error',
+      at: now,
+      source: 'hook',
+      attributionConfidence: 'high',
+      error: String(pipelineParseError.message || pipelineParseError),
+      hasModernIntent,
+    });
+    if (hasModernIntent) {
+      writeStatus({ state: 'blocked', phase: 'blocked', currentAgent: 'task-router' });
+      process.stdout.write(JSON.stringify({
+        followup_message: `pipeline.json is malformed for slug "${slug}" — JSON parse error: ${pipelineParseError.message}. Re-run the task-router to regenerate pipeline.json, then resume via /task-continue ${slug}.`,
+      }));
+      process.exit(0);
+    }
+  }
   legacyFlow();
 }
 

package/presets/cursor/next/rules/README.md

@@ -14,13 +14,14 @@ Special Cursor Rule format:
 ### Starting a new task
 
 - **Agent team (recommended):** `/task <description>` — router picks roles and order; on human gate — `/task-continue <slug>`. See **`agent-team-orchestrator.mdc`** and `.cursor/team/README.md`.
-- **Legacy:** `/feature-start` → `/feature-continue`.
+
 - **End-to-end layer checklist (for developer):** **`feature-delivery-workflow.mdc`**.
 
 ### Loading strategy
 
-- **`alwaysApply: true`** (Cursor) / **without `paths:`** (Claude) — only base invariants (**3**):
-  - `next-app-core`, `package-manager`, `code-quality-and-refactoring`
+- **`alwaysApply: true`** (Cursor) / **without `paths:`** (Claude) — base invariants (**Cursor ≤4**, Claude exactly 3):
+  - Cursor: `next-app-core`, `package-manager`, `code-quality-and-refactoring`, `ai-local-overlay`
+  - Claude: `next-app-core`, `package-manager`, `code-quality`
 - **On-demand / requestable** — `post-change-lint` (**required after code edits**, not always-on), `agent-team-intake` (via orchestrator/commands), `agent-team-orchestrator`, architecture, imports, UI, tests, feature-delivery-workflow, `design-guidance`, `mcp-usage`, `anti-sycophancy-discipline`, `react-next-anti-hallucination`, reference-features, product-specs, product-specs-authoring, next-app-router, `security-next`, react-a11y-coding, `technical-retro`, `mockup-review`, `ux-design`
 - **Preset author meta** (globs `packages/ai-rules/presets/**`, never alwaysApply): `preset-layering`, `preset-twin-sync`, `preset-token-budget`, `preset-pr-checklist`, `preset-no-cross-stack-leakage`
 - **Skills** — long procedures (`feature-delivery`, `spec-authoring`, `spec-discovery`, `code-review`, …)
@@ -46,6 +47,8 @@ SoT prose: `packages/ai-rules/presets/_shared/core/**` (see `_shared/README.md`)
 | `review/mockup-review.md` | `mockup-review.mdc` | Stack notes breakpoints; requestable |
 | `review/ux-design.md` | `ux-design.mdc` | Stack notes form-factor; requestable |
 | `meta/preset-*.md` | `preset-*.mdc` | author-only globs |
+| `testing/testing-principles.md` | `tests-unit.mdc` | Stack notes: `@testing-library/react`, `userEvent`, DOM matchers, `app/eslint.config.mjs` `jest/valid-title`, `app/src/mocks/**`, `app/src/lib/clients/**` |
+| `testing/testing-principles.md` | `tests-e2e-structure.mdc` | Stack notes: Playwright, `*.cases.md`, `_shared` folder, `{parent}__{element}` data-testid, `PREFIX-XXX` |
 
 Claude twins + Cursor→Claude map: `presets/claude/next/rules/README.md`.
 

package/presets/cursor/next/rules/agent-team-orchestrator.mdc

@@ -1,5 +1,5 @@
 ---
-description: Orchestrates the agent team via task-router and pipeline.json. Use for /task, /task-continue, /feature-start, task decomposition, or when the user describes a feature, bug, or review request.
+description: Orchestrates the agent team via task-router and pipeline.json. Use for /task, /task-continue, task decomposition, or when the user describes a feature, bug, or review request.
 alwaysApply: false
 ---
 
@@ -17,8 +17,6 @@ Work request without `/task` — see **`agent-team-intake.mdc`** (when to sugges
 |---------|------|
 | **`/task <desc>`** | **Preferred** — router → dynamic pipeline → first agent |
 | `/task-continue <slug>` | After human gate or pause |
-| `/feature-start <desc>` | Legacy: analyst-only start (no router) |
-| `/feature-continue <slug>` | Alias of task-continue |
 | `/spec-start [desc]` | Generate/bootstrap `docs/specs` — router intent `spec-gen` → analyst author mode → human gate |
 | `/technical-retro [slug]` | Retro with agent team block |
 
@@ -57,7 +55,7 @@ Full prompts: `.cursor/agents/*.md`. Artifact conventions: `.cursor/team/README.
 
