@bonesofspring/ai-rules 0.2.14 → 0.2.15

package/presets/claude/svelte/rules/tooling-and-review/post-change-lint.md

@@ -1,44 +1,44 @@
 ---
-description: Прогон ESLint, Stylelint и svelte-check после изменений кода. Requestable — подгружать после правок src/**; агенты обязаны запускать после code edits.
+description: Run ESLint, Stylelint, and svelte-check after code changes. Requestable — load after edits under src/**; agents must run after code edits.
 paths:
   - src/routes/**/*
   - src/lib/components/**/*
 ---
 
-# Линтеры после изменений кода
+# Linters after code changes
 
-**Requestable, но обязателен при изменениях кода:** правило не always-on (экономия контекста); после правок исходников агент **должен** следовать этому чеклисту.
+**Requestable, but required on code changes:** the rule is not always-on (context savings); after source edits the agent **must** follow this checklist.
 
-## Когда применять
+## When to apply
 
-После **любого** изменения исходников в `src/routes/**`, `src/lib/**`, `src/hooks.*.ts`, `src/params/**`, `tests/**` (Svelte/TS/JS, CSS, `<style>`).
+After **any** source change under `src/routes/**`, `src/lib/**`, `src/hooks.*.ts`, `src/params/**`, `tests/**` (Svelte/TS/JS, CSS, `<style>`).
 
-Исключения: правки документации, конфигов CI, `.cursor/rules/**`, если исполняемый код приложения не менялся.
+Exceptions: docs, CI configs, `.claude/rules/**`, when application executable code did not change.
 
-**Pipeline exception:** если задача идёт через agent team и следующий шаг — `build-verifier`, developer может ограничиться lint/check **изменённых файлов**; полный прогон — обязанность `build-verifier`. В single-agent режиме (без pipeline) — всегда полный прогон.
+**Pipeline exception:** if the task goes through the agent team and the next step is `build-verifier`, the developer may limit lint/check to **changed files**; the full run is `build-verifier`’s duty. In single-agent mode (no pipeline) — always a full run.
 
-## Обязательные команды
+## Required commands
 
-Рабочий каталог — **корень SvelteKit** (где `svelte.config.*`). Менеджер пакетов — **`package-manager`**.
+Working directory — **SvelteKit root** (where `svelte.config.*` lives). Package manager — **`package-manager`**.
 
-1. **`lint:js`** — полный ESLint по проекту (`eslint-plugin-svelte` when configured).
-2. **`lint:css`** — полный Stylelint.
+1. **`lint:js`** — full project ESLint (`eslint-plugin-svelte` when configured).
+2. **`lint:css`** — full Stylelint.
 
-Точечный lint на один файл **не заменяет** полный прогон перед завершением задачи (кроме pipeline exception выше).
+Point lint on a single file **does not replace** a full run before finishing the task (except the pipeline exception above).
 
-## Алгоритм
+## Algorithm
 
-1. Завершить правки кода.
-2. Запустить **`lint:js`** и **`lint:css`** из корня SvelteKit.
-3. Проанализировать весь вывод; исправить errors/warnings в изменённых файлах; для Stylelint — autofix если доступен.
-4. Повторить до exit code 0 или зафиксировать блокер в ответе пользователю.
-5. **`check`** (`svelte-kit sync && svelte-check`) при изменениях TypeScript / `.svelte` / SvelteKit config. CI-уровень: **`lint`** (= `lint:js` + `lint:css` + `check`).
+1. Finish code edits.
+2. Run **`lint:js`** and **`lint:css`** from SvelteKit root.
+3. Analyze the full output; fix errors/warnings in changed files; for Stylelint — autofix if available.
+4. Repeat until exit code 0 or record a blocker in the user reply.
+5. **`check`** (`svelte-kit sync && svelte-check`) when TypeScript / `.svelte` / SvelteKit config changed. CI-level: **`lint`** (= `lint:js` + `lint:css` + `check`).
 
-**Имя скрипта type/svelte gate — `check`**, не next-овский `type-check` и не nuxt-овский `typecheck`. Бинарь — `svelte-check`; package script — **`check`**.
+**Type/svelte gate script name is `check`**, not Next’s `type-check` and not Nuxt’s `typecheck`. Binary — `svelte-check`; package script — **`check`**.
 
-## Что исправлять
+## What to fix
 
-- **Errors** — обязательно.
-- **Warnings** — обязательно в файлах задачи; вне скоупа — упомянуть, если мешают нулевому exit code.
+- **Errors** — required.
+- **Warnings** — required in task files; outside scope — mention if they block a zero exit code.
 
