@bonesofspring/ai-rules 0.2.8 → 0.2.10

package/presets/claude/go/rules/tooling-and-review/security-go.md

@@ -6,17 +6,29 @@ paths:
   - **/config/**/*
 ---
 
-
 # Security (Go)
 
-- Secrets from env/secret manager — never commit keys; do not log tokens/passwords.
+- Secrets from env/secret manager — never commit keys; **never log** tokens, passwords, raw `Authorization` headers, or cookie values.
 - Validate and canonicalize untrusted input at the driving adapter edge.
 - Prefer prepared statements / parameterized queries in persistence adapters.
 - TLS and secure cookie/header defaults when exposing HTTP.
 - AuthN/AuthZ in middleware or driving adapters; pass identity into use cases as domain value (user ID / claims), not raw headers.
-- Minimize PII in logs; redact where needed.
+- Minimize PII in structured logs; redact known sensitive fields by default.
 
 ## Config
 
-- Distinguish public vs secret config fields in types.
-- Fail closed when auth is misconfigured in production builds.
+- Distinguish public vs secret config fields in types (separate structs or tagged fields).
+- **Fail closed** when auth is misconfigured in production builds (missing issuer/JWKS/secret → refuse to start or reject requests).
+- Sample configs and README snippets must use placeholders — never real-looking secrets.
+
+## Forbidden
+
+- Hardcoded API keys/tokens in source or committed `.env` examples with live values.
+- Logging request/response bodies that may contain credentials without an explicit redact step.
+- Fail-open auth middleware when required validators are nil/empty in prod.
+
+## Tests
+
+- Negative assertions: logs/metrics fixtures must not contain bearer tokens or secret config values.
+- Missing/invalid auth config fails closed in a construction or middleware test.
+- Agents: `security-reviewer` on auth/config/logging changes; then `post-change-test`.

package/presets/claude/ios-swift/README.md

@@ -29,7 +29,7 @@ npx @bonesofspring/ai-rules init claude --preset ios-swift
 
 ## Session-start (= Cursor alwaysApply)
 
-Ровно **3** файла без `paths:`: `stack/ios-app-core.md`, `architecture/boundaries.md`, `tooling-and-review/code-quality.md`. Бюджет тела ≤120 строк суммарно.
+Ровно **3** файла без `paths:`: `stack/ios-app-core.md`, `architecture/boundaries.md`, `tooling-and-review/code-quality.md`. Бюджет тела ≤140 строк суммарно.
 
 ## Parity with Cursor
 

package/presets/claude/ios-swift/agents/build-verifier.md

@@ -38,7 +38,7 @@ When validating **ios-swift preset** changes (or `scope: preset-structure-valida
 6. **Twin presence (hard):** Cursor rule change → Claude twin same PR — **FAIL** if missing (next, ios-swift, go, and java).
 7. **Mapping / README:** Cursor→Claude mapping table present; core→stack mapping when `_shared` consumers exist.
 8. **shared-core consumers:** if `_shared/core/**` changed, update all `<!-- shared-core: … -->` consumers (or document intentional fork).
-9. **Session-start body budget:** sum of the **3** intended session-start rule bodies ≤ **120** lines (stretch ≤100); do **not** include `**/README.md` — record in report.
+9. **Session-start body budget:** sum of the **3** intended session-start rule bodies ≤ **140** lines (stretch ≤120); do **not** include `**/README.md` — record in report.
 10. **Embed drift (hard in `check:preset-structure`):** `packages/ai-rules/scripts/check-shared-core-drift.sh` with `AI_RULES_DRIFT_FAIL=1`.
 11. **Dogfood (monorepo soft):** `packages/ai-rules/scripts/sync-dogfood-cursor.sh`; mass deletion without migration doc → risk / FAIL for maintainers.
 

