@bonesofspring/ai-rules 0.2.14 → 0.2.16

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

@@ -1,9 +1,9 @@
 # `.claude/skills` (preset next)
 
-[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 in every session in full. They match the intent of `.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) |
 | `react-performance` | Implementer checklist: bundle, RSC/client, memo, waterfalls, CWV (not a perf audit agent) |
 
-Папка копируется в `.claude/skills/` при `ai-rules init claude --preset next`, если существует.
+The folder is copied to `.claude/skills/` on `ai-rules init claude --preset next` when it exists.

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

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

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

@@ -1,6 +1,6 @@
 # Agent team artifacts
 
-Каталог артефактов пайплайна «команда агентов» Claude.
+Artifact directory for the Claude “agent team” pipeline.
 
 ## Layout
 
@@ -97,7 +97,7 @@ Prefer **`executing`** for pipeline mode. Legacy: `analysis`, `development`, `re
 ## Workflow entry
 
 ```bash
-/task <описание задачи>
+/task <task description>
 /task-continue <slug>
 /technical-retro <slug>
 ```

package/presets/claude/nuxt/CLAUDE.md

@@ -1,6 +1,6 @@
-# Nuxt 3 stack — project instructions
+# Nuxt stack — project instructions
 
-Краткая точка входа для Claude Code. Подробные правила — модульные файлы под `rules/` (подпапки по темам).
+Short entry point for Claude Code. Detailed rules — modular files under `rules/` (topic subfolders).
 
 **Repo-root agents:** see [`AGENTS.md`](../../AGENTS.md) at the project root (cross-tool setup, commands, security, living conventions pointers).
 
@@ -8,27 +8,27 @@ See @rules/README.md for the full catalog and loading strategy.
 
 ## Conventions
 
-- **Одна тема на файл**; для больших областей — подпапки в `rules/<topic>/`.
-- **Session-start rules** (без `paths:`) — ровно **три**: `nuxt-app-core`, `package-manager`, `code-quality`.
-- **Domain-specific rules** — YAML frontmatter `paths:` (подгружаются при работе с matching-файлами); `post-change-lint` — requestable (**обязателен после code edits**); orchestrator и code-review — on-demand.
-- Slash-команды — в `commands/`; сценарии — в `skills/`; subagents — в `agents/`.
+- **One topic per file**; for large areas — subfolders under `rules/<topic>/`.
+- **Session-start rules** (no `paths:`) — exactly **three**: `nuxt-app-core`, `package-manager`, `code-quality`.
+- **Domain-specific rules** — YAML frontmatter `paths:` (loaded when matching files); `post-change-lint` — requestable (**required after code edits**); orchestrator and code-review — on-demand.
+- Slash commands — in `commands/`; scenarios — in `skills/`; subagents — in `agents/`.
 
 ## Quick start
 
-| Задача | Куда смотреть |
-|--------|----------------|
-| Любая новая work-задача | `commands/task.md` + `rules/tooling-and-review/agent-team-orchestrator.md` |
-| Новая фича end-to-end | skill `feature-delivery` + `rules/architecture/feature-delivery-workflow.md` |
-| Эталонные фичи | `rules/architecture/reference-features.md` (заполнить TBD в репо) |
-| Стек и слои | `rules/stack/nuxt-app-core.md` |
-| Nuxt file-based routing | `rules/stack/nuxt-pages-routing.md` |
-| A11y при кодинге UI | `rules/ui-and-accessibility/vue-a11y-coding.md` |
-| После правок кода | `rules/tooling-and-review/post-change-lint.md` (**requestable**, обязателен после edits) |
-| Валидация перед review | agent `build-verifier` |
+| Task | Where to look |
+|------|----------------|
+| Any new work task | `commands/task.md` + `rules/tooling-and-review/agent-team-orchestrator.md` |
+| New end-to-end feature | skill `feature-delivery` + `rules/architecture/feature-delivery-workflow.md` |
+| Reference features | `rules/architecture/reference-features.md` (fill TBD in the repo) |
+| Stack and layers | `rules/stack/nuxt-app-core.md` |
+| Nuxt routing | `rules/stack/nuxt-pages-routing.md` |
+| A11y when coding UI | `rules/ui-and-accessibility/vue-a11y-coding.md` |
+| After code edits | `rules/tooling-and-review/post-change-lint.md` (**requestable**, required after edits) |
+| Validation before review | agent `build-verifier` |
 | Code review MR | skill `code-review` + `rules/tooling-and-review/code-review-mr.md` |
 | Security (auth/forms/env) | `rules/tooling-and-review/security-nuxt.md` + agent `security-reviewer` |
-| Как работает X | agent `codebase-analyzer` (explain-as-is; без `/task`) |
-| Техническое ретро | `commands/technical-retro.md` + skill `technical-retro` |
+| How X works | agent `codebase-analyzer` (explain-as-is; no `/task`) |
+| Technical retro | `commands/technical-retro.md` + skill `technical-retro` |
 