-Конфиги: `eslint.config.js` / `eslint.config.mjs` / `.eslintrc*`, `.stylelintrc*` (порядок CSS — `css-property-order-stylelint`).
+Configs: `eslint.config.js` / `eslint.config.mjs` / `.eslintrc*`, `.stylelintrc*` (CSS property order — `css-property-order-stylelint`).

package/presets/claude/svelte/rules/tooling-and-review/preset-layering.md

@@ -8,29 +8,28 @@ paths:
 
 <!-- shared-core: meta/preset-layering.md -->
 
-
 # Preset layering
 
-Правила для **авторов пресетов** (`packages/ai-rules/presets/**`). Не always-on в consumer apps.
+Rules for **preset authors** (`packages/ai-rules/presets/**`). Not always-on in consumer apps.
 
-## Слои
+## Layers
 
-| Слой | Где | Что класть |
-|------|-----|------------|
-| **Core** | `presets/_shared/core/**` | Stack-agnostic prose + checklists; без frontmatter; без путей `app/**`, `Features/**`, Playwright, xcodebuild |
-| **Stack** | `presets/{cursor\|claude}/<stack>/` | Domain/tooling, always-on trio стека, stack examples в **Stack notes** |
+| Layer | Where | What to put |
+|-------|-------|-------------|
+| **Core** | `presets/_shared/core/**` | Stack-agnostic prose + checklists; no frontmatter; no paths `app/**`, `Features/**`, Playwright, xcodebuild |
+| **Stack** | `presets/{cursor\|claude}/<stack>/` | Domain/tooling, stack always-on trio, stack examples in **Stack notes** |
 | **Platform** | Cursor `.mdc` / Claude `.md` | Frontmatter (`alwaysApply`/`globs` vs `paths:`), platform-only (`BUGBOT.md`, `CLAUDE.md`) |
 
-## Куда класть новое правило
+## Where to put a new rule
 
-1. Общие принципы для всех стеков → **core** + адаптеры с `<!-- shared-core: … -->`.
-2. Только один из installable стеков (`next` / `nuxt` / `svelte` / `ios-swift` / `go` / `java` / `mcp-ts` / `php-hexagonal` / `php-laravel`) → **stack-specific** (не в `_shared`).
-3. Только Cursor или только Claude packaging → platform artifact / frontmatter, не дублировать семантику.
+1. Shared principles for all stacks → **core** + adapters with `<!-- shared-core: … -->`.
+2. Only one of the installable stacks (`next` / `nuxt` / `svelte` / `ios-swift` / `go` / `java` / `mcp-ts` / `php-hexagonal` / `php-laravel`) → **stack-specific** (not in `_shared`).
+3. Only Cursor or only Claude packaging → platform artifact / frontmatter; do not duplicate semantics.
 
 ## SoT
 
 - Packages path — SoT; root `.cursor/` — dogfood sync.
 - Per stack: **Cursor** `presets/cursor/<stack>/` → Claude twin same PR.
-- `_shared` **не** `--preset` и не копируется CLI `init`.
+- `_shared` is **not** a `--preset` and is not copied by CLI `init`.
 
-См. также: `preset-twin-sync`, `preset-token-budget`, `preset-pr-checklist`, `preset-no-cross-stack-leakage`.
+See also: `preset-twin-sync`, `preset-token-budget`, `preset-pr-checklist`, `preset-no-cross-stack-leakage`.

package/presets/claude/svelte/rules/tooling-and-review/preset-no-cross-stack-leakage.md

@@ -8,10 +8,9 @@ paths:
 
 <!-- shared-core: meta/preset-no-cross-stack-leakage.md -->
 
-
 # Preset no cross-stack leakage
 
-Запрет протекания stack-specific имён, путей и handoff stems между пресетами.
+Ban leakage of stack-specific names, paths, and handoff stems across presets.
 
 ## Principles
 

package/presets/claude/svelte/rules/tooling-and-review/preset-pr-checklist.md

@@ -8,19 +8,18 @@ paths:
 
 <!-- shared-core: meta/preset-pr-checklist.md -->
 
-
 # Preset PR checklist
 
-Чеклист для PR, затрагивающих `packages/ai-rules/presets/**` (и dogfood `.cursor/` sync).
+Checklist for PRs that touch `packages/ai-rules/presets/**` (and dogfood `.cursor/` sync).
 