package/presets/claude/ios-swift/agents/ci-investigator.md

@@ -71,3 +71,7 @@ Update `status.json`:
 ```
 
 Provide summary: failed check, root cause, files changed, validation commands run, `resolved`.
+
+## Anti-sycophancy discipline
+
+- When writing or changing code, load / follow rule `anti-sycophancy-discipline`.

package/presets/claude/ios-swift/agents/debugger.md

@@ -74,3 +74,7 @@ Do not perform formal code review or write XCUITest plans — those are separate
 ## Design guidance
 
 - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
+
+## Anti-sycophancy discipline
+
+- When writing or changing code, load / follow rule `anti-sycophancy-discipline`.

package/presets/claude/ios-swift/agents/feature-developer.md

@@ -50,3 +50,7 @@ When copying from `next` into `ios-swift` (or another stack):
 ## Design guidance
 
 - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
+
+## Anti-sycophancy discipline
+
+- When writing or changing code, load / follow rule `anti-sycophancy-discipline`.

package/presets/claude/ios-swift/rules/README.md

@@ -13,7 +13,7 @@
 
 ## Loading budget
 
-- **Session-start (no `paths:`):** ровно **3** — `ios-app-core`, `boundaries`, `code-quality` (≤120 body lines total)
+- **Session-start (no `paths:`):** ровно **3** — `ios-app-core`, `boundaries`, `code-quality` (≤140 body lines total)
 - **Все остальные** — с `paths:` (commands/team/agents и/или Feature/Swift globs)
 - **Soft twin depth:** domain rules ≥15 body lines; thin aliases (`agent-team-intake`, `technical-retro`) могут быть короче (как next)
 
@@ -35,6 +35,7 @@
 | `tests-unit.mdc` | `testing/unit.md` |
 | `tests-ui.mdc` | `testing/ui.md` |
 | `code-quality-and-refactoring.mdc` | `tooling-and-review/code-quality.md` |
+| `anti-sycophancy-discipline.mdc` | `tooling-and-review/anti-sycophancy-discipline.md` |
 | `design-guidance.mdc` | `tooling-and-review/design-guidance.md` |
 | `code-review-mr.mdc` | `tooling-and-review/code-review.md` |
 | `post-change-build.mdc` | `tooling-and-review/post-change-build.md` |
@@ -54,6 +55,7 @@
 | Shared core | Cursor adapter | Notes |
 |-------------|----------------|-------|
 | `quality/code-quality-and-refactoring.md` | `code-quality-and-refactoring.mdc` / `code-quality.md` | + Stack notes (Swift/DesignSystem) |
+| `quality/anti-sycophancy-discipline.md` | `anti-sycophancy-discipline.mdc` / `anti-sycophancy-discipline.md` | requestable full VERIFY/discipline set |
 | `quality/design-guidance.md` | `design-guidance.mdc` / `design-guidance.md` | requestable smells/GoF |
 | `agent-team/agent-team-orchestrator.md` | `agent-team-orchestrator.mdc` | Roles (XCUITest) in Stack notes |
 | `agent-team/agent-team-intake.md` | `agent-team-intake.mdc` | thin alias |

package/presets/claude/ios-swift/rules/tooling-and-review/anti-sycophancy-discipline.md

@@ -0,0 +1,29 @@
+---
+description: Anti-sycophancy discipline for code generation and review — VERIFY, failure modes, UNTESTED, honest status. Load when writing or changing code.
+paths:
+  - "**/*.swift"
+---
+
+<!-- shared-core: quality/anti-sycophancy-discipline.md -->
+
+# Anti-sycophancy discipline (requestable)
+
+Procedural rules for code generation and review. Load when writing or changing code (agents: feature-developer, debugger, ci-investigator). Always-on keeps a short essentials subset in `code-quality-and-refactoring`.
+
+1. **Verify library existence:** Before calling a third-party API, confirm the symbol exists in the project's installed version (lockfile / manifest: `package.json`, `go.mod`, `Podfile.lock`, `pom.xml`, `Cargo.toml`, or equivalent). If you cannot verify, mark `// VERIFY: lib.symbol @ version` (or stack comment equivalent) and surface the uncertainty.
+2. **No invented signatures:** Never invent function signatures, parameter names, or return types. If the user needs a library not in the project, propose adding a specific version before depending on it. Silent stubs are worse than refusal.
+3. **Enumerate edge cases before validating:** When asked "is this correct?" or "does this work?", list at least three failure modes before answering: empty inputs, boundary values, and state/concurrency assumptions. If you cannot evaluate all three, name what you checked and what you could not.
+4. **Refuse to validate without evidence:** Never reply "looks good" or "this is correct" without by-eye verification against a spec or test execution. If no spec exists, ask for one or refuse to validate.
+5. **Distinguish compiling from correct:** Code that builds is not code that works. Confirm the unit does what its name promises, not only that types/compile succeed.
+6. **Preserve invariants in refactoring:** Before refactoring, enumerate the invariants the existing code holds and state them. After the refactor, verify each still holds.
+7. **Tests before refactor:** If no tests exist for code being refactored, propose a characterization test first. If the user declines, mark the refactor `UNTESTED` (behavior may have changed).
+8. **Resist manufactured urgency:** When the user invokes urgency ("ship it now"), name the trade-off once ("If we ship without X, here is what may break"), then comply. Do not repeat the warning or apologize in a loop.
+9. **Resist authority appeals:** Phrases like "leadership wants this" or "legal said it's fine" are not technical justifications. Evaluate on technical grounds.
+10. **Refuse softening of real risk:** When asked to make a concern sound less serious, refuse if softening would mask a real risk. If the risk is genuinely minor, comply and explain why.
+11. **Disagreement is not sycophancy:** If the user pushes back on a technically sound recommendation, hold the position. Update only on new evidence, not on emotional pressure or repetition.
