@bonesofspring/ai-rules 0.1.40 → 0.1.42

package/presets/claude/next/rules/testing/playwright-agents.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - app/__tests__/e2e/**
+---
+
 # Playwright Agents in this project
 
 Playwright Agents (planner, generator, healer) **must follow the existing e2e structure**:

package/presets/claude/next/rules/tooling-and-review/agent-team-orchestrator.md

@@ -17,12 +17,26 @@ Parent agent = **manager**. Router plans; specialists execute. Artifacts: `.clau
 | Agent | May edit production code | Typical intent |
 |-------|--------------------------|----------------|
 | `task-router` | no | Every `/task` — writes `pipeline.json` |
-| `task-analyst` | no | feature, refactor, test-only |
+| `task-analyst` | no | feature, refactor, test-only, a11y, docs-only, migration |
 | `solution-architect` | no | spike, complex cross-layer feature |
+| `migration-specialist` | no | migration — phased upgrade plan |
+| `api-contract-reviewer` | no | new/changed backend API contracts |
 | `debugger` | yes, minimal fixes only | bugfix |
-| `feature-developer` | yes | feature, bugfix, refactor |
+| `ci-investigator` | yes, minimal CI fixes | ci-fix |
+| `feature-developer` | yes | feature, bugfix, refactor, migration, a11y |
+| `build-verifier` | no | lint/type-check/unit gate after developer |
+| `accessibility-reviewer` | no | a11y, UI-heavy feature |
+| `performance-auditor` | no | perf-audit, perf-sensitive feature |
 | `code-reviewer` | no | most pipelines, review-only |
+| `security-reviewer` | no | auth, forms, sensitive data |
 | `qa-tester` | tests only | feature, bugfix, test-only |
+| `unit-test-planner` | no | unit-only — coverage plan |
+| `unit-test-generator` | tests only | unit-only — spec generation |
+| `unit-test-healer` | tests only | failing/flaky unit tests |
+| `playwright-test-planner` | no | e2e scenario planning |
+| `playwright-test-generator` | tests only | e2e spec generation |
+| `playwright-test-healer` | tests only | failing/flaky e2e fixes |
+| `tech-writer` | docs only | docs-only, feature/migration docs |
 
 Full prompts: `.claude/agents/*.md`. Artifact conventions: `.claude/team/README.md`.
 
@@ -69,18 +83,28 @@ flowchart TD
 | `in_progress` | Current step running |
 | `completed` | Current step done; hook or orchestrator advances |
 | `awaiting_approval` | Human gate; wait for `/task-continue` |
-| `changes_requested` | Reviewer blocked; re-run developer |
+| `changes_requested` | Reviewer blocked; re-run developer (`retryAfterFix`) |
+| `validation_failed` | build-verifier failed; re-run developer then build-verifier |
+
+## Pipeline step options
+
+| Field | Use |
+|-------|-----|
+| `skipIf` | `debugger.fixed` / `ci-investigator.resolved` |
+| `parallel: true` | `agent` array — invoke all in one parent turn |
+| `scope` | e.g. `unit-in-dev`, `e2e-only` |
 
 ## Rules (strict)
 
 1. **`/task` always starts with task-router** (except user says "skip router" with documented pipeline).
 2. Read `pipeline.json` before every subagent invocation.
-3. One role per subagent call.
+3. One role per subagent call — **except** parallel steps.
 4. **Never** skip `humanGates` without `/task-continue` or explicit user approval.
-5. Persist handoffs to disk (`brief.md`, `decomposition.md`, `debug-report.md`, `architecture.md`, `review.md`).
-6. On `changes_requested`: re-invoke `feature-developer`, then `code-reviewer` — do not advance `pipelineIndex` until review passes.
-7. When all steps complete, suggest `/technical-retro <slug>`.
-8. If `autoChain: false` in pipeline, do not rely on hook — manual step only.
+5. Persist handoffs including `validation-report.md`.
+6. On `changes_requested`: hook sets `retryAfterFix` → developer → same reviewer.
+7. On `validation_failed`: hook sets `retryAfterFix: build-verifier` → developer → build-verifier.
+8. When all steps complete, suggest `/technical-retro <slug>`.
+9. If `autoChain: false`, manual step only.
 