 ## Before merge
 
-- [ ] **SoT:** правки в `packages/…` (не только root `.cursor/`)
-- [ ] **Core:** если менялся `_shared/core/**` — обновлены все `<!-- shared-core: … -->` consumers (или documented intentional fork)
-- [ ] **Twin:** Cursor change → Claude twin **same PR** (**FAIL** if missing on next, nuxt, svelte, ios-swift, go, java, mcp-ts, php-hexagonal, and php-laravel — см. `preset-twin-sync`)
-- [ ] **Mapping:** `claude/<stack>/rules/README.md` mapping table актуален
+- [ ] **SoT:** edits in `packages/…` (not only root `.cursor/`)
+- [ ] **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, 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
-- [ ] **Leakage:** нет чужих stack agent stems / handoff strings (`preset-no-cross-stack-leakage`)
+- [ ] **Leakage:** no foreign stack agent stems / handoff strings (`preset-no-cross-stack-leakage`)
 - [ ] **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

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

@@ -8,21 +8,20 @@ paths:
 
 <!-- shared-core: meta/preset-token-budget.md -->
 
-
 # Preset token budget
 
-Инварианты загрузки правил в **установленном** пресете (consumer app).
+Invariants for rule loading in an **installed** preset (consumer app).
 
 ## Hard caps
 
 | Platform | Always-on | Cap |
 |----------|-----------|-----|
 | Cursor | `alwaysApply: true` | **≤ 3** |
-| Claude | rules **without** `paths:` | **ровно 3** |
+| Claude | rules **without** `paths:` | **exactly 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 (где задокументировано): ≤140 строк суммарно (stretch ≤120).
+Session-start body budget (where documented): ≤140 lines total (stretch ≤120).
 
 ## Meta / author rules
 

package/presets/claude/svelte/rules/tooling-and-review/preset-twin-sync.md

@@ -8,7 +8,6 @@ paths:
 
 <!-- shared-core: meta/preset-twin-sync.md -->
 
-
 # Preset twin sync
 
 Cursor `.mdc` — **SoT per stack**. Claude topic `.md` — derived twin.

package/presets/claude/svelte/rules/tooling-and-review/technical-retro.md

@@ -1,17 +1,17 @@
 ---
-description: Роль агента для проведения технического ретроспективы (retro) команды / спринта. On-demand — предпочтительнее slash-команда /technical-retro.
+description: Agent role for a team/sprint technical retrospective (retro). On-demand — prefer the /technical-retro slash command.
 paths:
   - .claude/team/**
 ---
 
 <!-- shared-core: review/technical-retro.md -->
 
-# Техническое ретро — rule alias
+# Technical retro — rule alias
 
-Полный сценарий (включая блок **«Работа агентов»** для slug из team tasks) — в slash-команде:
+Full scenario (including the **“Agent work”** block for a slug from team tasks) lives in the slash command:
 
 **`commands/technical-retro.md`** → `/technical-retro`
 
 When a task has `metrics.json`, use the local aggregation script and state the cohort, sample size, incomplete artifacts, attribution confidence, active attempt duration, and human-gate wait separately. Do not score malformed artifacts or gate wait as agent work.
 
-Используй rule только если command недоступен. Не дублируй содержимое command в ответе — следуй command-файлу и skill `technical-retro`.
+Use this rule only if the command is unavailable. Do not duplicate the command contents in the response — follow the command file and skill `technical-retro`.

package/presets/claude/svelte/rules/ui-and-accessibility/README.md

@@ -1,12 +1,12 @@
 # UI and accessibility
 
-Компоненты, стили, пропсы.
+Components, styles, props.
 
-| Файл | Содержание | Загрузка |
-|------|------------|----------|
-| `no-rest-props-spread.md` | Явные пропсы, без `{...props}` / `$$restProps` | `paths: **/*.svelte` |
-| `css-property-order.md` | Порядок CSS (Stylelint idiomatic-order) | `paths: **/*.{css,scss,svelte}` |
-| `svelte-ui.md` | Структура SFC, стили, lib facades | `paths: src/lib/components/**,src/routes/**` |
-| `svelte-a11y-coding.md` | A11y при написании UI | `paths: src/lib/components/**,src/routes/**` |
+| File | Contents | Loading |
+|------|----------|---------|
+| `no-rest-props-spread.md` | Explicit props; no `{...props}` / `$$restProps` | `paths: **/*.svelte` |
+| `css-property-order.md` | CSS property order (Stylelint idiomatic-order) | `paths: **/*.{css,scss,svelte}` |
+| `svelte-ui.md` | SFC structure, styles, lib facades | `paths: src/lib/components/**,src/routes/**` |
+| `svelte-a11y-coding.md` | A11y when writing UI | `paths: src/lib/components/**,src/routes/**` |
 
 Deprecated stub `component-styles.md` **removed** — styles colocation lives in `svelte-ui.md`.

package/presets/claude/svelte/rules/ui-and-accessibility/svelte-ui.md

@@ -7,14 +7,14 @@ paths:
 