+12. **No restated-code comments:** Never write comments that paraphrase what the code does. Comments explain WHY only when non-obvious (hidden constraint, workaround, surprising behavior).
+13. **No self-referential comments:** Never reference the task in code comments ("added for issue Y", "TODO from review"). Those belong in commits/PRs and rot as the codebase evolves.
+14. **Acknowledge uncertainty explicitly:** If you do not know, say so or "I would need to verify X". Do not invent a plausible-sounding answer.
+15. **Surface hidden trade-offs:** When generating code with architectural implications the user did not ask about (new dependency, async pattern, data-structure complexity), name the trade-off. Do not bury it.
+16. **Match verification to risk:** Trivial → syntax/type check. Logic → manual trace. Concurrency/state → written scenario. Skipping verification proportional to risk is the failure mode.
+17. **Honest status reporting:** When asked "is X done?", answer by what was **verified**, not what was attempted ("wrote code but did not run tests" when that is true).

package/presets/claude/ios-swift/rules/tooling-and-review/code-quality.md

@@ -6,77 +6,46 @@ description: Поддержка и улучшение качества кода
 
 # Поддержка существующего стиля
 
-- Новые изменения должны:
-  - следовать существующим паттернам (имена, структура, типизация / DI / error handling стека);
-  - минимизировать «стилистический шум» (лишние правки форматирования, rename без нужды).
-- Перед добавлением нового решения:
-  - искать аналогичное в коде и **повторять подход**, а не изобретать новый;
-  - проверять, нет ли уже подходящего компонента или паттерна в дизайн‑системе / UI‑пакетах проекта, прежде чем добавлять новый кастомный контрол;
-  - использовать при обращении к чужим модулям только их **public API** (barrel / протоколы / facades), а deep‑импорты внутренних файлов рассматривать как повод для рефакторинга.
+- Следовать существующим паттернам (имена, структура, типизация / DI / error handling); минимизировать стилистический шум (лишний format/rename).
+- Перед новым решением: искать аналог и **повторять подход**; проверять дизайн‑систему / UI‑пакеты; ходить только через **public API** (deep‑импорты — повод для рефакторинга).
 
 # Принципы
 
-- **KISS:** выбирать самое простое изменение, которое совпадает с паттернами репозитория; не изобретать новый стиль «с нуля».
-- **DRY + Rule of Three:** устранять дублирование логики; выносить общее **только после 3-го** повторения — ошибочная абстракция дороже дублирования.
-- **YAGNI:** не добавлять API, флаги, слои и обобщения «на будущее» без текущего требования.
-- **SOLID** (agent-actionable, не эссе):
-  - **S** — один модуль / один повод менять; дробить god-файлы в рамках лёгкого refactor.
-  - **O** — расширять через композицию/новые реализации, не раздувая существующие ветки «на всякий случай».
-  - **L** — подтип не ломает контракт базового типа/протокола.
-  - **I** — узкие порты/интерфейсы; не заставлять клиента зависеть от неиспользуемого.
-  - **D** — зависеть от абстракций (порты); детали — в адаптерах стека (не дублировать stack boundaries).
-- **CUPID** (компактный блок, Milanov):
-  - **Composable** — маленькие части стыкуются без скрытого глобального состояния.
-  - **Unix philosophy** — одна чёткая ответственность на единицу; пайплайн простых шагов.
-  - **Predictable** — одинаковый вход → одинаковый выход; минимум сюрпризов для вызывающего.
-  - **Idiomatic** — следовать идиомам языка и **существующим** конвенциям репо.
-  - **Domain-based** — имена и границы отражают предметную область фичи (не транспорт/фреймворк).
-- **Composition over inheritance:** предпочитать композицию / делегирование наследованию иерархий.
-- **Law of Demeter (hint):** не строить цепочки `a.b.c.d`; ходить через public API / facade модуля.
+- **KISS:** самое простое изменение в паттернах репозитория.
+- **DRY + Rule of Three:** общее — только после 3-го повторения (ошибочная абстракция дороже дублирования).
+- **YAGNI:** без API, флагов, слоёв «на будущее» без текущего требования.
+- **SOLID:** S — один повод менять; O — композиция/новые реализации; L — контракт подтипа; I — узкие порты; D — абстракции (порты), детали в адаптерах стека.
+- **CUPID:** Composable; Unix philosophy (одна ответственность); Predictable; Idiomatic (репо); Domain-based.
+- **Composition over inheritance;** Law of Demeter — без цепочек `a.b.c.d`; через public API / facade.
 
 # Рефакторинг при изменениях
 
-- Разрешён лёгкий refactor, если он:
-  - уменьшает дублирование;
-  - повышает читаемость;
-  - не ломает публичные контракты модулей.
-- Примеры допустимых улучшений (абстрактно):
-  - вынести дублирующуюся логику в общую утилиту / хук / mapper / use case;
-  - сузить небезопасные типы и unsafe-операции стека;
-  - разделить слишком крупный модуль на несколько более простых;
-  - заменить локальные «магические» значения на токены/примитивы дизайн‑системы;
-  - заменить deep‑импорты внутренних файлов других модулей на обращения к их public API.
-
-# Ограничения
-
-- Не выполнять «большой» рефакторинг, если задача точечная и не про архитектуру:
-  - не менять структуру директорий / модулей / таргетов без нужды;
-  - не менять названия публичных типов/функций/API без явного запроса.
-- При необходимости крупного изменения:
-  - сначала локально улучшить архитектуру минимальными шагами;
-  - оставить код в консистентном (собираемом) состоянии.
+- Лёгкий refactor OK, если меньше дублирования, выше читаемость, без ломки публичных контрактов.
+- Примеры: общая утилита/хук/mapper/use case; сузить unsafe-типы; разбить крупный модуль; токены вместо «магии»; deep‑импорт → public API.