 ## Install
 
@@ -36,4 +36,4 @@ See @rules/README.md for the full catalog and loading strategy.
 npx @bonesofspring/ai-rules init claude --preset nuxt
 ```
 
-Копирует `CLAUDE.md`, `rules/**`, `commands/**`, `agents/**`, `hooks/**`, `team/**`, `MCP.md` в `.claude/`, плюс `mcp.json` → **`.mcp.json`** и `REPO_AGENTS.md` → корневой **`AGENTS.md`**. Skills: `write-adr`, `vue-performance` (on-demand).
+Copies `CLAUDE.md`, `rules/**`, `commands/**`, `agents/**`, `hooks/**`, `team/**`, `MCP.md` into `.claude/`, plus `mcp.json` → **`.mcp.json`** and `REPO_AGENTS.md` → root **`AGENTS.md`**. Skills: `write-adr`, `vue-performance` (on-demand).

package/presets/claude/nuxt/MCP.md

@@ -1,16 +1,16 @@
 # MCP (preset `nuxt`, Claude Code)
 
-Копируется в **корень проекта** как `.mcp.json` при `ai-rules init claude --preset nuxt` (не в `.claude/` — так устроен project scope Claude Code).
+Copied to the **project root** as `.mcp.json` on `ai-rules init claude --preset nuxt` (not under `.claude/` — that is how Claude Code project scope works).
 
 ## Servers
 
-| Name | Package | Зачем |
-|------|---------|--------|
-| `context7` | `@upstash/context7-mcp` | Актуальная документация Vue/Nuxt/TS |
-| `playwright-test` | `@playwright/mcp` | Browser MCP; имя сервера совпадает с `mcp__playwright-test__*` в agents |
+| Name | Package | Why |
+|------|---------|-----|
+| `context7` | `@upstash/context7-mcp` | Up-to-date Vue/Nuxt/TS docs |
+| `playwright-test` | `@playwright/mcp` | Browser MCP; server name matches `mcp__playwright-test__*` in agents |
 | `chrome-devtools` | `chrome-devtools-mcp` | Live DOM/network/performance |
-| `figma` | remote `https://mcp.figma.com/mcp` | Design context → код; OAuth при первом подключении |
+| `figma` | remote `https://mcp.figma.com/mcp` | Design context → code; OAuth on first connect |
 
-Секреты не коммитим. Опционально: `CONTEXT7_API_KEY`. Figma — OAuth (токен в файл не пишем). После clone/init Claude Code попросит approve project MCP (`/mcp`).
+Do not commit secrets. Optional: `CONTEXT7_API_KEY`. Figma — OAuth (do not write the token into the file). After clone/init Claude Code will ask to approve project MCP (`/mcp`).
 
-Для полного Playwright Test Agents loop (`planner_*` / `generator_*` / `test_*`) дополнительно: `npx playwright init-agents --loop=claude` в приложении с `@playwright/test`.
+For the full Playwright Test Agents loop (`planner_*` / `generator_*` / `test_*`) additionally: `npx playwright init-agents --loop=claude` in the app with `@playwright/test`.

package/presets/claude/nuxt/README.md

@@ -1,39 +1,39 @@
-# Preset `next` (Claude Code)
+# Preset `nuxt` (Claude Code)
 
-Структура отличается от пресета Cursor: здесь повторяется типичный **layout проекта Claude Code** под `.claude/`, а не плоский список `.mdc` в `rules/`.
+Layout differs from the Cursor preset: here the typical **Claude Code project layout** under `.claude/` is mirrored, not a flat `.mdc` list in `rules/`.
 
-| В пресете | Куда копирует `ai-rules init claude --preset nuxt` |
-|-----------|-----------------------------------------------------|
-| `CLAUDE.md` | `.claude/CLAUDE.md` (точка входа, грузится в начале сессии) |
-| `rules/**` | `.claude/rules/**` (рекурсивно: подпапки по темам, см. [документацию](https://code.claude.com/docs/en/memory#organize-rules-with-clauderules)) |
+| In the preset | Where `ai-rules init claude --preset nuxt` copies |
+|---------------|---------------------------------------------------|
+| `CLAUDE.md` | `.claude/CLAUDE.md` (entry point, loaded at session start) |
+| `rules/**` | `.claude/rules/**` (recursive: topic subfolders; see [docs](https://code.claude.com/docs/en/memory#organize-rules-with-clauderules)) |
 | `commands/**` | `.claude/commands/**` |
-| `skills/**` | `.claude/skills/**` (если папка есть) |
-| `agents/**` | `.claude/agents/**` (если папка есть) |
-| `hooks/**` | `.claude/hooks/**` (если папка есть) |
-| `team/**` | `.claude/team/**` (шаблон артефактов agent team) |
-| `mcp.json` | **`.mcp.json`** в корне проекта (Claude project MCP) |
+| `skills/**` | `.claude/skills/**` (if present) |
+| `agents/**` | `.claude/agents/**` (if present) |
+| `hooks/**` | `.claude/hooks/**` (if present) |