 # Svelte UI (SvelteKit)
 
-- Предпочитать **`.svelte` SFC** с `<script lang="ts">` (`svelte-script-conventions`).
-- Явные props (`$props()` / typed props); без массового `{...props}` / `$$restProps` (`no-rest-props-spread`).
+- Prefer **`.svelte` SFC** with `<script lang="ts">` (`svelte-script-conventions`).
+- Explicit props (`$props()` / typed props); no mass `{...props}` / `$$restProps` (`no-rest-props-spread`).
 - Svelte 5: snippets / `{@render …}` preferred for new code; legacy slots OK when following neighbors.
-- Стили: scoped `<style>` / tokens — как у соседей; порядок свойств — `css-property-order-stylelint`.
-- Данные: читать stores / runes / `load` data; **не** вызывать HTTP из `.svelte` — только через `$lib/api` / store actions.
-- Навигация: `<a href>`, `goto`, `invalidate`, `$app/navigation` — не `next/link`, не `<NuxtLink>`, не `navigateTo`.
+- Styles: scoped `<style>` / tokens — as neighbors do; property order — `css-property-order-stylelint`.
+- Data: read stores / runes / `load` data; **do not** call HTTP from `.svelte` — only via `$lib/api` / store actions.
+- Navigation: `<a href>`, `goto`, `invalidate`, `$app/navigation` — not `next/link`, not `<NuxtLink>`, not `navigateTo`.
 - A11y: `svelte-a11y-coding`.
-- Границы UI: `architecture-boundaries-ui` — no DTO in markup; map in `src/lib/api/**`.
+- UI boundaries: `architecture-boundaries-ui` — no DTO in markup; map in `src/lib/api/**`.
 
 ## Incorrect
 

package/presets/claude/svelte/skills/README.md

@@ -1,9 +1,9 @@
 # `.claude/skills` (preset svelte)
 
-[Skills](https://code.claude.com/docs/en/skills) в Claude Code — сценарии, которые подгружаются по необходимости, а не в каждой сессии целиком. Они синхронизированы по смыслу с `.cursor/skills` из Cursor-пресета.
+[Skills](https://code.claude.com/docs/en/skills) in Claude Code are scenarios loaded on demand, not wholesale every session. They are semantically synced with `.cursor/skills` from the Cursor preset.
 
-| Skill | Когда использовать |
-|-------|--------------------|
+| Skill | When to use |
+|-------|-------------|
 | `feature-delivery` | End-to-end feature work across types, API, store, UI, tests |
 | `code-review` | MR/diff review using project architecture and test standards |
 | `debug-investigation` | Reproducing and fixing bugs with root-cause evidence |
@@ -14,4 +14,4 @@
 | `write-adr` | Author an Architecture Decision Record (context / decision / consequences) |
 | `svelte-performance` | Implementer checklist: bundle, SSR/payload/client, memo, waterfalls, CWV (not a perf audit agent) |
 
-Папка копируется в `.claude/skills/` при `ai-rules init claude --preset svelte`, если существует.
+The folder is copied to `.claude/skills/` on `ai-rules init claude --preset svelte` when it exists.

package/presets/claude/svelte/skills/feature-delivery/SKILL.md

@@ -8,7 +8,7 @@ description: Delivers SvelteKit frontend features end-to-end across domain types
 1. Read task brief, acceptance criteria, and decomposition if present.
 2. Read **`feature-delivery-workflow`** and **`reference-features`** — follow layer order and mirror closest reference feature.
 3. Add or update focused tests for changed behavior.
-4. Validation from SvelteKit root: **invoke** **`post-change-lint`** after code edits (requestable, not always-on — but mandatory when code changed). Pipeline: scoped lint OK if next step is `build-verifier`.
+4. Validation from SvelteKit root: **invoke** **`post-change-lint`** after code edits (requestable, not always-on — but **must** when code changed). Pipeline: scoped lint OK if next step is `build-verifier`.
 
 ## Scope discipline
 

package/presets/claude/svelte/team/README.md

@@ -1,6 +1,6 @@
 # Agent team artifacts
 
-Каталог артефактов пайплайна «команда агентов» Claude.
+Artifact directory for the Claude Code “agent team” pipeline.
 
 ## Layout
 
@@ -97,16 +97,20 @@ Prefer **`executing`** for pipeline mode. Legacy: `analysis`, `development`, `re
 ## Workflow entry
 
 ```bash
-/task <описание задачи>
+/task <task description>
 /task-continue <slug>
 /technical-retro <slug>
 ```
 
 Legacy: `/feature-start`, `/feature-continue`.
 