 **Behavioral UX:** `task-analyst` loads requestable skill `ux-design` for standalone intent `ux-design` and embedded required-signal / advisory UI AC. No `ux-designer` agent in v1.
 
-**Product specs:** When `/task`, `/feature-start`, or `/spec-start` touches pages/features/`docs/specs`: if INDEX exists and no generate intent → instruct next agent to load requestable **`product-specs`** (consume; soft-fail; never invent). If generate/bootstrap/`spec-gen` → load **`product-specs-authoring`** + skill **`spec-authoring`** inside **task-analyst** (not a separate pipeline step); pass created spec paths + INDEX diff in handoff; human gate must approve before feature-developer. No-op if INDEX absent and no author intent.
+**Product specs:** When `/task` or `/spec-start` touches pages/features/`docs/specs`: if INDEX exists and no generate intent → instruct next agent to load requestable **`product-specs`** (consume; soft-fail; never invent). If generate/bootstrap/`spec-gen` → load **`product-specs-authoring`** + skill **`spec-authoring`** inside **task-analyst** (not a separate pipeline step); pass created spec paths + INDEX diff in handoff; human gate must approve before feature-developer. No-op if INDEX absent and no author intent.
 
 When editing `packages/ai-rules/presets/**`, follow **`preset-pr-checklist.mdc`** (+ twin-sync / layering / token-budget / leakage meta-rules).
 
@@ -180,7 +178,7 @@ After each agent completes, verify its terminal manifest receipt, then let the o
 
 ## Legacy mode
 
-If `pipeline.json` is missing (old `/feature-start` tasks), fall back to fixed phases: analysis → development → review → testing. Hook supports both.
+If `pipeline.json` is missing, fall back to fixed phases: analysis → development → review → testing. Hook supports both.
 
 ## Skip pipeline when
 
@@ -196,3 +194,7 @@ Borderline work requests — see **`agent-team-intake.mdc`**.
 ## Auto-detection (optional)
 
 When user describes a **non-trivial task** (not a question), suggest `/task <message>` or run router if they agree.
+
+## Preset authoring
+
+When the work edits `packages/ai-rules/presets/**` (or dogfood `.cursor/` sync of presets), follow meta-rules: **preset-pr-checklist**, **preset-twin-sync**, **preset-layering**, **preset-token-budget**, **preset-no-cross-stack-leakage**.

package/presets/cursor/next/rules/ai-local-overlay.mdc

@@ -0,0 +1,43 @@
+---
+description: Local overlay from .ai.local/ (consumer-owned rules with priority over preset rules) — MANDATORY
+alwaysApply: true
+impact: CRITICAL
+---
+
+# Local overlay (`.ai.local/`) — MANDATORY
+
+This rule is mandatory. **You MUST** obey it on every turn, without exception.
+
+## On every turn
+
+1. **Probe** — before answering, run `ls -la .ai.local` from the repository root.
+2. **Walk** — if `.ai.local/` exists at multiple levels (monorepo), read every level from root to leaf. **Deeper wins** in practice: more specific rules appear later in the assembled context and take precedence.
+3. **Apply** — treat every `.ai.local/rules/*.md` and `.ai.local/conventions.md` as a higher-priority rule for this repo. The block below ("Authoring `.ai.local/rules/*.md`") defines the conventions.
+4. **Conflict** — if a local rule conflicts with a preset rule, **the local rule wins**. If a local rule body contains `override: kill <preset-rule-name>`, drop that preset rule from your context window entirely.
+5. **Acknowledge** — when answering a user question, briefly state which `.ai.local/` rules apply to the current task (one line is enough). Format: `Using .ai.local: <rule-name>(, <rule-name>)*`. If no `.ai.local/` exists, do NOT mention this rule.
+
+If `.ai.local/` does not exist → **no-op**, do not error. Do not produce any log line about its absence.
+
+## Authoring `.ai.local/rules/*.md` (consumer-side reference)
+
+Each `.ai.local/rules/<name>.md` is a plain-markdown rule body. The model parses it as:
+
+- Lines before `## Body` are scope metadata. Only `glob:` / `globs:` / `override:` lines are recognised.
+- Everything from `## Body` onward is the rule body.
+- `glob: always` → always-on. Counts against your context budget.
+- `globs: <comma-separated globs>` → on-demand; applies only when matching files are in focus.
+- `override: kill <preset-rule-name>` → drop that preset rule from context.
+
+Keep files ≤ 120 lines. Match the style of preset rules (short sections, bullets, code examples).
+
+## Limitations (read this)
+
+- Cursor/Claude do **not** natively read `.ai.local/`. This rule is a **prompt-only** mechanism: it asks you, the model, to read and apply the files. Reliability is high but not 100%.
+- If a user adds a file to `.ai.local/` mid-session, **restart the session** to be sure it is picked up.
+- "Priority" is **contextual**, not enforced. Always re-read the local rule before answering questions that touch it.
+
+## Pointers
+
+- Authoring guide: `docs/LOCAL-OVERLAY.md` in the `@bonesofspring/ai-rules` package.
+- Living gotchas alternative: `.cursor/team/conventions.md`.
+- Root `AGENTS.md` reinforces this rule with a `MANDATORY` section.