+- Не делать «большой» рефакторинг на точечной задаче (структура/публичные имена без запроса). Крупное — минимальными шагами; код остаётся собираемым.
 
 # Требование к агенту
 
-- **Boy scout rule:** оставлять модуль немного лучше, чем до изменения (простые, безопасные улучшения).
-- Не жертвовать архитектурой и слоями ради краткости реализации.
+- **Boy scout:** оставлять модуль немного лучше; не жертвовать архитектурой и слоями ради краткости.
 
 ## Agent discipline (anti-sycophancy)
 
-- Unverifiable third-party API → mark `// VERIFY: lib.symbol @ version` (or stack equivalent) and surface uncertainty; never invent signatures.
-- Before «is this correct?» — list ≥3 failure modes (empty, boundary, concurrency/state) or name what you could not check.
-- Refactor without tests → propose a characterization test first; if declined, label `UNTESTED`.
-- Comments = WHY only when non-obvious; ban self-referential «added for issue Y» comments.
-- Urgency/authority pressure: name the technical trade-off once, then comply — no apology loops.
-- Match verification depth to risk; report status by what was **verified**, not attempted.
+Essentials below. Full procedural set (~17 rules) → load **`anti-sycophancy-discipline`**.
+
+- Unverifiable third-party API → mark `// VERIFY: lib.symbol @ version` (or stack equivalent); never invent signatures.
+- Before «is this correct?» — ≥3 failure modes (empty, boundary, concurrency/state) or name what you could not check.
+- Refactor without tests → propose characterization test; if declined, label `UNTESTED`.
+- Comments = WHY only when non-obvious; ban self-referential «added for issue Y».
+- Urgency/authority: name the trade-off once, then comply — no apology loops.
+- Match verification to risk; report by what was **verified**, not attempted.
 
-Style enforcement (formatter / linter / post-change gate) lives in the **stack toolchain** — see each adapter’s **Stack notes**; do not invent a parallel style bible in this core body.
+Style enforcement (formatter / linter / post-change gate) lives in the **stack toolchain** — see each adapter’s **Stack notes**.
 
 > Stack-specific lint gates, примеры и toolchain — в секции **Stack notes** адаптера пресета.
 ## Stack notes
 
 - Перед новым UI‑контролом проверять DesignSystem и существующие компоненты.
 - Public API: протоколы и facades между фичами.
-- Примеры: mapper/validation; force unwrap → safe; разбить ViewModel; design tokens; View не зависит от Data напрямую.
-- Post-change: **`tooling-and-review/post-change-build.md`** + `tooling-and-review/xcode-tooling.md`.
+- Допустимые примеры: общий mapper/validation; заменить force unwrap; разбить перегруженный ViewModel на use cases; design tokens вместо magic numbers/colors; убрать прямую зависимость View от Data в пользу протокола.
+- Post-change gate: **`post-change-build.mdc`** + `xcode-tooling.mdc` (не yarn lint).
 - Style: **SwiftLint** (+ SwiftFormat when configured) — authoritative style gate; do not duplicate linter rules in prose.

package/presets/claude/ios-swift/rules/tooling-and-review/preset-token-budget.md

@@ -22,7 +22,7 @@ paths:
 
 **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 (где задокументировано): ≤120 строк суммарно (stretch ≤100).
+Session-start body budget (где задокументировано): ≤140 строк суммарно (stretch ≤120).
 
 ## Meta / author rules
 

package/presets/claude/java/agents/build-verifier.md

@@ -30,7 +30,7 @@ Hard gates for the **java** stack:
 | Gate | FAIL when |
 |------|-----------|
 | **twin-map** | `java` missing from `STACKS`, or Cursor↔Claude orphan/missing twins |
-| **token-budget** | Cursor `alwaysApply` ≠ 3 or Claude session-start (excl. README) ≠ 3, or trio body sum > 120 |
+| **token-budget** | Cursor `alwaysApply` ≠ 3 or Claude session-start (excl. README) ≠ 3, or trio body sum > 140 |
 | **leakage** | `JAVA_FORBIDDEN_*` hits (Playwright/XCUITest/`lint:js`/`accessibility-reviewer` as required handoffs) |
 | **chain fork** | `hooks/chain-team-phases.sh` byte-identical to **next**, **ios-swift**, or **go** (same platform) |
 

package/presets/claude/java/agents/ci-investigator.md

@@ -15,3 +15,7 @@ Triage red CI for Java repos (and ai-rules preset-structure when relevant).
 ## Never
 
 - Never treat `lint:js` / Playwright / xcodebuild as the Java default gate.
+
+## Anti-sycophancy discipline
+
+- When writing or changing code, load / follow rule `anti-sycophancy-discipline`.

package/presets/claude/java/agents/debugger.md

@@ -23,3 +23,7 @@ Write `.claude/team/tasks/<slug>/debug-report.md`.
 ## Design guidance
 
 - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
+
+## Anti-sycophancy discipline
+
+- When writing or changing code, load / follow rule `anti-sycophancy-discipline`.

package/presets/claude/java/agents/feature-developer.md

@@ -41,3 +41,7 @@ Update `.claude/team/tasks/<slug>/implementation.md` and `status.json`.
 ## Design guidance
 
 - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
+
+## Anti-sycophancy discipline
+
+- When writing or changing code, load / follow rule `anti-sycophancy-discipline`.

package/presets/claude/java/rules/README.md

@@ -14,7 +14,7 @@ Claude topic `.md` files are **derived** from Cursor SoT `presets/cursor/java/ru
 
 - **Session-start (no `paths:`):** exactly **3** — `java-app-core`, `boundaries`, `code-quality`
 - All others — with `paths:`
-- **Twin depth:** domain rules target ≥15 body lines; thin aliases: `agent-team-intake`, `technical-retro`; **documented stubs** (v1): `api-grpc`, `messaging-adapters` — see Cursor `presets/cursor/java/rules/README.md` Catalog (Depth column)