+## Creating task dirs
+
+Bootstrap `<slug>/` by **writing** `pipeline.json` (Write tool). Runtime/hook owns `status.json` lifecycle; parent may only create a minimal bootstrap if missing. Do **not** use Shell `mkdir -p` — Cursor’s default sandbox returns `Operation not permitted` (especially for repos on macOS Desktop/Documents).
+
 ## Git
 
-Commit task artifacts if you want them to survive `ai-rules clean claude`. Or copy finished tasks to `docs/agent-workflow/tasks/<slug>/`.
+Commit task artifacts if you want them to survive `ai-rules clean cursor`. Or copy finished tasks to `docs/agent-workflow/tasks/<slug>/`.
 
 ## Artifact manifest and receipts
 
@@ -131,6 +135,6 @@ After a human gate, `/task-continue` closes wait via the installed hook (do not
 printf '%s\n' '{"status":"completed","action":"end_human_gate","activateNext":true}' | bash .claude/hooks/chain-team-phases.sh
 ```
 
-That appends `human_gate_ended` before the next `attempt_started`. Cursor twin uses the same payload against `.cursor/hooks/chain-team-phases.sh`. Other installable stacks ship the same ledger contract in their `team/README.md`.
+That appends `human_gate_ended` before the next `attempt_started`. Claude twins use the same payload against `.claude/hooks/chain-team-phases.sh`. Other installable stacks ship the same ledger contract in their `team/README.md`.
 
 Aggregate with `node packages/ai-rules/scripts/aggregate-agent-task-metrics.mjs --team-root .claude/team`. It reports role/agent count, completed count, total/average duration, distinct completed run IDs, separate human-gate wait, and incomplete artifacts. For retros, see `/technical-retro` → **Metrics evidence**.

package/presets/cursor/go/AGENTS.md

@@ -2,16 +2,16 @@
 
 **Repo-root agents:** see [`AGENTS.md`](../../AGENTS.md) at the project root (cross-tool setup, commands, security, living conventions pointers).
 
-| Задача | Куда смотреть |
+| Task | Where to look |
 |--------|----------------|
-| Новая work-задача | `/task` → `commands/task.md` + `agent-team-orchestrator.mdc` |
-| Фича end-to-end | skill `feature-delivery` + `feature-delivery-workflow.mdc` |
-| Стек и слои | `go-app-core.mdc`, `architecture-boundaries.mdc` |
-| После правок Go | `post-change-test.mdc` (+ `go-tooling.mdc`) |
+| New work task | `/task` → `commands/task.md` + `agent-team-orchestrator.mdc` |
+| Feature end-to-end | skill `feature-delivery` + `feature-delivery-workflow.mdc` |
+| Stack and layers | `go-app-core.mdc`, `architecture-boundaries.mdc` |
+| After Go edits | `post-change-test.mdc` (+ `go-tooling.mdc`) |
 | Integration tests | `integration-test-*` + skill `integration-testing` |
 | Code review | skill `code-review` + `code-review-mr.mdc` |
 | ADR | skill `write-adr` (on-demand) |
-| Как работает X | agent `codebase-analyzer` (explain-as-is; без `/task`) |
+| How does X work | agent `codebase-analyzer` (explain-as-is; without `/task`) |
 
 ## Install
 
@@ -19,12 +19,12 @@
 npx @bonesofspring/ai-rules init cursor --preset go
 ```
 
-Копирует rules/agents/hooks/skills/team + `REPO_AGENTS.md` → корневой `AGENTS.md`.
+Copies rules/agents/hooks/skills/team + `REPO_AGENTS.md` → root `AGENTS.md`.
 
-## Dogfood (5 сценариев)
+## Dogfood (5 scenarios)
 
-1. `/task` — новый use case (domain → ports → adapters → wire).
-2. Баг маппинга HTTP — debugger + httptest.
+1. `/task` — new use case (domain → ports → adapters → wire).
+2. HTTP mapping bug — debugger + httptest.
 3. Repository contract — integration-test trio.
 4. Unit use case — unit-test planner/generator.
 5. Secrets in logs — security-reviewer + `security-go`.

package/presets/cursor/go/MCP.md

@@ -1,16 +1,16 @@
 # MCP (preset `go`, Cursor)
 
-Копируется в `.cursor/mcp.json` при `ai-rules init cursor --preset go`.
+Copied to `.cursor/mcp.json` on `ai-rules init cursor --preset go`.
 