 ## Invoking agents
 

package/presets/claude/next/rules/ui-and-accessibility/component-styles.md

@@ -1,3 +1,9 @@
+---
+paths:
+  - app/src/ui/**/*.ts
+  - app/src/ui/**/*.tsx
+---
+
 # Стили только рядом с компонентом
 
 ## Имя корневого styled-элемента: `Root`

package/presets/claude/next/rules/ui-and-accessibility/css-property-order.md

@@ -1,3 +1,9 @@
+---
+paths:
+  - app/src/**/*.{css,ts,tsx}
+  - app/**/*.css
+---
+
 # Порядок CSS-свойств (как в Stylelint)
 
 Действует для **любого** CSS в репозитории: `.css`, стилевые блоки в `styles.ts` / `styles.tsx`, `styled` / Linaria и другой CSS-in-JS в `.ts` / `.tsx`, если этот код попадает под `lint:css`.

package/presets/claude/next/rules/ui-and-accessibility/no-props-spread.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - app/src/**/*.tsx
+---
+
 # Не использовать спред пропов при передаче в компоненты
 
 При вызове **пользовательских** React-компонентов (имя с заглавной буквы) **передавать пропы явно**, а не через spread (`{...props}`, `{...obj}`).

package/presets/claude/next/rules/ui-and-accessibility/react-a11y-coding.md

@@ -0,0 +1,37 @@
+---
+paths:
+  - app/src/ui/**/*.tsx
+  - app/src/ui/**/*.ts
+---
+
+# A11y при разработке UI
+
+Reviewer (`accessibility-reviewer`) проверяет diff; эти правила — **при написании** кода.
+
+## Семантика и ARIA
+
+- Предпочитать **нативные элементы** (`button`, `a`, `label`, `input`) вместо `div` с `onClick`.
+- **`role` / `aria-*`** — только когда нативного аналога нет; не дублировать то, что даёт семантика.
+- Заголовки — иераархия `h1`–`h6` без пропусков уровней ради стилей.
+
+## Формы
+
+- Каждый input связан с **`label`** (`htmlFor` / `id` или обёртка).
+- Сообщения об ошибках — **`aria-describedby`**, `aria-invalid` при validation errors.
+- Кнопки submit vs button — явный `type`.
+
+## Клавиатура и focus
+
+- Все интерактивные элементы **достижимы с Tab** и активируются Enter/Space где ожидается.
+- **Modals/drawers** — focus trap, возврат focus на trigger при закрытии, Esc закрывает (если по UX).
+- Не удалять видимый **focus outline** без замены на доступный custom focus style.
+
+## Контент
+
+- Изображения — **`alt`** (пустой `alt` только для декора).
+- Иконки-кнопки — **`aria-label`** или visually hidden text.
+- Динамические обновления — `aria-live` для критичных status/error (умеренно).
+
+## Проверка
+
+- При сомнении — devtools a11y tree или `accessibility-reviewer` в pipeline для UI-heavy фич.

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

@@ -1,5 +1,15 @@
 # `.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. Добавьте сюда `SKILL.md` или структуру skills по документации инструмента.
+[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.
+
+| Skill | Когда использовать |
+|-------|--------------------|
+| `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 |
+| `ci-investigation` | Diagnosing and fixing failing CI checks on PRs/branches |
+| `unit-testing` | Planning, generating, or healing unit test coverage |
+| `playwright-e2e` | Planning, generating, or healing Playwright e2e coverage |
+| `technical-retro` | Technical retrospective for a task, sprint, incident, or agent pipeline |
 
 Папка копируется в `.claude/skills/` при `ai-rules init claude --preset next`, если существует.