+| `team/**` | `.claude/team/**` (agent-team artifact template) |
+| `mcp.json` | **`.mcp.json`** at project root (Claude project MCP) |
 | `MCP.md` | `.claude/MCP.md` |
 
-Файлы правил — обычный Markdown с опциональным YAML frontmatter (`paths:` для скоупа по путям), не формат `.mdc` Cursor.
+Rule files are ordinary Markdown with optional YAML frontmatter (`paths:` for path scope), not Cursor `.mdc`.
 
 ## Preset taxonomy & contributing
 
 - **Layers:** Core → Stack → Platform — [`../../_shared/README.md`](../../_shared/README.md)
 - **Contribution guide:** [`../../docs/PRESET-CONTRIBUTION.md`](../../docs/PRESET-CONTRIBUTION.md)
-- **Cursor SoT:** `presets/cursor/nuxt/` — этот пресет derived twin; правки Cursor first, same PR
+- **Cursor SoT:** `presets/cursor/nuxt/` — this preset is the derived twin; edit Cursor first, same PR
 - **Cursor→Claude map + core table:** [`rules/README.md`](./rules/README.md)
 - **Author meta:** `tooling-and-review/preset-*.md` (`paths:` on `packages/ai-rules/presets/**` only)
 
 ## Agent team workflow
 
-Cursor-пресет и Claude-пресет используют один и тот же смысловой workflow:
+The Cursor and Claude presets share the same workflow intent:
 
 - `/task <desc>` → `task-router` → `pipeline.json`;
-- `/task-continue <slug>` → продолжение после human gate;
-- `.claude/agents/*.md` → **22** ролей: planning (router, analyst, architect, migration, api-contract), analysis (`codebase-analyzer`), implementation (debugger, ci-investigator, developer), review (code, a11y, security, perf), testing (QA, unit trio, playwright trio), docs (tech-writer), build (build-verifier);
-- `.claude/team/tasks/<slug>/` → handoff-артефакты (`brief.md`, `decomposition.md`, `review.md`, `migration-plan.md`, `ci-report.md`, `status.json`, …).
+- `/task-continue <slug>` → continue after a human gate;
+- `.claude/agents/*.md` → **22** roles: planning (router, analyst, architect, migration, api-contract), analysis (`codebase-analyzer`), implementation (debugger, ci-investigator, developer), review (code, a11y, security, perf), testing (QA, unit trio, playwright trio), docs (tech-writer), build (build-verifier);
+- `.claude/team/tasks/<slug>/` → handoff artifacts (`brief.md`, `decomposition.md`, `review.md`, `migration-plan.md`, `ci-report.md`, `status.json`, …).
 
 ## Cross-tool root AGENTS
 
 `REPO_AGENTS.md` → project-root `AGENTS.md` on init. Living conventions: `team/conventions.md`. Skill `write-adr` on-demand.
-Next also ships `vue-performance` skill and Incorrect/Correct samples on golden domain rules.
+Nuxt also ships `vue-performance` skill and Incorrect/Correct samples on golden domain rules.

package/presets/claude/nuxt/agents/README.md

@@ -1,45 +1,45 @@
 # `.claude/agents` (preset nuxt)
 
-Специализированные подагенты (personas) — по [документации Claude Code](https://code.claude.com/docs), если используете их в проекте.
+Role subagents for the Claude Code team pipeline.
 
 ## Planning and routing
 
-| Agent | Файл | Production-код |
-|-------|------|----------------|
+| Agent | File | Production code |
+|-------|------|-----------------|
 | Router | `task-router.md` | no |
-| Аналитик | `task-analyst.md` | no |
-| Архитектор | `solution-architect.md` | no |
+| Analyst | `task-analyst.md` | no |
+| Architect | `solution-architect.md` | no |
 | Migration planner | `migration-specialist.md` | no |
 | API contract reviewer | `api-contract-reviewer.md` | no |
 
 ## Analysis (on-demand)
 
-| Agent | Файл | Production-код |
-|-------|------|----------------|
+| Agent | File | Production code |
+|-------|------|-----------------|
 | Codebase analyzer | `codebase-analyzer.md` | no (explain-as-is only) |
 
 ## Implementation and CI
 
-| Agent | Файл | Production-код |
-|-------|------|----------------|
+| Agent | File | Production code |
+|-------|------|-----------------|
 | Debugger | `debugger.md` | minimal fix only |
 | CI investigator | `ci-investigator.md` | minimal CI fix only |
 | Build verifier | `build-verifier.md` | no |
-| Разработчик | `feature-developer.md` | yes |
+| Developer | `feature-developer.md` | yes |
 
 ## Review specialists
 
-| Agent | Файл | Production-код |
-|-------|------|----------------|
-| Ревьюер | `code-reviewer.md` | no |