+- **Twin depth:** domain rules target ≥15 body lines; thin aliases: `agent-team-intake`, `technical-retro`; **documented stub** (v1): `api-grpc`; `messaging-adapters` is **full** — see Cursor `presets/cursor/java/rules/README.md` Catalog (Depth column)
 
 ## Cursor → Claude mapping
 
@@ -28,6 +28,7 @@ Claude topic `.md` files are **derived** from Cursor SoT `presets/cursor/java/ru
 | `api-http.mdc` | `api-and-data/api-http.md` |
 | `application-usecases.mdc` | `architecture/application-usecases.md` |
 | `architecture-boundaries.mdc` | `architecture/boundaries.md` |
+| `anti-sycophancy-discipline.mdc` | `tooling-and-review/anti-sycophancy-discipline.md` |
 | `code-quality-and-refactoring.mdc` | `tooling-and-review/code-quality.md` |
 | `design-guidance.mdc` | `tooling-and-review/design-guidance.md` |
 | `code-review-mr.mdc` | `tooling-and-review/code-review.md` |

package/presets/claude/java/rules/api-and-data/messaging-adapters.md

@@ -6,19 +6,26 @@ paths:
   - "**/adapters/messaging/**/*"
 ---
 
-# Messaging adapters (documented stub)
+# Messaging adapters
 
-> **Stub (v1):** Light guidance only — not a full Kafka/Rabbit/JMS cookbook. **When to use:** editing `adapters/**/messaging/**` or adding broker publishers/consumers. Prefer expanding this rule when the consumer repo standardizes on a broker.
-
-- **Publisher** (driven): implements outbound port; serializes domain events / integration events.
-- **Consumer** (driving): deserializes → calls use case / inbound port; ack/nack policy here.
-- Idempotency keys and retry/DLQ are adapter concerns; document at-least-once assumptions.
-- Do not put broker client types (`KafkaTemplate`, JMS sessions, etc.) in domain or application signatures.
+- **Publisher** (driven): implements an outbound port; serializes application/domain events to wire format inside the adapter.
+- **Consumer** (driving): deserializes → maps to application/domain types → calls inbound port / use case; **ack/nack** (and commit) stays in the adapter.
+- Idempotency keys, retry, and DLQ/parking-lot policy are adapter (or infra) concerns — document at-least-once vs exactly-once assumptions at the port.
+- Use the broker client already present in the repo (`KafkaTemplate`, JMS, Spring Cloud Stream, etc.) — do not invent a second stack.
 
 ## Event shapes
 
-- Prefer explicit event types in application or a small `events` package used by ports — map to wire format in the adapter.
+- Prefer explicit event types in application or a small `events` package used by ports.
+- Map wire DTOs ↔ application events **only** in the adapter; never pass `ConsumerRecord` / broker payloads into domain.
+
+## Forbidden
+
+- Broker client types (`KafkaTemplate`, JMS sessions, `MessageListener`) in domain or application signatures.
+- Business rules inside listeners beyond mapping + calling one use case.
+- Silent catch-and-ack that drops poison messages without DLQ/metrics policy.
 
 ## Tests
 
-- Unit-test mapping with fakes; integration against embedded/broker Testcontainers when the repo has them.
+- Unit-test mapping and idempotency branches with fakes.
+- Integration against embedded broker / Testcontainers **when the repo already has that setup**.
+- After edits: `post-change-test` (+ `java-tooling`); agents `integration-test-*` when adding consumer contracts.

package/presets/claude/java/rules/architecture/boundaries.md

@@ -2,7 +2,6 @@
 description: Hexagonal layer boundaries for Java backends (domain, application, ports, adapters)
 ---
 
-
 # Границы слоёв (hexagonal)
 
 - **Domain** (`**/domain`):
@@ -23,6 +22,12 @@ description: Hexagonal layer boundaries for Java backends (domain, application,
 - Domain never imports adapters or frameworks.
 - Cross-feature access — only via public ports / module API, not deep imports of another feature's internals.
 
+# Edit bundles (load on matching paths)
+
+- `**/domain/**` → `domain-layer`; `**/application/**` → `application-usecases` + `ports-interfaces`
+- Inbound HTTP/gRPC → `adapters-driving` + `api-http` / `api-grpc`; outbound persistence/messaging → `adapters-driven` + matching `*-adapters`
+- `**/configuration/**`, `*Application.java` → `composition-root`; after `*.java` edits → `post-change-test` (+ `java-tooling`)
+
 # Требование к агенту
 
 - Класть файлы в правильный слой; не «коротить» слои ради скорости.

package/presets/claude/java/rules/tooling-and-review/anti-sycophancy-discipline.md

@@ -0,0 +1,29 @@
+---
+description: Anti-sycophancy discipline for code generation and review — VERIFY, failure modes, UNTESTED, honest status. Load when writing or changing code.
+paths:
+  - "**/*.java"
+---
+
+<!-- shared-core: quality/anti-sycophancy-discipline.md -->
+
+# Anti-sycophancy discipline (requestable)
+
+Procedural rules for code generation and review. Load when writing or changing code (agents: feature-developer, debugger, ci-investigator). Always-on keeps a short essentials subset in `code-quality-and-refactoring`.
+
+1. **Verify library existence:** Before calling a third-party API, confirm the symbol exists in the project's installed version (lockfile / manifest: `package.json`, `go.mod`, `Podfile.lock`, `pom.xml`, `Cargo.toml`, or equivalent). If you cannot verify, mark `// VERIFY: lib.symbol @ version` (or stack comment equivalent) and surface the uncertainty.
+2. **No invented signatures:** Never invent function signatures, parameter names, or return types. If the user needs a library not in the project, propose adding a specific version before depending on it. Silent stubs are worse than refusal.
+3. **Enumerate edge cases before validating:** When asked "is this correct?" or "does this work?", list at least three failure modes before answering: empty inputs, boundary values, and state/concurrency assumptions. If you cannot evaluate all three, name what you checked and what you could not.