package/presets/claude/next/skills/ci-investigation/SKILL.md

@@ -0,0 +1,36 @@
+---
+name: ci-investigation
+description: Investigates failing CI checks on PRs and branches — lint, type-check, unit, e2e — with local reproduction and minimal fixes. Use when CI is red or for ci-fix pipeline tasks.
+---
+
+# CI Investigation
+
+## Workflow
+
+1. Identify the **first failing check** (lint, type-check, unit, e2e, build).
+2. Capture error output — ignore cascading failures until root cause is found.
+3. Reproduce locally with the same commands CI uses from `app/`:
+   - `lint:js`, `lint:css`, `type-check`
+   - targeted unit test file or suite
+   - affected Playwright spec if e2e failed
+4. Inspect git diff for changed files related to the failure.
+5. Apply **minimal fix** — no unrelated refactors.
+
+## Artifact
+
+Write `ci-report.md` under the task slug folder:
+
+- Failed check name and link/log excerpt
+- Root cause classification
+- Fix applied (or handoff to feature-developer)
+- Validation commands and results
+
+## Handoff Rules
+
+- Config-only or one-line fixes → fix in place, re-run check.
+- Missing tests or architecture work → document and route to `feature-developer` or `qa-tester`.
+- Flaky e2e → prefer `playwright-test-healer` after ci-investigator identifies the spec.
+
+## Validation
+
+Always re-run the failing command locally before marking complete. If environment blocks execution, state the exact command and blocker.

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

@@ -0,0 +1,26 @@
+---
+name: code-review
+description: Reviews pull requests, merge requests, git diffs, and branch changes using the preset's architecture, import, UI, API, and testing standards. Use when the user asks for review or when code-reviewer runs in an agent pipeline.
+---
+
+# Code Review
+
+## Inputs
+
+Use the local repository as the source of truth: `git status`, `git diff`, task artifacts under `.claude/team/tasks/<slug>/` when present, and opened files. Do not invent hosting metadata such as labels, CI status, or reviewers.
+
+## Review Order
+
+1. Understand the intent and affected layers.
+2. Check correctness and regressions first.
+3. Verify architecture boundaries: UI does not know DTO/transport, store does not depend on UI, API services do not pull UI/store.
+4. Check public imports through `@/types` and `@/api`, plus barrel updates for new public symbols.
+5. Review UI consistency, styling conventions, and prop shape.
+6. Check tests: unit for mapper/domain logic, behavior tests for HTTP client changes, e2e plan/spec updates for user flows.
+7. Report validation gaps: lint, stylelint, type-check, or relevant tests not run.
+
+## Output
+
+Lead with findings ordered by severity. Each finding should include the file, the problem, impact, and a concrete fix direction. If there are no findings, say so and call out remaining test or validation risk.
+
+For agent team tasks, write `.claude/team/tasks/<slug>/review.md` and set `status.json` to `completed` or `changes_requested`.

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

@@ -0,0 +1,28 @@
+---
+name: debug-investigation
+description: Investigates bugs, failing tests, crashes, and incorrect behavior with runtime evidence before applying minimal fixes. Use for bugfix tasks, debugger agent runs, regressions, and flaky test diagnosis.
+---
+
+# Debug Investigation
+
+## Process
+
+1. Reproduce the issue or collect the closest available evidence: error output, failing test, browser snapshot, logs, or user steps.
+2. Define expected vs actual behavior in one sentence.
+3. Trace the failing path through the smallest relevant slice of the codebase.
+4. Identify the root cause before editing. Avoid broad refactors during bugfixes.
+5. Apply the smallest fix that preserves existing architecture and public contracts.
+6. Add or update a regression test when the behavior is user-facing or likely to recur.
+7. Run the narrow failing check first, then relevant lint/type/test validation.
+
+## Artifacts
+
+For agent team tasks, write `.claude/team/tasks/<slug>/debug-report.md` with:
+
+- Reproduction steps or evidence source.
+- Root cause.
+- Fix scope.
+- Regression coverage.
+- Remaining risk.
+
+Update `status.json` when complete.