package/presets/cursor/next/rules/preset-pr-checklist.mdc

@@ -19,11 +19,15 @@ Checklist for PRs that touch `packages/ai-rules/presets/**` (and dogfood `.curso
 - [ ] **Core:** if `_shared/core/**` changed — all `<!-- shared-core: … -->` consumers updated (or documented intentional fork)
 - [ ] **Twin:** Cursor change → Claude twin **same PR** (**FAIL** if missing on next, nuxt, svelte, ios-swift, android-kotlin, go, java, mcp-ts, php-hexagonal, and php-laravel — see `preset-twin-sync`)
 - [ ] **Mapping:** `claude/<stack>/rules/README.md` mapping table is current
-- [ ] **Token budget:** alwaysApply / session-start ≤ 3; meta rules not always-on
+- [ ] **Token budget:** Cursor `alwaysApply` ≤ 4 (4th slot reserved for `ai-local-overlay`); Claude session-start exactly 3; meta rules not always-on
+- [ ] **Local overlay coverage:** every installable stack ships `ai-local-overlay.mdc` (Cursor) and `ai-local-overlay.md` (Claude) with `MANDATORY` + acknowledgement format + `docs/LOCAL-OVERLAY.md` pointer; Claude twin listed in `claude/<stack>/rules/README.md` mapping table. Run `packages/ai-rules/scripts/check-local-overlay.sh`.
 - [ ] **Leakage:** no foreign stack agent stems / handoff strings (`preset-no-cross-stack-leakage`)
+- [ ] **Hook-only lifecycle:** `status.json` / `metrics.json` writes happen only inside `hooks/`; agents read but never rewrite lifecycle fields. Run `packages/ai-rules/scripts/check-hook-only-lifecycle.sh`.
+- [ ] **Chain fork:** the byte-wise MD5 uniqueness of `chain-team-phases.sh` across the 10 stacks × 2 platforms (20 hooks) holds. Run `packages/ai-rules/scripts/check-chain-hook-coverage.sh` and `packages/ai-rules/scripts/test-chain-team-phases-coverage.mjs`.
 - [ ] **Twin depth:** domain ≥15 lines; thin aliases documented
 - [ ] **README:** stack `rules/README.md` core→stack mapping / catalog updated if stems added
 - [ ] **CHANGELOG / package README:** note when public preset paths or install surface change
+- [ ] **i18n anchors:** kept-marked Cyrillic fragments in `tests-unit.md(c)` stay consistent with their English counterparts. Run `packages/ai-rules/scripts/check-preset-i18n.sh`.
 - [ ] **Dogfood:** run `packages/ai-rules/scripts/sync-dogfood-cursor.sh` (or document intentional skip) when maintaining this monorepo
 - [ ] **shared-core drift:** for embed-mode stems, run `packages/ai-rules/scripts/check-shared-core-drift.sh` (or document intentional fork)
 

package/presets/cursor/next/rules/preset-token-budget.mdc

@@ -17,12 +17,16 @@ Invariants for rule loading in an **installed** preset (consumer app).
 
 | Platform | Always-on | Cap |
 |----------|-----------|-----|
-| Cursor | `alwaysApply: true` | **≤ 3** |
+| Cursor | `alwaysApply: true` | **≤ 4** |
 | Claude | rules **without** `paths:` | **exactly 3** |
 
+**Cursor 4th slot is reserved for `ai-local-overlay`** (consumer-owned `.ai.local/` rules). If you do not need local overlay, demote that rule to `globs: ["**/.ai.local/**"]` and revert to ≤3.
+
 **Claude Option A (README exclusion):** when counting Claude rules without `paths:` / session-start, **exclude `**/README.md`** (topic indexes are not session-start rules). The intended session-start trio remains **exactly 3**; body budget sums **only those 3** rules.
 
-Session-start body budget (where documented): ≤140 lines total (stretch ≤120).
+Session-start body budget:
+- Claude trio: ≤140 lines total (stretch ≤120).
+- Cursor 4-set: ≤170 lines total (4 rules including `ai-local-overlay`).
 