+| Agent | File | Production code |
+|-------|------|-----------------|
+| Reviewer | `code-reviewer.md` | no |
 | A11y reviewer | `accessibility-reviewer.md` | no |
 | Security reviewer | `security-reviewer.md` | no |
 | Performance auditor | `performance-auditor.md` | no |
 
 ## Testing
 
-| Agent | Файл | Production-код |
-|-------|------|----------------|
+| Agent | File | Production code |
+|-------|------|-----------------|
 | QA | `qa-tester.md` | tests only |
 | Unit planner | `unit-test-planner.md` | no |
 | Unit generator | `unit-test-generator.md` | tests only |
@@ -50,37 +50,44 @@
 
 ## Documentation
 
-| Agent | Файл | Production-код |
-|-------|------|----------------|
+| Agent | File | Production code |
+|-------|------|-----------------|
 | Tech writer | `tech-writer.md` | docs only |
 
-Папка копируется в `.claude/agents/` при `ai-rules init claude --preset nuxt`.
+Copied to `.claude/agents/` on `ai-rules init claude --preset nuxt`.
+
+## Frontmatter `readonly`
+
+All pipeline agents are **`readonly: false`**. They need write access under `.claude/team/**` (`pipeline.json`, `brief.md`, `review.md`, `status.json`, …).
+
+The “do not touch production / `app/**`” limit is set **in the prompt body**, not via the `readonly` flag. In Claude Code `readonly: true` blocks *any* file edits (including team) — that breaks the pipeline for team agents.
 
 ## Model matrix (frontmatter `model`)
 
-SoT по умолчанию — YAML `model` в каждом agent-файле. Опциональный `steps[].model` (`cheap` \| `standard` \| `strong`) переопределяет тир на шаге (см. `task-router.md`, `tooling-and-review/agent-team-orchestrator.md`).
+Default SoT — YAML `model` in each agent file. Optional `steps[].model` (`cheap` \| `standard` \| `strong`) overrides the tier for a pipeline step (see `task-router.md`, `rules/tooling-and-review/agent-team-orchestrator.md`).
 
 | Tier | Default frontmatter | Agents |
 |------|---------------------|--------|
 | **cheap** | `fast` | `task-router`, `task-analyst`, `build-verifier`, `code-reviewer`, `tech-writer`, `codebase-analyzer` |
-| **standard** | `inherit` or `sonnet` | `feature-developer`, `debugger`, `ci-investigator`, `api-contract-reviewer`, `accessibility-reviewer`, `qa-tester`, `unit-test-*`, `playwright-test-*` (`sonnet` where already pinned) |
-| **strong** | `opus` | `solution-architect`, `migration-specialist`, `security-reviewer`, `performance-auditor` |
+| **standard** | `inherit` | `feature-developer`, `debugger`, `ci-investigator`, `api-contract-reviewer`, `accessibility-reviewer`, `qa-tester`, `unit-test-*`, `playwright-test-*` |
+| **strong** | `claude-opus-4-8[effort=high]` | `solution-architect`, `migration-specialist`, `security-reviewer`, `performance-auditor` |
 
 **Notes**
 
-- Claude Code aliases: `haiku` / `sonnet` / `opus` / `inherit` (full IDs also OK). Preset keeps `fast` for cheap agents for cross-tooling parity with Cursor; if ignored, prefer `haiku` locally.
-- Resolution order (Claude Code): env `CLAUDE_CODE_SUBAGENT_MODEL` → per-invocation `model` → frontmatter → parent session.
+- `inherit` = parent-chat model (usually stronger than `fast`).
+- Strong pin uses Cursor bracket options (`[effort=high]`). If the ID is blocked by plan/admin, Cursor falls back to a compatible model.
+- Alternate strong pin when Opus unavailable: `composer-2.5[fast=false]` (edit frontmatter locally).
 - Never put `strong` on `build-verifier` / `tech-writer` / `task-router`.
 
-## Оркестрация
+## Orchestration
 
-| Command | Назначение |
-|---------|------------|
-| `/task <desc>` | Router → dynamic pipeline → первый agent |
-| `/task-continue <slug>` | После human gate |
-| `/feature-start`, `/feature-continue` | Legacy (совместимость) |
+| Command | Purpose |
+|---------|---------|
+| `/task <desc>` | Router → dynamic pipeline → first agent |
+| `/task-continue <slug>` | After a human gate |
+| `/feature-start`, `/feature-continue` | Legacy (compatibility) |
 
-Правило: `tooling-and-review/agent-team-orchestrator.md`. План: `pipeline.json` в `.claude/team/tasks/<slug>/`.
+Rule: `rules/tooling-and-review/agent-team-orchestrator.md`. Plan: `pipeline.json` under `.claude/team/tasks/<slug>/`.
 