 ## Servers
 
-| Name | Package | Зачем |
+| Name | Package | Why |
 |------|---------|--------|
-| `context7` | `@upstash/context7-mcp` | Актуальная документация Go / stdlib / популярных библиотек |
-| `figma` | remote `https://mcp.figma.com/mcp` | Design context при необходимости; OAuth в Cursor |
+| `context7` | `@upstash/context7-mcp` | Up-to-date Go / stdlib / popular library docs |
+| `figma` | remote `https://mcp.figma.com/mcp` | Design context when needed; OAuth in Cursor |
 
-Browser e2e MCP (Playwright / Chrome DevTools) **не** входят в go-пресет.
+Browser e2e MCP (Playwright / Chrome DevTools) are **not** part of the go preset.
 
-Секреты в файл не кладём. Опционально: `CONTEXT7_API_KEY` в окружении. Figma — OAuth (токен не коммитим).
+Do not put secrets in the file. Optional: `CONTEXT7_API_KEY` in the environment. Figma — OAuth (do not commit the token).
 
-После init: Settings → MCP → включить серверы. `init` перезаписывает одноимённый `mcp.json`.
+After init: Settings → MCP → enable servers. `init` overwrites the same-named `mcp.json`.

package/presets/cursor/go/README.md

@@ -1,6 +1,6 @@
 # Go hexagonal preset (Cursor)
 
-Правила и agent-team surface для Go backend (hexagonal / ports & adapters).
+Rules and agent-team surface for Go backends (hexagonal / ports & adapters).
 