 ## Meta / author rules
 
@@ -38,4 +42,4 @@ Orchestrator, feature-delivery, code-review, post-change gates, domain globs —
 
 ## Verifier
 
-build-verifier **FAIL** if alwaysApply / session-start count exceeds 3 (Claude count **excludes `**/README.md`**), or if a `preset-*` meta rule is marked always-on.
+build-verifier **FAIL** if Cursor `alwaysApply` count exceeds 4, Claude session-start count exceeds 3 (Claude count **excludes `**/README.md`**), or if a `preset-*` meta rule is marked always-on.

package/presets/cursor/next/rules/preset-twin-sync.mdc

@@ -39,6 +39,8 @@ Cursor `.mdc` — **SoT per stack**. Claude topic `.md` — derived twin.
 
 - **Domain** rules: ≥15 body lines (FAIL if thin without documented alias reason).
 - **Thin aliases** (`agent-team-intake`, `technical-retro`): may be shorter (soft) if they only point to a command/skill.
+- **Slim-companion rules** (UI-edit bundle, slim app-cores, slim tooling): may be shorter than 15 lines **if and only if** the body is a pointer into shared-core / stack-prose (no standalone prose). Examples live in stack `rules/README.md` (e.g. `cursor/next/rules/README.md` "UI-edit bundle" intent).
+  - **Mechanical enforcement is pending.** Today build-verifier excludes only `agent-team-intake` / `technical-retro` / `preset-layering`; slim-companion rules currently pass under the same human-judgement path as thin aliases. Follow-up: add `allow_slim_stems` to `packages/ai-rules/scripts/check-preset-token-budget.sh` analogous to `trio_stems_allowlist`.
 
 ## Severity (build-verifier)
 

package/presets/cursor/next/rules/tests-e2e-structure.mdc

@@ -4,48 +4,88 @@ globs: app/__tests__/e2e/**/*
 alwaysApply: false
 ---
 
-# E2E structure in the project
+<!-- shared-core: testing/testing-principles.md -->
 