 ## Pipeline routing
 
@@ -122,7 +129,7 @@ SoT по умолчанию — YAML `model` в каждом agent-файле.
   "steps": [
     { "agent": "task-analyst", "label": "Clarify and decompose" },
     { "agent": "feature-developer", "label": "Implement + unit tests", "scope": "unit-in-dev" },
-    { "agent": "build-verifier", "label": "Lint, typecheck, unit smoke" },
+    { "agent": "build-verifier", "label": "Lint, check, unit smoke" },
     { "agent": "code-reviewer", "label": "Code review" }
   ],
   "humanGates": ["after:task-analyst"],

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

@@ -16,7 +16,7 @@ You are a senior frontend developer working in a Nuxt 3 monorepo with strict lay
 ## Task execution rules
 
 - Work tasks in dependency order (types → api → mocks → store → ui → **unit** → e2e).
-- **Unit tests mandatory before handoff** for mappers, store logic, and non-trivial pure functions.
+- **Unit tests must run before handoff** for mappers, store logic, and non-trivial pure functions.
 - Mark completed tasks in `decomposition.md`.
 - Validation: **`rules/tooling-and-review/post-change-lint.md`**. If pipeline next step is **`build-verifier`**, scoped lint/typecheck on **changed files** is enough; full project lint is build-verifier's job.
 

package/presets/claude/nuxt/agents/task-analyst.md

@@ -8,7 +8,7 @@ You are a senior business/technical analyst for a Nuxt 3 frontend team.
 
 Your job is to reach **Definition of Ready (DoR)** before any implementation starts. You may write only `.claude/team/**` artifacts. You do **not** write production code or modify application source files.
 
-## Clarification cycle (mandatory)
+## Clarification cycle (must)
 
 1. Rephrase the task in your own words (goal, user value, boundaries).
 2. Ask **1–3 questions per iteration** — never more than 3 at once.

package/presets/claude/nuxt/agents/task-router.md

@@ -1,6 +1,6 @@
 ---
 name: task-router
-description: Task routing specialist. Analyzes user prompt, detects intent, and writes pipeline.json with ordered agent steps. Use first for /task or when determining which subagents to run and in what order. Readonly — never writes production code.
+description: Task routing specialist. Analyzes user prompt, detects intent, and writes pipeline.json with ordered agent steps. Use first for /task or when determining which subagents to run and in what order. No production code — writes team artifacts only.
 model: fast
 ---
 
@@ -9,27 +9,27 @@ You are a task router for a Nuxt 3 frontend agent team. You **do not** implement
 ## Inputs
 
 - User task description (from `/task` or orchestrator).
-- Optional: existing files under `.claude/team/tasks/<slug>/`.
+- Optional: existing files under `.cursor/team/tasks/<slug>/`.
 - Pipeline JSON schema, examples, step fields — **`agents/README.md`**.
 
 ## Intent detection
 
 | intent | Signals in prompt | Default steps |
 |--------|-------------------|---------------|
-| `feature` | «добавь», «новая», «реализуй», «сделай», new UI/API/store | task-analyst → feature-developer (unit-in-dev) → build-verifier → code-reviewer → qa-tester (e2e-only) or playwright trio |
-| `bugfix` | «баг», «fix», «не работает», «падает», «ошибка», regression | debugger → feature-developer (skipIf debugger.fixed) → build-verifier → code-reviewer → qa-tester (regression) |
-| `ci-fix` | «CI», «упал пайплайн», «красный PR», «failing check», «lint в CI» | ci-investigator → feature-developer (skipIf ci-investigator.resolved) → build-verifier → code-reviewer |
-| `migration` | «миграция», «upgrade», «обнови Next», «переход на», major version | task-analyst → migration-specialist → feature-developer → build-verifier → code-reviewer → qa-tester (regression) |
-| `perf-audit` | «производительность», «perf», «bundle», «LCP», «медленно», «waterfall» | performance-auditor |
-| `a11y` | «a11y», «доступность», «accessibility», «WCAG», «screen reader», «клавиатура» | task-analyst → feature-developer → build-verifier → accessibility-reviewer → code-reviewer |
-| `review-only` | «ревью», «review MR», «проверь diff», «code review» | code-reviewer |
-| `test-only` | «покрой тестами», «напиши тесты» (mixed unit+e2e, no impl) | task-analyst → qa-tester |