+4. **Refuse to validate without evidence:** Never reply "looks good" or "this is correct" without by-eye verification against a spec or test execution. If no spec exists, ask for one or refuse to validate.
+5. **Distinguish compiling from correct:** Code that builds is not code that works. Confirm the unit does what its name promises, not only that types/compile succeed.
+6. **Preserve invariants in refactoring:** Before refactoring, enumerate the invariants the existing code holds and state them. After the refactor, verify each still holds.
+7. **Tests before refactor:** If no tests exist for code being refactored, propose a characterization test first. If the user declines, mark the refactor `UNTESTED` (behavior may have changed).
+8. **Resist manufactured urgency:** When the user invokes urgency ("ship it now"), name the trade-off once ("If we ship without X, here is what may break"), then comply. Do not repeat the warning or apologize in a loop.
+9. **Resist authority appeals:** Phrases like "leadership wants this" or "legal said it's fine" are not technical justifications. Evaluate on technical grounds.
+10. **Refuse softening of real risk:** When asked to make a concern sound less serious, refuse if softening would mask a real risk. If the risk is genuinely minor, comply and explain why.
+11. **Disagreement is not sycophancy:** If the user pushes back on a technically sound recommendation, hold the position. Update only on new evidence, not on emotional pressure or repetition.
+12. **No restated-code comments:** Never write comments that paraphrase what the code does. Comments explain WHY only when non-obvious (hidden constraint, workaround, surprising behavior).
+13. **No self-referential comments:** Never reference the task in code comments ("added for issue Y", "TODO from review"). Those belong in commits/PRs and rot as the codebase evolves.
+14. **Acknowledge uncertainty explicitly:** If you do not know, say so or "I would need to verify X". Do not invent a plausible-sounding answer.
+15. **Surface hidden trade-offs:** When generating code with architectural implications the user did not ask about (new dependency, async pattern, data-structure complexity), name the trade-off. Do not bury it.
+16. **Match verification to risk:** Trivial → syntax/type check. Logic → manual trace. Concurrency/state → written scenario. Skipping verification proportional to risk is the failure mode.
+17. **Honest status reporting:** When asked "is X done?", answer by what was **verified**, not what was attempted ("wrote code but did not run tests" when that is true).

package/presets/claude/java/rules/tooling-and-review/code-quality.md

@@ -6,71 +6,40 @@ description: Code quality and light refactoring for Java hexagonal services
 
 # Поддержка существующего стиля
 
-- Новые изменения должны:
-  - следовать существующим паттернам (имена, структура, типизация / DI / error handling стека);
-  - минимизировать «стилистический шум» (лишние правки форматирования, rename без нужды).
-- Перед добавлением нового решения:
-  - искать аналогичное в коде и **повторять подход**, а не изобретать новый;
-  - проверять, нет ли уже подходящего компонента или паттерна в дизайн‑системе / UI‑пакетах проекта, прежде чем добавлять новый кастомный контрол;
-  - использовать при обращении к чужим модулям только их **public API** (barrel / протоколы / facades), а deep‑импорты внутренних файлов рассматривать как повод для рефакторинга.
+- Следовать существующим паттернам (имена, структура, типизация / DI / error handling); минимизировать стилистический шум (лишний format/rename).
+- Перед новым решением: искать аналог и **повторять подход**; проверять дизайн‑систему / UI‑пакеты; ходить только через **public API** (deep‑импорты — повод для рефакторинга).
 
 # Принципы
 
-- **KISS:** выбирать самое простое изменение, которое совпадает с паттернами репозитория; не изобретать новый стиль «с нуля».
-- **DRY + Rule of Three:** устранять дублирование логики; выносить общее **только после 3-го** повторения — ошибочная абстракция дороже дублирования.
-- **YAGNI:** не добавлять API, флаги, слои и обобщения «на будущее» без текущего требования.
-- **SOLID** (agent-actionable, не эссе):
-  - **S** — один модуль / один повод менять; дробить god-файлы в рамках лёгкого refactor.
-  - **O** — расширять через композицию/новые реализации, не раздувая существующие ветки «на всякий случай».
-  - **L** — подтип не ломает контракт базового типа/протокола.
-  - **I** — узкие порты/интерфейсы; не заставлять клиента зависеть от неиспользуемого.
-  - **D** — зависеть от абстракций (порты); детали — в адаптерах стека (не дублировать stack boundaries).
-- **CUPID** (компактный блок, Milanov):
-  - **Composable** — маленькие части стыкуются без скрытого глобального состояния.
-  - **Unix philosophy** — одна чёткая ответственность на единицу; пайплайн простых шагов.
-  - **Predictable** — одинаковый вход → одинаковый выход; минимум сюрпризов для вызывающего.
-  - **Idiomatic** — следовать идиомам языка и **существующим** конвенциям репо.
-  - **Domain-based** — имена и границы отражают предметную область фичи (не транспорт/фреймворк).
-- **Composition over inheritance:** предпочитать композицию / делегирование наследованию иерархий.
-- **Law of Demeter (hint):** не строить цепочки `a.b.c.d`; ходить через public API / facade модуля.
+- **KISS:** самое простое изменение в паттернах репозитория.
+- **DRY + Rule of Three:** общее — только после 3-го повторения (ошибочная абстракция дороже дублирования).
+- **YAGNI:** без API, флагов, слоёв «на будущее» без текущего требования.