+# Testing principles
+
+Stack-agnostic; concrete paths, runners, and selectors live in the stack adapter (`## Stack notes`).
+
+## Behavior vs. implementation
+
+- Verify **behavior and business rules**, not implementation or internal details.
+
+## File naming
+
+- For **new** tests use `*.spec.ts` / `*.spec.tsx`. Do not rename existing `*.test.ts` / `*.test.tsx` without a separate task (legacy).
+
+## Runner and matchers
+
+- Use the project's runner (Jest or Vitest are common); components — the project's Testing Library integration. Reuse existing matchers — no new micro-framework.
+
+## Test title locale
+
+- Consumer apps **may use the project locale** (often Russian) — clear business phrases stating what is checked and the expected outcome.
+- When ESLint enforces the locale (e.g. `jest/valid-title`): each sentence must start with a **capital letter** (including after `.`, `!`, `?`); a space after `.` followed by a lowercase letter is forbidden ("capital after period" violation).
+
+Good (Russian locale in consumer app):
+
+- `it('Возвращает пустой список. Пользователь не авторизован', () => {})` <!-- i18n-keep: E5 --> (Returns empty list. User is not authorized)
+
+Bad (no capital after period; or wrong locale for configured ESLint):
+
+- `it('Возвращает пустой список. пользователь не авторизован', () => {})` <!-- i18n-keep: E5 -->
+- `it('Returns empty list when user is guest', () => {})` (wrong locale if ESLint enforces Russian)
+
+## Isolation and mocks
+
+- Mock at the **public-contract boundary**; use the project's accepted HTTP/API/store mock approach. Do not mock what is part of the feature's public contract if that breaks the test's meaning.
+
+## Coverage of cross-cutting modules
+
+- When changing a **shared cross-cutting module** (e.g. HTTP client body parsing, headers, error / auth handling) — **update or add behavior tests** covering success, error, and edge branches relevant to the module under change.
+
+## Data transformation coverage
+
+- Data transformation functions with computed fields and branches must have unit tests covering edge cases (boundary values, missing fields, unexpected value combinations).
+
+## Reuse fixtures over ad-hoc random data
+
+- Prefer shared fixtures / handlers from the project's accepted mocks module; do not duplicate interfaces in tests. Use the API response types (DTO types) and the **target domain types** from the project's public type surface.
+
+## E2E: one canonical scenario plan per feature
+
+- For each feature keep a **single canonical scenario plan** (distinct from implementation specs; the stack adapter names the file — typically `*.cases.md`).
+
+## E2E: scenario ↔ test traceability
+
+- Every scenario has a corresponding test. **Do not weaken** assertions to match an outdated implementation — tests must reflect business expectations from the plan. Colocate plan and executable tests in the same directory.
+
+## E2E: page objects / shared helpers
+
+- Prefer page objects and shared helpers over scattered selectors and per-test setup duplication.
+
+## E2E: stable identifiers (PREFIX-XXX)
+
+- When scenarios need stable IDs, prefix the title with `PREFIX-XXX`: `PREFIX` = first letters of words in the entity under test (Latin uppercase); `XXX` = sequential number with three digits and leading zeros. Within one `PREFIX`, numbers must form a consistent sequence with no duplicates.
+- Example: `test('OH-001 Отображается список заказов', async ({ page }) => { ... })` <!-- i18n-keep: E5 --> (Order list is displayed)
+
+## E2E: selector priority
+
+- Prefer role/label selectors for accessibility and forms; fall back to `data-testid` for stable elements. Use a **hierarchical naming convention** on page roots and key interactive elements (stack adapter defines the scheme — typically `{parent}__{element}`).
+
+## E2E: keep plans and selectors in sync with UI
+
+- When changing UI: update selectors in page objects and cross-check with the scenario plan. When adding/changing tests: read the matching plan and sync scenario titles first.
+
+## Stack notes
+
+- Runner: Playwright (`@playwright/test`).
 - E2E folder: `app/__tests__/e2e/**`.
-- Scenario plans:
-  - `*.cases.md` files — **canonical source of scenarios**.
-- Tests:
-  - `*.spec.ts` files — Playwright scenario implementations.
-- Shared utilities and abstractions:
-  - `app/__tests__/e2e/_shared/**` — constants, fluent interfaces, helpers.
-
-# Principles
-
-- Every scenario from `*.cases.md` must have a corresponding test (or set of tests).
-- **Do not** weaken assertions in tests if that contradicts business expectations from the plans.
-- Prefer:
-  - page objects (for example, `OrderHistoryPage.ts`);
-  - shared helpers from `_shared`.
-
-# E2E test naming
-
-- Language:
-  - in consumer apps, `test` / `it`, `describe` block titles, and steps in `*.cases.md` **may use the project locale** (often Russian) — phrasing behavior and expected outcome;
-  - when the repo ESLint or team convention requires Russian titles, follow that; otherwise use clear English business phrases.
-- E2E test title format (`test(...)` / `it(...)`):
-  - before the scenario description, include a **numbered prefix** in the form: `PREFIX-XXX Scenario description`.
-  - `PREFIX` — abbreviation from the **first letters of words** in the entity under test, written **in Latin uppercase**.
-    - example: `OrderHistory` → `OH`, `BillingReport` → `BR`.
-  - `XXX` — sequential test number **with three digits and leading zeros**: `001`, `002`, `010`, `123`, etc.
-  - full e2e test title example (Russian locale in consumer app):
-    - `test('OH-001 Отображается список заказов', async ({ page }) => { ... })` <!-- i18n-keep: E5 --> (Order list is displayed)
-  - within one entity (`PREFIX`), test numbers must form a **consistent sequence** with no duplicate numbers.
-
-# data-testid for e2e
-
-- **Selector priority:** `data-testid` for stable elements; `getByRole` and `getByLabel` for forms and accessible elements.
-- **Naming:** `{parent}__{element}` scheme (for example, `history-page__title`, `history-page__recognition-banner__attach-files-button`).
-- **Where to add:** on page root containers and key interactive elements (buttons, links, fields) that page objects target.
-- **When changing UI:** update data-testid in components and matching selectors in page objects; cross-check with `*.cases.md`.
-
-# Agent requirement
-
-When adding/changing e2e tests:
-- First read the matching `*.cases.md` and sync scenario titles.
-- Place specs next to plans in the same directory.
-- Reuse shared page objects and helpers instead of copying selectors directly into every test.
+- Scenario plans: `*.cases.md` files — canonical source of scenarios.
+- Tests: `*.spec.ts` files — Playwright scenario implementations.
+- Shared utilities and abstractions: `app/__tests__/e2e/_shared/**` — constants, fluent interfaces, helpers.
+- `data-testid` naming scheme: `{parent}__{element}` — example `history-page__title`, `history-page__recognition-banner__attach-files-button`.
+- `PREFIX-XXX` example: `OrderHistory` → `OH`, `BillingReport` → `BR`; Russian example — `test('OH-001 Отображается список заказов', async ({ page }) => { ... })` <!-- i18n-keep: E5 --> (Order list is displayed).
+- Page object example filename: `OrderHistoryPage.ts` (the seed test pointer lives at `app/__tests__/e2e/seed.spec.ts`).
+- Cross-reference: See also **`playwright-agents.mdc`** for the e2e planner / generator / healer agents.
+- `## Stack notes` content is stripped by `scripts/check-shared-core-drift.sh` before byte-comparing this file against `_shared/core/testing/testing-principles.md`; keep prose above (core content) verbatim against the core file.