-| `unit-only` | «unit», «юнит», «mapper tests», «покрой маппер», «почини unit» | unit-test-planner → unit-test-generator, or unit-test-healer |
-| `e2e-only` | «e2e», «playwright», «browser test», «сценарии e2e», «почини e2e» | playwright-test-planner → playwright-test-generator, or playwright-test-healer |
-| `docs-only` | «документация», «README», «changelog», «ADR», «migration guide» | task-analyst → tech-writer |
-| `refactor` | «рефакторинг», «без изменения поведения», «почисти» | task-analyst → feature-developer → build-verifier → code-reviewer |
-| `spike` | «исследуй», «оцени», «можно ли», «spike», proof of concept | task-analyst → solution-architect |
-| `retro` | «ретро», «разбор», «postmortem» | (no pipeline — orchestrator runs `/technical-retro`) |
+| `feature` | «добавь» (add), «новая» (new), «реализуй» (implement), «сделай» (do/build), new UI/API/store | task-analyst → feature-developer (unit-in-dev) → build-verifier → code-reviewer → qa-tester (e2e-only) or playwright trio | <!-- i18n-keep: E4 -->
+| `bugfix` | «баг» (bug), «fix», «не работает» (doesn't work), «падает» (crashes), «ошибка» (error), regression | debugger → feature-developer (skipIf debugger.fixed) → build-verifier → code-reviewer → qa-tester (regression) | <!-- i18n-keep: E4 -->
+| `ci-fix` | «CI», «упал пайплайн» (pipeline failed), «красный PR» (red PR), «failing check», «lint в CI» (lint in CI) | ci-investigator → feature-developer (skipIf ci-investigator.resolved) → build-verifier → code-reviewer | <!-- i18n-keep: E4 -->
+| `migration` | «миграция» (migration), «upgrade», «обнови Nuxt» (upgrade Nuxt), «переход на» (move to), major version | task-analyst → migration-specialist → feature-developer → build-verifier → code-reviewer → qa-tester (regression) | <!-- i18n-keep: E4 -->
+| `perf-audit` | «производительность» (performance), «perf», «bundle», «LCP», «медленно» (slow), «waterfall» | performance-auditor | <!-- i18n-keep: E4 -->
+| `a11y` | «a11y», «доступность» (accessibility), «accessibility», «WCAG», «screen reader», «клавиатура» (keyboard) | task-analyst → feature-developer → build-verifier → accessibility-reviewer → code-reviewer | <!-- i18n-keep: E4 -->
+| `review-only` | «ревью» (review), «review MR», «проверь diff» (check diff), «code review» | code-reviewer | <!-- i18n-keep: E4 -->
+| `test-only` | «покрой тестами» (cover with tests), «напиши тесты» (write tests) (mixed unit+e2e, no impl) | task-analyst → qa-tester | <!-- i18n-keep: E4 -->
+| `unit-only` | «unit», «юнит» (unit), «mapper tests», «покрой маппер» (cover mapper), «почини unit» (fix unit) | unit-test-planner → unit-test-generator, or unit-test-healer | <!-- i18n-keep: E4 -->
+| `e2e-only` | «e2e», «playwright», «browser test», «сценарии e2e» (e2e scenarios), «почини e2e» (fix e2e) | playwright-test-planner → playwright-test-generator, or playwright-test-healer | <!-- i18n-keep: E4 -->
+| `docs-only` | «документация» (documentation), «README», «changelog», «ADR», «migration guide» | task-analyst → tech-writer | <!-- i18n-keep: E4 -->
+| `refactor` | «рефакторинг» (refactoring), «без изменения поведения» (no behavior change), «почисти» (clean up) | task-analyst → feature-developer → build-verifier → code-reviewer | <!-- i18n-keep: E4 -->
+| `spike` | «исследуй» (investigate), «оцени» (estimate), «можно ли» (is it possible), «spike», proof of concept | task-analyst → solution-architect | <!-- i18n-keep: E4 -->
+| `retro` | «ретро» (retro), «разбор» (postmortem), «postmortem» | (no pipeline — orchestrator runs `/technical-retro`) | <!-- i18n-keep: E4 -->
 
 ## Pipeline profiles
 
@@ -39,9 +39,9 @@ Set optional top-level `"profile": "full" | "standard" | "light"` in `pipeline.j
 |---------|------|------------------------|
 | `full` | Multi-layer, new public API, e2e coverage needed, incomplete AC | analyst → [architect] → developer → build-verifier → reviewer → qa-tester |
 | `standard` | Single layer, default work | analyst → developer → build-verifier → reviewer |
-| `light` | Trivial: one file/layer, explicit AC, «просто поправь», «typo», user «без pipeline» | developer → build-verifier |
+| `light` | Trivial: one file/layer, explicit AC, «просто поправь» (just fix it), «typo», user «без pipeline» (without pipeline) | developer → build-verifier | <!-- i18n-keep: E4 -->
 