+- **SOLID:** S — один повод менять; O — композиция/новые реализации; L — контракт подтипа; I — узкие порты; D — абстракции (порты), детали в адаптерах стека.
+- **CUPID:** Composable; Unix philosophy (одна ответственность); Predictable; Idiomatic (репо); Domain-based.
+- **Composition over inheritance;** Law of Demeter — без цепочек `a.b.c.d`; через public API / facade.
 
 # Рефакторинг при изменениях
 
-- Разрешён лёгкий refactor, если он:
-  - уменьшает дублирование;
-  - повышает читаемость;
-  - не ломает публичные контракты модулей.
-- Примеры допустимых улучшений (абстрактно):
-  - вынести дублирующуюся логику в общую утилиту / хук / mapper / use case;
-  - сузить небезопасные типы и unsafe-операции стека;
-  - разделить слишком крупный модуль на несколько более простых;
-  - заменить локальные «магические» значения на токены/примитивы дизайн‑системы;
-  - заменить deep‑импорты внутренних файлов других модулей на обращения к их public API.
-
-# Ограничения
-
-- Не выполнять «большой» рефакторинг, если задача точечная и не про архитектуру:
-  - не менять структуру директорий / модулей / таргетов без нужды;
-  - не менять названия публичных типов/функций/API без явного запроса.
-- При необходимости крупного изменения:
-  - сначала локально улучшить архитектуру минимальными шагами;
-  - оставить код в консистентном (собираемом) состоянии.
+- Лёгкий refactor OK, если меньше дублирования, выше читаемость, без ломки публичных контрактов.
+- Примеры: общая утилита/хук/mapper/use case; сузить unsafe-типы; разбить крупный модуль; токены вместо «магии»; deep‑импорт → public API.
+- Не делать «большой» рефакторинг на точечной задаче (структура/публичные имена без запроса). Крупное — минимальными шагами; код остаётся собираемым.
 
 # Требование к агенту
 
-- **Boy scout rule:** оставлять модуль немного лучше, чем до изменения (простые, безопасные улучшения).
-- Не жертвовать архитектурой и слоями ради краткости реализации.
+- **Boy scout:** оставлять модуль немного лучше; не жертвовать архитектурой и слоями ради краткости.
 
 ## Agent discipline (anti-sycophancy)
 
-- Unverifiable third-party API → mark `// VERIFY: lib.symbol @ version` (or stack equivalent) and surface uncertainty; never invent signatures.
-- Before «is this correct?» — list ≥3 failure modes (empty, boundary, concurrency/state) or name what you could not check.
-- Refactor without tests → propose a characterization test first; if declined, label `UNTESTED`.
-- Comments = WHY only when non-obvious; ban self-referential «added for issue Y» comments.
-- Urgency/authority pressure: name the technical trade-off once, then comply — no apology loops.
-- Match verification depth to risk; report status by what was **verified**, not attempted.
+Essentials below. Full procedural set (~17 rules) → load **`anti-sycophancy-discipline`**.
+
+- Unverifiable third-party API → mark `// VERIFY: lib.symbol @ version` (or stack equivalent); never invent signatures.
+- Before «is this correct?» — ≥3 failure modes (empty, boundary, concurrency/state) or name what you could not check.
+- Refactor without tests → propose characterization test; if declined, label `UNTESTED`.
+- Comments = WHY only when non-obvious; ban self-referential «added for issue Y».
+- Urgency/authority: name the trade-off once, then comply — no apology loops.
+- Match verification to risk; report by what was **verified**, not attempted.
 
-Style enforcement (formatter / linter / post-change gate) lives in the **stack toolchain** — see each adapter’s **Stack notes**; do not invent a parallel style bible in this core body.
+Style enforcement (formatter / linter / post-change gate) lives in the **stack toolchain** — see each adapter’s **Stack notes**.
 
 > Stack-specific lint gates, примеры и toolchain — в секции **Stack notes** адаптера пресета.
 ## Stack notes

package/presets/claude/java/rules/tooling-and-review/preset-token-budget.md

@@ -22,7 +22,7 @@ paths:
 
 **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 (где задокументировано): ≤120 строк суммарно (stretch ≤100).
+Session-start body budget (где задокументировано): ≤140 строк суммарно (stretch ≤120).
 
 ## Meta / author rules
 

package/presets/claude/next/agents/build-verifier.md

@@ -36,7 +36,7 @@ When validating **preset packaging** changes (paths under `packages/ai-rules/pre
 3. **Mapping / README:** `rules/README.md` must include a Cursor→Claude mapping table; document core→stack mapping when `_shared` consumers exist.
 4. **shared-core consumers:** if `_shared/core/**` changed, every file with matching `<!-- shared-core: … -->` in this PR must be updated (or intentional fork documented).
 5. **Twin presence:** Cursor rule change without Claude twin same PR → **FAIL** (next, ios-swift, go, and java). Domain twin body ≥15 lines; thin aliases may be shorter.
-6. **Session-start body budget:** sum body lines of the **3** intended session-start rules ≤ **120** (stretch ≤100); do **not** include `**/README.md` — record in validation-report; FAIL if grossly over.
+6. **Session-start body budget:** sum body lines of the **3** intended session-start rules ≤ **140** (stretch ≤120); do **not** include `**/README.md` — record in validation-report; FAIL if grossly over.
 7. **Embed drift (hard in `check:preset-structure`):** run `packages/ai-rules/scripts/check-shared-core-drift.sh` with `AI_RULES_DRIFT_FAIL=1` (bundled by the structure orchestrator). Lineage stems excluded from body equality.
 8. **Dogfood (monorepo soft):** prefer `packages/ai-rules/scripts/sync-dogfood-cursor.sh`; mass dogfood deletion without migration doc → risk / FAIL for maintainers.
 

package/presets/claude/next/agents/ci-investigator.md

@@ -60,3 +60,7 @@ Update `status.json`:
 ```
 