package/presets/cursor/next/rules/tests-unit.mdc

@@ -3,80 +3,113 @@ description: Unit and integration tests (Testing Library and project runner)
 globs:
   - app/src/**/*.spec.{ts,tsx}
   - app/src/**/*.test.{ts,tsx}
+  - app/__tests__/unit/**/*.spec.{ts,tsx}
+  - app/__tests__/unit/**/*.test.{ts,tsx}
 alwaysApply: false
 impact: MEDIUM
 ---
 
-# General testing rules
+<!-- shared-core: testing/testing-principles.md -->
 
-- **File names:** for **new** tests use the **`*.spec.ts` / `*.spec.tsx`** suffix. Do not rename existing **`*.test.ts` / `*.test.tsx`** without a separate task (legacy).
-- **Runner and matchers** — as in the project (often Jest or Vitest); for components — **@testing-library/react**.
-- Primary goal of tests:
-  - verify **behavior and business rules**, not implementation or internal details.
-- **Unit test naming** (strings in `describe` / `it` / `test`):
-  - consumer apps **may use Russian locale** for titles — clear business phrases (what is checked and expected outcome);
-  - when ESLint enforces Russian (see below), each sentence in the title **must start with a capital letter** (including after `.`, `!`, `?` and with multiple sentences on one line); the first letter of the whole string is capitalized too.
-  - **CI check (when configured):** ESLint (`jest/valid-title` in `app/eslint.config.mjs`) may require titles to start with a Russian capital letter and forbid a space after `.` followed immediately by a lowercase letter (typical "capital after period" violation).
+# Testing principles
+
+Stack-agnostic; concrete paths, runners, and selectors live in the stack adapter (`## Stack notes`).
+
+## Behavior vs. implementation
+
+- Verify **behavior and business rules**, not implementation or internal details.
+
+## File naming
+
+- For **new** tests use `*.spec.ts` / `*.spec.tsx`. Do not rename existing `*.test.ts` / `*.test.tsx` without a separate task (legacy).
+
+## Runner and matchers
+
+- Use the project's runner (Jest or Vitest are common); components — the project's Testing Library integration. Reuse existing matchers — no new micro-framework.
+
+## Test title locale
+
+- Consumer apps **may use the project locale** (often Russian) — clear business phrases stating what is checked and the expected outcome.
+- When ESLint enforces the locale (e.g. `jest/valid-title`): each sentence must start with a **capital letter** (including after `.`, `!`, `?`); a space after `.` followed by a lowercase letter is forbidden ("capital after period" violation).
 
 Good (Russian locale in consumer app):
 
 - `it('Возвращает пустой список. Пользователь не авторизован', () => {})` <!-- i18n-keep: E5 --> (Returns empty list. User is not authorized)
-- `it('При ошибке сети показывается сообщение об ошибке', () => {})` <!-- i18n-keep: E5 --> (On network error, an error message is shown)
 
 Bad (no capital after period; or wrong locale for configured ESLint):
 
 - `it('Возвращает пустой список. пользователь не авторизован', () => {})` <!-- i18n-keep: E5 -->
-- `it('Returns empty list when user is guest', () => {})`
+- `it('Returns empty list when user is guest', () => {})` (wrong locale if ESLint enforces Russian)
+
+## Isolation and mocks
+
+- Mock at the **public-contract boundary**; use the project's accepted HTTP/API/store mock approach. Do not mock what is part of the feature's public contract if that breaks the test's meaning.
+
+## Coverage of cross-cutting modules
+
+- When changing a **shared cross-cutting module** (e.g. HTTP client body parsing, headers, error / auth handling) — **update or add behavior tests** covering success, error, and edge branches relevant to the module under change.
+
+## Data transformation coverage
 
-# Component tests
+- Data transformation functions with computed fields and branches must have unit tests covering edge cases (boundary values, missing fields, unexpected value combinations).
 
-- Use `render` from `@testing-library/react`.
-- Assertions:
-  - DOM matchers for Testing Library as wired in the project (`toBeInTheDocument`, `toHaveTextContent`, etc.).
-- Interactions:
-  - `userEvent` from `@testing-library/user-event`.
+## Reuse fixtures over ad-hoc random data
 
-# Isolation and mocks
+- Prefer shared fixtures / handlers from the project's accepted mocks module; do not duplicate interfaces in tests. Use the API response types (DTO types) and the **target domain types** from the project's public type surface.
 