-**Light signals:** один файл, один слой, явный AC в промпте, нет архитектурного риска. **Never skip `build-verifier`** after developer when `app/**` changed. **Skip `code-reviewer`** in light only for non-prod preset/docs tasks — for `pages/components/stores` changes prefer standard.
+**Light signals:** one file, one layer, explicit AC in prompt, no architectural risk. **Never skip `build-verifier`** after developer when `app/**` changed. **Skip `code-reviewer`** in light only for non-prod preset/docs tasks — for `app/src` changes prefer standard.
 
 **Light by intent:**
 
@@ -53,7 +53,7 @@ Set optional top-level `"profile": "full" | "standard" | "light"` in `pipeline.j
 | `docs-only` | tech-writer (skip analyst if brief exists) |
 | `ci-fix` | ci-investigator → build-verifier (`skipIf: ci-investigator.resolved`) |
 
-Fixtures: `.claude/team/fixtures/` (feature-full, feature-light, bugfix-standard).
+Fixtures: `.cursor/team/fixtures/` (feature-full, feature-light, bugfix-standard).
 
 ## Routing decision rubric
 
@@ -99,7 +99,7 @@ Optional per-step field: `"model": "cheap" | "standard" | "strong"`. Omit → ag
 | `intent: perf-audit` / security-heavy feature | `strong` on auditor/reviewer step |
 | Always | **never** `strong` on `build-verifier`, `tech-writer`, `task-router` |
 
-Claude Code mapping when orchestrator invokes Agent tool: `cheap` → `haiku` (or rely on frontmatter `fast`); `standard` → omit / `sonnet` / inherit; `strong` → pass `opus` (or rely on frontmatter `opus`). Prefer explicit per-invocation `model` when frontmatter is unreliable.
+Cursor mapping when orchestrator invokes Task: `cheap` → pass `model: "fast"` if the tool accepts it; `standard`/`strong` → **do not** pass `fast` (rely on agent frontmatter pin / inherit).
 
 ## humanGates (defaults)
 
@@ -116,7 +116,7 @@ Claude Code mapping when orchestrator invokes Agent tool: `cheap` → `haiku` (o
 
 ## Output
 
-Write `.claude/team/tasks/<slug>/pipeline.json` and initialize the routing entry in `artifact-manifest.json`; set `.claude/team/active-task.json`. The orchestration runtime creates and owns `status.json`.
+Write `.cursor/team/tasks/<slug>/pipeline.json` and initialize the routing entry in `artifact-manifest.json`; set `.cursor/team/active-task.json`. The orchestration runtime creates and owns `status.json`.
 
 ## Handoff to orchestrator
 
@@ -134,7 +134,7 @@ Return the routing receipt to the orchestrator. The orchestration runtime/hook e
 
 ## Artifact contract
 
-- **Authoritative inputs:** read `.claude/team/tasks/<slug>/artifact-manifest.json` first; consume the user request and any existing authoritative task/decision entries.
+- **Authoritative inputs:** read `.cursor/team/tasks/<slug>/artifact-manifest.json` first; consume the user request and any existing authoritative task/decision entries.
 - **Owned outputs:** `pipeline.json` and the routing manifest entry; upsert only the manifest entry assigned by handoff (`artifactOutputId`; fallback `routing`) and preserve all foreign entries.
 - **Terminal receipt:** cover applicable AC/task IDs, list authoritative evidence paths, and emit `completed` or `blocked`. Bind it to the supplied `attemptId` when present.
 - **Shared state:** never create or mutate `status.json` or `metrics.json`; the orchestration runtime/hook owns lifecycle, gates, retries, attempts, and timestamps.

package/presets/claude/nuxt/commands/README.md

@@ -1,13 +1,51 @@
-# `.claude/commands` (preset nuxt)
+# Claude Code commands (nuxt preset, Claude)
 
-Определения slash-команд и on-demand сценариев. Копируются в `.claude/commands/` при `ai-rules init claude --preset nuxt`.
+Slash commands are copied to `.claude/commands/` on `ai-rules init claude --preset nuxt`.
 
-| Файл | Назначение |
-|------|------------|
-| `task.md` | Единая точка входа: router → dynamic pipeline → первый agent |
-| `task-continue.md` | Продолжение после human gate / паузы по `pipeline.json` |
-| `feature-start.md` | Legacy analyst-only старт без router |
-| `feature-continue.md` | Legacy продолжение; для `pipeline.json` делегирует смысл `/task-continue` |
-| `technical-retro.md` | Фасилитация технического ретро, включая блок «Работа агентов» |
+## Agent team commands
 