 ## Install
 
@@ -8,13 +8,13 @@
 npx @bonesofspring/ai-rules init cursor --preset go
 ```
 
-| Path | Содержание |
+| Path | Contents |
 |------|------------|
 | `REPO_AGENTS.md` | → repo-root `AGENTS.md` (cross-tool) |
 | `AGENTS.md` | → `.cursor/AGENTS.md` quick-start |
 | `BUGBOT.md` | Bugbot review priorities (Go) |
 | `rules/**` | `.mdc` + README (alwaysApply ≤3) |
-| `agents/**` | **21** ролей (+ README; includes on-demand `codebase-analyzer`) |
+| `agents/**` | **21** roles (+ README; includes on-demand `codebase-analyzer`) |
 | `skills/**` | **8** skills (incl. `integration-testing`, `write-adr`; no `react-performance`) |
 | `commands/**` | task, task-continue, feature-start/continue, technical-retro |
 | `hooks.json` + `hooks/**` | guard-shell + chain-team-phases; optional `hooks/examples/` |
@@ -36,4 +36,4 @@ Requestable: `post-change-test`, `go-tooling`, `agent-team-*`, hexagonal layer g
 
 ## Sync with Claude
 
-SoT = этот Cursor-пресет. Twin: `presets/claude/go/` **в том же PR**.
+SoT = this Cursor preset. Twin: `presets/claude/go/` **in the same PR**.

package/presets/cursor/go/agents/README.md

@@ -1,10 +1,10 @@
 # `.cursor/agents` (preset go)
 
-Ролевые subagents для командного пайплайна Cursor (Go hexagonal).
+Role subagents for the Cursor agent-team pipeline (Go hexagonal).
 
 ## Analysis (on-demand)
 
-| Agent | Файл | Production-код |
+| Agent | File | Production code |
 |-------|------|----------------|
 | Codebase analyzer | `codebase-analyzer.md` | no (explain-as-is only) |
 
@@ -25,7 +25,7 @@
 
 ## Frontmatter `readonly`
 
-Все agents — **`readonly: false`** (нужна запись в `.cursor/team/**`). Ограничения production — в теле промпта.
+All agents are **`readonly: false`** (need write access to `.cursor/team/**`). Production constraints are in the prompt body.
 
 ## Model matrix (frontmatter `model`)
 

package/presets/cursor/go/agents/task-router.md

@@ -17,21 +17,21 @@ You are a task router for a **Go hexagonal backend** agent team. You **do not**
 
 | intent | Signals | Default steps |
 |--------|---------|---------------|
-| `feature` | «добавь», «новая», «реализуй», use case/API/adapter | task-analyst → feature-developer → build-verifier → code-reviewer → qa-tester or **integration-test** trio when adapter AC |
-| `bugfix` | «баг», «fix», «не работает», «падает» | debugger → feature-developer (skipIf debugger.fixed) → build-verifier → code-reviewer |
-| `ci-fix` | «CI», «красный PR», «failing check» | ci-investigator → feature-developer (skipIf resolved) → build-verifier → code-reviewer |
-| `migration` | «миграция», «upgrade», «обнови Go/module» | task-analyst → migration-specialist → feature-developer → build-verifier → code-reviewer |
-| `perf-audit` | «производительность», «pprof», «медленно» | performance-auditor |
-| `review-only` | «ревью», «review MR», «проверь diff» | code-reviewer |
-| `test-only` | «покрой тестами» (unit+integration, no impl) | task-analyst → qa-tester |
-| `unit-only` | «unit», «юнит», «покрой use case» | unit-test-planner → unit-test-generator, or unit-test-healer |
+| `feature` | «добавь» (add), «новая» (new), «реализуй» (implement), use case/API/adapter | task-analyst → feature-developer → build-verifier → code-reviewer → qa-tester or **integration-test** trio when adapter AC | <!-- i18n-keep: E4 -->
+| `bugfix` | «баг» (bug), «fix», «не работает» (doesn't work), «падает» (crashes) | debugger → feature-developer (skipIf debugger.fixed) → build-verifier → code-reviewer | <!-- i18n-keep: E4 -->
+| `ci-fix` | «CI», «красный PR» (red PR), «failing check» | ci-investigator → feature-developer (skipIf resolved) → build-verifier → code-reviewer | <!-- i18n-keep: E4 -->
+| `migration` | «миграция» (migration), «обнови Go/module» (upgrade), "update Go/module" | task-analyst → migration-specialist → feature-developer → build-verifier → code-reviewer | <!-- i18n-keep: E4 -->
+| `perf-audit` | «производительность» (performance), «pprof», «медленно» (slow) | performance-auditor | <!-- i18n-keep: E4 -->
+| `review-only` | «ревью» (review), «проверь diff» (review MR), "check diff" | code-reviewer | <!-- i18n-keep: E4 -->
+| `test-only` | «покрой тестами» (cover with tests), (unit+integration, no impl) | task-analyst → qa-tester | <!-- i18n-keep: E4 -->
+| `unit-only` | «юнит» (unit), «покрой use case» (cover use case) | unit-test-planner → unit-test-generator, or unit-test-healer | <!-- i18n-keep: E4 -->
 | `e2e-only` / integration | «integration», «e2e», «httptest», «testcontainers» | **integration-test-planner** → **integration-test-generator**, or **integration-test-healer** |
-| `docs-only` | «документация», «README», «changelog» | task-analyst → tech-writer |
-| `refactor` | «рефакторинг», «без изменения поведения» | task-analyst → feature-developer → build-verifier → code-reviewer |
-| `spike` | «исследуй», «spike», proof of concept | task-analyst → solution-architect |
-| `retro` | «ретро», «postmortem» | (orchestrator → `/technical-retro`) |
+| `docs-only` | «документация» (docs), "README", "changelog" | task-analyst → tech-writer | <!-- i18n-keep: E4 -->
+| `refactor` | «рефакторинг» (refactor), «без изменения поведения» (no behavior change) | task-analyst → feature-developer → build-verifier → code-reviewer | <!-- i18n-keep: E4 -->
+| `spike` | «исследуй» (explore), "spike", proof of concept | task-analyst → solution-architect | <!-- i18n-keep: E4 -->
+| `retro` | «ретро» (retro), "postmortem" | (orchestrator → `/technical-retro`) | <!-- i18n-keep: E4 -->
 
-**Never schedule** Playwright (`playwright-test-*`), XCUITest (`xcuitest-test-*`), or `accessibility-reviewer`. Put them in `skipped` with reason «Go backend uses integration-test trio».
+**Never schedule** Playwright (`playwright-test-*`), XCUITest (`xcuitest-test-*`), or `accessibility-reviewer`. Put them in `skipped` with reason "Go backend uses integration-test trio".
 
 ## Pipeline profiles
 

package/presets/cursor/go/commands/README.md

@@ -1,54 +1,54 @@
 # Cursor commands (go preset)
 
-Slash-команды копируются в `.cursor/commands/` при `ai-rules init cursor --preset go`.
+Slash commands are copied to `.cursor/commands/` on `ai-rules init cursor --preset go`.
 
-## Команда агентов
+## Agent commands
 
-| Command | Назначение |
+| Command | Purpose |
 |---------|------------|
-| **`/task <описание>`** | **Главная точка входа:** router → pipeline.json → нужные роли по порядку |
-| `/task-continue <slug>` | После human gate или паузы |
-| `/feature-start <описание>` | Legacy: только analyst (без router) |
+| **`/task <description>`** | **Main entry point:** router → pipeline.json → required roles in order |
+| `/task-continue <slug>` | After a human gate or pause |
+| `/feature-start <description>` | Legacy: analyst only (no router) |
 | `/feature-continue <slug>` | Alias task-continue |
-| `/technical-retro [slug]` | Ретро; с slug — блок «Работа агентов» |
+| `/technical-retro [slug]` | Retro; with slug — “Agent work” block |
 
-## Примеры `/task`
+## `/task` examples
 