-- For API/store work:
-  - mock the store (via test-store) or use the project's accepted HTTP/API mock approach.
-- Do not mock what is part of the feature's public contract if that breaks the test's meaning.
+## E2E: one canonical scenario plan per feature
 
-# HTTP client
+- For each feature keep a **single canonical scenario plan** (distinct from implementation specs; the stack adapter names the file — typically `*.cases.md`).
 
-- When changing the **shared HTTP client implementation** (body parsing, headers, error branches, 401/refresh, `FormData`, `blob`, etc.) — **update or add behavior tests** next to the client module in `app/src/lib/clients/**` (prefer `*.spec.ts`; legacy `*.test.ts` — do not touch without a task).
-- Cover meaningful branches: successful JSON, HTTP error, network, auth scenarios relevant to the project.
+## E2E: scenario ↔ test traceability
 
-# Mappers and data transformation
+- Every scenario has a corresponding test. **Do not weaken** assertions to match an outdated implementation — tests must reflect business expectations from the plan. Colocate plan and executable tests in the same directory.
 
-- Data mapping functions (DTO → domain model and back), especially with computed fields and branches, must have unit tests.
-- In mapper tests, pay special attention to edge cases and business-rule regression (for example, boundary values, missing fields, unexpected value combinations).
+## E2E: page objects / shared helpers
 
-# Agent requirement
+- Prefer page objects and shared helpers over scattered selectors and per-test setup duplication.
+
+## E2E: stable identifiers (PREFIX-XXX)
+
+- When scenarios need stable IDs, prefix the title with `PREFIX-XXX`: `PREFIX` = first letters of words in the entity under test (Latin uppercase); `XXX` = sequential number with three digits and leading zeros. Within one `PREFIX`, numbers must form a consistent sequence with no duplicates.
+- Example: `test('OH-001 Отображается список заказов', async ({ page }) => { ... })` <!-- i18n-keep: E5 --> (Order list is displayed)
+
+## E2E: selector priority
+
+- Prefer role/label selectors for accessibility and forms; fall back to `data-testid` for stable elements. Use a **hierarchical naming convention** on page roots and key interactive elements (stack adapter defines the scheme — typically `{parent}__{element}`).
+
+## E2E: keep plans and selectors in sync with UI
+
+- When changing UI: update selectors in page objects and cross-check with the scenario plan. When adding/changing tests: read the matching plan and sync scenario titles first.
+
+## Stack notes
+
+- `render` from `@testing-library/react` for component tests.
+- `userEvent` from `@testing-library/user-event` for interactions.
+- DOM matchers as wired in the project (`toBeInTheDocument`, `toHaveTextContent`, …).
+- `jest/valid-title` ESLint rule in `app/eslint.config.mjs` enforces the Russian capital-after-period rule (when configured).
+- `@/types` and `@/api` imports — types come from the public API surface, never duplicated in tests.
+- `app/src/mocks/**` — shared fixtures and MSW handlers live here (or repo equivalent).
+- HTTP-client behavior tests live next to the client module in `app/src/lib/clients/**` (prefer `*.spec.ts`); when dual-glob consumer layout is used, the mirrored `app/__tests__/unit/lib/clients/**` path is also accepted.
+- UI test placement: sibling `*.spec.tsx` — no `__tests__/unit/` subfolder inside the component folder; an existing `__tests__` layout in `api/services` is acceptable — do not break it for UI uniformity.
+- `## Stack notes` content is stripped by `scripts/check-shared-core-drift.sh` before byte-comparing this file against `_shared/core/testing/testing-principles.md`; keep prose above (core content) verbatim against the core file.
 
-When adding tests:
-- Follow existing test structure and patterns in the repository: `*.spec.ts(x)` next to the module or in a shared test directory — as in neighboring features.
-- Add tests for critical logic branches and edge cases.
- - When working with data:
-   - use **response types** from the API (DTO types) and **target domain types** from `@/types`; do not duplicate interfaces in tests;
-   - when possible, rely on data and handlers from `app/src/mocks/**` (or repo equivalent), not ad-hoc random test data.
- - Placement:
-   - for **UI components** — **do not create** a `__tests__` subdirectory inside the component folder; the test is a sibling `*.spec.tsx`.
-   - in **other modules** (for example `api/services`) an existing `__tests__` layout is acceptable — do not break it for UI uniformity.
-   - **new** files — `*.spec.ts` / `*.spec.tsx` (see "File names" above).
 ## Incorrect
 
+Title violates capital-after-period rule (Russian locale). The rule's enforcement (`jest/valid-title`) will reject this in CI.
+
 ```ts
-it('returns empty list when guest', () => {})
+it('возвращает пустой список. пользователь не авторизован', () => { <!-- i18n-keep: E5 -->
+  expect(result).toEqual([]);
+});
 ```
 