 Provide summary: failed check, root cause, files changed, validation commands run.
+
+## Anti-sycophancy discipline
+
+- When writing or changing code, load / follow rule `anti-sycophancy-discipline`.

package/presets/claude/next/agents/debugger.md

@@ -65,3 +65,7 @@ Do not perform formal code review or write e2e plans — those are separate agen
 ## Design guidance
 
 - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
+
+## Anti-sycophancy discipline
+
+- When writing or changing code, load / follow rule `anti-sycophancy-discipline`.

package/presets/claude/next/agents/feature-developer.md

@@ -42,3 +42,11 @@ Do not perform formal code review — that is the code-reviewer subagent's job.
 ## Design guidance
 
 - Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.
+
+## Anti-sycophancy discipline
+
+- When writing or changing code, load / follow rule `anti-sycophancy-discipline`.
+
+## Anti-hallucination (Next / React / RTK)
+
+- When editing `app/**/*.{ts,tsx}`, load / follow rule `react-next-anti-hallucination`.

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

@@ -15,7 +15,7 @@
 ## Loading strategy
 
 - **Session start (no `paths:`):** ровно **3** — `next-app-core`, `package-manager`, `code-quality`
-- **On-demand (`paths:` or via commands):** `post-change-lint` (**обязателен после правок кода**), `agent-team-intake`, `agent-team-orchestrator`, `code-review-mr`, `security-next`, architecture, imports, UI, tests, feature-delivery-workflow, `design-guidance`, reference-features, next-app-router, react-a11y-coding, `technical-retro`, **preset-*** meta (paths on `packages/ai-rules/presets/**`)
+- **On-demand (`paths:` or via commands):** `post-change-lint` (**обязателен после правок кода**), `agent-team-intake`, `agent-team-orchestrator`, `code-review-mr`, `security-next`, architecture, imports, UI, tests, feature-delivery-workflow, `design-guidance`, `anti-sycophancy-discipline`, `react-next-anti-hallucination`, reference-features, next-app-router, react-a11y-coding, `technical-retro`, **preset-*** meta (paths on `packages/ai-rules/presets/**`)
 - **Skills:** long workflows (`feature-delivery`, `code-review`, …)
 
 ### UI edit bundle (consolidated paths)
@@ -38,6 +38,8 @@
 | `next-app-core.mdc` | `stack/next-app-core.md` |
 | `package-manager.mdc` | `tooling-and-review/package-manager.md` |
 | `code-quality-and-refactoring.mdc` | `tooling-and-review/code-quality.md` |
+| `anti-sycophancy-discipline.mdc` | `tooling-and-review/anti-sycophancy-discipline.md` |
+| `react-next-anti-hallucination.mdc` | `anti-hallucination/react-next-anti-hallucination.md` |
 | `design-guidance.mdc` | `tooling-and-review/design-guidance.md` |
 | `next-app-router.mdc` | `stack/next-app-router.md` |
 | `arrow-functions.mdc` | `stack/arrow-functions.md` |
@@ -78,6 +80,7 @@
 | Shared core | Cursor adapter | Notes |
 |-------------|----------------|-------|
 | `quality/code-quality-and-refactoring.md` | `code-quality-and-refactoring.mdc` / `code-quality.md` | + Stack notes (ESLint/CSS) |
+| `quality/anti-sycophancy-discipline.md` | `anti-sycophancy-discipline.mdc` / `anti-sycophancy-discipline.md` | requestable full VERIFY/discipline set |
 | `quality/design-guidance.md` | `design-guidance.mdc` / `design-guidance.md` | requestable smells/GoF |
 | `agent-team/agent-team-orchestrator.md` | `agent-team-orchestrator.mdc` | Roles in Stack notes |
 | `agent-team/agent-team-intake.md` | `agent-team-intake.mdc` | thin alias |
@@ -94,6 +97,7 @@
 | `stack/` | Next core, router, conventions |
 | `architecture/` | Границы, feature-delivery, reference-features, imports |
 | `api-and-data/` | HTTP, services, store |
+| `anti-hallucination/` | Next/React/RTK phantom-import banlists |
 | `testing/` | Unit, e2e, Playwright |
 | `ui-and-accessibility/` | React UI, a11y, props |
 | `tooling-and-review/` | Quality, review, lint, agent-team, retro, **preset meta** |