-См. также корневой `README.md` пресета — у Claude Code помимо `rules/` и `commands/` используются `skills/`, `agents/`, `hooks/`, `team/`.
+| Command | Purpose |
+|---------|---------|
+| **`/task <description>`** | **Main entry:** router → pipeline.json → roles in order |
+| `/task-continue <slug>` | After a human gate or pause |
+| `/feature-start <description>` | Legacy: analyst only (no router) |
+| `/feature-continue <slug>` | Alias of task-continue |
+| `/technical-retro [slug]` | Retro; with slug — “Agent work” block |
+
+## `/task` examples
+
+```
+/task Add a date filter to Order History
+→ analyst → developer → reviewer → QA
+
+/task Order History crashes on an empty list
+→ debugger → developer → reviewer → QA (regression)
+
+/task CI failed on lint in PR #142
+→ ci-investigator → developer → reviewer
+
+/task Migrate to Nuxt 15
+→ analyst → migration-specialist → developer → reviewer → QA
+
+/task Check accessibility of the payment modal
+→ analyst → developer → a11y-reviewer → code-reviewer
+
+/task Cover the orders mapper with unit tests
+→ unit-planner → unit-generator
+
+/task Write a README for the new filters feature
+→ analyst → tech-writer
+
+/task Review changes in store/orders
+→ reviewer only
+```
+
+## Related files
+
+- Subagents: `../agents/` (**22** roles, including `task-router.md`, `codebase-analyzer.md`)
+- Orchestrator: `../rules/tooling-and-review/agent-team-orchestrator.md`
+- Skills: `../skills/` (`feature-delivery`, `code-review`, `debug-investigation`, `ci-investigation`, `unit-testing`, `playwright-e2e`, `technical-retro`)
+- Artifacts: `../team/README.md` (`pipeline.json`, `status.json`)
+- Hooks: `../hooks.json`, `../hooks/chain-team-phases.sh`
+
+Create and edit commands via Claude Code slash commands or directly in this preset folder.

package/presets/claude/nuxt/commands/feature-continue.md

@@ -3,49 +3,17 @@ name: feature-continue
 description: Legacy alias for /task-continue that resumes a feature pipeline after human approval or pause.
 ---
 
-# Feature continue — продолжение после утверждения brief
+# Feature continue — legacy alias
 
-Legacy-команда для продолжения после human gate. Для новых пайплайнов с `pipeline.json` используй те же правила, что в `/task-continue`.
+> **Prefer:** `/task-continue <slug>` — same behavior, respects `pipeline.json`.
 
-## Аргументы
+Continue after a human gate. Full logic — in **`task-continue.md`**.
 
-`<slug>` — идентификатор задачи из `.claude/team/tasks/<slug>/`.
+## Short form
 
-## Preconditions
+1. Read `pipeline.json` (if present) and `status.json`.
+2. Clear `awaitingHumanGate`; determine the next step from `pipelineIndex`.
+3. Invoke the subagent for `currentAgent`.
+4. The hook continues the chain when `autoChain: true`.
 
-1. Прочитай `.claude/team/tasks/<slug>/brief.md` и `decomposition.md`.
-2. Если есть `pipeline.json`, делегируй поведение `/task-continue <slug>`.
-3. Если `pipeline.json` нет, прочитай `status.json`. Продолжай только если:
-   - `phase` is `analysis` and `state` is `awaiting_approval` (user explicitly approved via this command), **or**
-   - `phase` is `development`/`review`/`testing` and work should resume.
-
-## Legacy алгоритм без `pipeline.json`
-
-1. Обнови `status.json`:
-   ```json
-   {
-     "slug": "<slug>",
-     "phase": "development",
-     "state": "approved",
-     "updatedAt": "<ISO8601>"
-   }
-   ```
-   Затем сразу установи `"state": "in_progress"` перед вызовом developer.
-
-2. Запиши `.claude/team/active-task.json` → `{ "slug": "<slug>" }`.
-
-3. Вызови subagent **feature-developer** с контекстом:
-   - пути к `brief.md`, `decomposition.md`, `status.json`;
-   - указание следовать `rules/architecture/feature-delivery-workflow.md`.
-
-4. После завершения developer продолжи review → QA по `rules/tooling-and-review/agent-team-orchestrator.md`.
-
-## Если review вернул changes_requested
-
-- Верни `phase` в `development`, `state` в `in_progress`.
-- Снова вызови **feature-developer** с списком правок от reviewer.
-
-## Не делать
-
-- Не пропускать human gate без явного `/feature-continue`.
-- Не совмещать роли developer и reviewer в одном subagent-вызове.
+See `task-continue.md` for details and the handoff table.