-- `it('Возвращает пустой список. пользователь не авторизован', () => {})` <!-- i18n-keep: E5 -->
-
 ## Correct
 
+Title respects capital-after-period rule.
+
 ```ts
-it('Возвращает пустой список. Пользователь не авторизован', () => {})
+it('Возвращает пустой список. Пользователь не авторизован', () => { <!-- i18n-keep: E5 -->
+  expect(result).toEqual([]);
+});
 ```
-<!-- i18n-keep: E5 -->
-
-- `it('Возвращает пустой список. Пользователь не авторизован', () => {})` <!-- i18n-keep: E5 -->

package/presets/cursor/next/skills/code-review/SKILL.md

@@ -33,6 +33,12 @@ Lead with findings ordered by severity. Required shape (also in `code-review-mr`
 
 For agent team tasks, write `.cursor/team/tasks/<slug>/review.md` and upsert the owned terminal receipt (`completed` or `changes_requested`); do not mutate `status.json`.
 
+## Receiving review feedback
+
+<!-- shared-core: review/receiving-code-review.md -->
+
+When **implementing** review comments (not when issuing them): verify each item against the codebase before changing code; do not perform agreement (`You're absolutely right!`). Unclear items → ask, do not guess.
+
 ## Design guidance
 
 - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

package/presets/cursor/next/skills/debug-investigation/SKILL.md

@@ -3,19 +3,36 @@ name: debug-investigation
 description: Investigates bugs, failing tests, crashes, and incorrect behavior with runtime evidence before applying minimal fixes. Use for bugfix tasks, debugger agent runs, regressions, and flaky test diagnosis.
 ---
 
-# Debug Investigation
+<!-- shared-core: quality/debug-investigation.md -->
 
-## Process
+# Debug investigation
 
-1. Reproduce the issue or collect the closest available evidence: error output, failing test, browser snapshot, logs, or user steps.
-2. Define expected vs actual behavior in one sentence.
-3. Trace the failing path through the smallest relevant slice of the codebase.
-4. Identify the root cause before editing. Avoid broad refactors during bugfixes.
-5. Apply the smallest fix that preserves existing architecture and public contracts.
-6. Add or update a regression test when the behavior is user-facing or likely to recur.
-7. Run the narrow failing check first, then relevant lint/type/test validation.
+Stack-agnostic root-cause loop. Consumed by skill `debug-investigation` and agent `debugger`. Platform paths, MCP, and stack commands belong in adapter **Stack notes**.
 
-## Artifacts
+## When
+
+Any bug, test failure, build failure, or unexpected behavior — **before** proposing a fix.
+
+## Phases (in order)
+
+1. **Evidence** — reproduce, or collect the closest evidence (error output, failing test, logs, user steps).
+2. **Isolate** — expected vs actual in one sentence; smallest relevant slice of the codebase.
+3. **Root cause** — name the cause before editing. One hypothesis at a time; do not stack speculative fixes.
+4. **Minimal fix + verify** — smallest change that preserves architecture and public contracts. Add a regression test when the behavior is user-facing or likely to recur. Re-run the **failing** check first, then the relevant lint/type/test slice.
+
+## 3-fix architecture gate
+
+If **three** fix attempts fail, or the same symptom returns after two supposed fixes: **STOP**. Do not attempt fix #4. Escalate — the design is likely wrong (human partner or `solution-architect`). Chasing symptoms is the failure mode.
+
+## Do not
+
+- Broad refactor during a bugfix.
+- Fix only where the error surfaces if invalid data originates elsewhere.
+- Claim `fixApplied: true` without re-running the failing check (see `quality/verification-before-completion.md`).
+
+## Stack notes
+
+### Artifacts
 
 For agent team tasks, write `.cursor/team/tasks/<slug>/debug-report.md` with:
 
@@ -27,8 +44,7 @@ For agent team tasks, write `.cursor/team/tasks/<slug>/debug-report.md` with:
 
 Agent team: upsert the owned terminal receipt in `artifact-manifest.json`; do not mutate `status.json`.
 
-
-## MCP usage
+### MCP usage
 
 Load requestable rule `mcp-usage` when verifying third-party library APIs (Context7) or when a local overlay MCP is present and the task fits. Discover tools at runtime; do not invent schemas. Overlay absence is not a blocker unless the user required that MCP as source of truth.
 
@@ -38,7 +54,6 @@ Shipped browser split: Playwright MCP for e2e specs/selectors; Chrome DevTools M
 
 If a Sentry/Datadog (or similar) MCP is ready and the task is a production error, event, or trace, use it. Do not invent telemetry.
 
-
-## Design guidance
+### Design guidance
 
 - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.