 ```
-/task Добавить CancelOrder use case (domain → ports → HTTP)
+/task Добавить CancelOrder use case (domain → ports → HTTP) (Add CancelOrder use case) <!-- i18n-keep: E4 -->
 → analyst → developer → build-verifier → reviewer → QA (integration)
 
-/task httptest CreateOrder падает на пустом body
+/task httptest CreateOrder падает на пустом body (httptest CreateOrder crashes on empty body) <!-- i18n-keep: E4 -->
 → debugger → developer → reviewer → QA (regression)
 
-/task CI упал на go test / golangci-lint в PR #142
+/task CI упал на go test / golangci-lint в PR #142 (CI failed on go test / golangci-lint in PR #142) <!-- i18n-keep: E4 -->
 → ci-investigator → developer → reviewer
 
-/task Миграция HTTP-роутера на chi v5
+/task Миграция HTTP-роутера на chi v5 (Migrate HTTP router to chi v5) <!-- i18n-keep: E4 -->
 → analyst → migration-specialist → developer → reviewer → QA
 
-/task Проверь OpenAPI drift для /orders
+/task Проверь OpenAPI drift для /orders (Check OpenAPI drift for /orders) <!-- i18n-keep: E4 -->
 → api-contract-reviewer (or analyst → …)
 
-/task Покрой unit-тестами CancelOrder use case
+/task Покрой unit-тестами CancelOrder use case (Cover CancelOrder use case with unit tests) <!-- i18n-keep: E4 -->
 → unit-planner → unit-generator
 
-/task Напиши README для нового adapter persistence
+/task Напиши README для нового adapter persistence (Write README for new persistence adapter) <!-- i18n-keep: E4 -->
 → analyst → tech-writer
 
-/task Сделай ревью изменений в internal/adapters/http
+/task Сделай ревью изменений в internal/adapters/http (Review changes in internal/adapters/http) <!-- i18n-keep: E4 -->
 → reviewer only
 
-/task Repository contract для OrderRepository
-→ integration-test-planner → generator → healer (или QA e2e-only = integration)
+/task Repository contract для OrderRepository (Repository contract for OrderRepository) <!-- i18n-keep: E4 -->
+→ integration-test-planner → generator → healer (or QA e2e-only = integration)
 ```
 
-## Связанные файлы
+## Related files
 
-- Subagents: `../agents/` (**21** ролей, включая `task-router.md`, `codebase-analyzer.md` и `integration-test-{planner,generator,healer}`; без `accessibility-reviewer` / Playwright / XCUITest)
-- Оркестратор: `../rules/agent-team-orchestrator.mdc`
+- Subagents: `../agents/` (**21** roles, including `task-router.md`, `codebase-analyzer.md`, and `integration-test-{planner,generator,healer}`; no `accessibility-reviewer` / Playwright / XCUITest)
+- Orchestrator: `../rules/agent-team-orchestrator.mdc`
 - Skills: `../skills/` (`feature-delivery`, `code-review`, `debug-investigation`, `ci-investigation`, `unit-testing`, `integration-testing`, `technical-retro`)
-- Артефакты: `../team/README.md` (`pipeline.json`, `status.json`)
+- Artifacts: `../team/README.md` (`pipeline.json`, `status.json`)
 - Hooks: `../hooks.json`, `../hooks/chain-team-phases.sh`
 
-Создавать и редактировать команды можно через `/commands` в Cursor или напрямую в этой папке пресета.
+Create and edit commands via `/commands` in Cursor or directly in this preset folder.

package/presets/cursor/go/commands/feature-continue.md

@@ -5,15 +5,15 @@ description: Legacy alias for /task-continue that resumes a feature pipeline aft
 
 # Feature continue — legacy alias
 
-> **Предпочтительно:** `/task-continue <slug>` — то же поведение, учитывает `pipeline.json`.
+> **Preferred:** `/task-continue <slug>` — same behavior, respects `pipeline.json`.
 
-Продолжение после human gate. Полная логика — в **`task-continue.md`**.
+Continue after a human gate. Full logic lives in **`task-continue.md`**.
 
-## Кратко
+## Short version
 
-1. Прочитай `pipeline.json` (если есть) и `status.json`.
-2. Сбрось `awaitingHumanGate`; определи следующий step по `pipelineIndex`.
-3. Вызови subagent для `currentAgent`.
-4. Hook продолжит цепочку при `autoChain: true`.
+1. Read `pipeline.json` (if present) and `status.json`.
+2. Clear `awaitingHumanGate`; determine the next step from `pipelineIndex`.
+3. Call the subagent for `currentAgent`.
+4. The hook continues the chain when `autoChain: true`.
 
-См. `task-continue.md` для деталей и таблицы handoff.
+See `task-continue.md` for details and the handoff table.