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

@@ -0,0 +1,30 @@
+---
+name: feature-delivery
+description: Delivers Next.js frontend features end-to-end across domain types, API services, store, UI, mocks, tests, and validation. Use when implementing or extending a feature, especially through /task or feature-developer.
+---
+
+# Feature Delivery
+
+## Workflow
+
+1. Read the task brief, acceptance criteria, and decomposition if present.
+2. Read **`architecture/reference-features.md`** and mirror the closest reference feature.
+3. Work in layer order: types -> API -> store -> UI -> **unit tests** -> e2e (if in scope).
+4. Keep DTOs out of UI/store; expose domain types through `@/types` and API calls through `@/api`.
+5. Prefer small, reviewable edits; update barrels when adding public symbols.
+6. Add or update focused tests for changed behavior.
+7. Run project validation from `app/`: `lint:js`, `lint:css`, and `type-check` when TypeScript changed.
+
+## Rule Map
+
+- Core stack and layers: `rules/stack/next-app-core.md`, `rules/architecture/architecture-boundaries.md`.
+- Data/API: `rules/api-and-data/http-client.md`, `rules/api-and-data/api-services.md`, `rules/api-and-data/store-rtk.md`.
+- Public imports: `rules/architecture/types-public-imports.md`, `rules/architecture/api-public-imports.md`, `rules/architecture/layer-barrel-exports.md`.
+- UI: `rules/ui-and-accessibility/react-ui.md`, `react-a11y-coding.md`, `no-props-spread.md`, `component-styles.md`.
+- App Router: `rules/stack/next-app-router.md`.
+- Tests: `rules/testing/tests-unit.md`, `rules/testing/tests-e2e-structure.md`, `rules/testing/playwright-agents.md`.
+- Finish: `rules/tooling-and-review/post-change-lint.md`, `rules/tooling-and-review/package-manager.md`.
+
+## Handoff
+
+Summarize completed work by layer, validation results, and known gaps. If this is part of an agent team task, update `.claude/team/tasks/<slug>/status.json`.

package/presets/claude/next/skills/playwright-e2e/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: playwright-e2e
+description: Plans, generates, and heals Playwright e2e tests using this preset's app/__tests__/e2e layout, *.cases.md plans, page objects, and shared helpers. Use for e2e planning, test generation, or fixing failing browser tests.
+---
+
+# Playwright E2E
+
+## Project Layout
+
+- Test root: `app/__tests__/e2e`.
+- Test plans: `*.cases.md` files under the matching feature folder.
+- Executable specs: `*.spec.ts` files in the same folder.
+- Seed/setup reference: `app/__tests__/e2e/seed.spec.ts`.
+
+Do not introduce top-level `specs/` or `tests/` folders for real coverage unless the user explicitly asks for a sandbox.
+
+## Planner
+
+Create or update the relevant `*.cases.md` file. Each scenario should include title, preconditions, steps, and expected result. Cover happy path, important edge cases, validation, and error states.
+
+## Generator
+
+Generate specs from `*.cases.md` into the same folder. Reuse existing page objects and `_shared/` helpers. Keep test names aligned with scenario names.
+
+## Healer
+
+Fix selectors, waits, setup, or page-object details without weakening business assertions. Use the matching `*.cases.md` file as the behavior contract.
+
+## Validation
+
+Run the affected spec when feasible. If the environment blocks execution, report the command that should be run and the blocker.

package/presets/claude/next/skills/technical-retro/SKILL.md

@@ -0,0 +1,40 @@
+---
+name: technical-retro
+description: Facilitates technical retrospectives for tasks, sprints, incidents, releases, and agent-team pipelines. Use when the user asks for retro, postmortem, process review, or action items after delivery.
+---
+
+# Technical Retro
+
+## Inputs
+
+Ask for missing period, focus, task slug, participants, or format constraints. If a slug is provided, read `.claude/team/tasks/<slug>/` artifacts and local git status/diff. Do not invent facts not present in artifacts or the user's message.
+
+## Facilitation Principles
+
+- Focus on process and system behavior, not blame.
+- Separate facts, interpretations, and proposed actions.
+- Balance what worked with what slowed delivery.
+- Keep action items concrete, owned, and measurable.
+
+## Default Structure
+
+1. Goal and scope.
+2. Timeline or factual observations.
+3. What worked.
+4. What hurt quality, speed, or confidence.
+5. Root causes for the top one or two issues.
+6. Experiments and action items.
+
+## Agent Team Block
+
+For `/task` pipelines, include router, analyst, developer, **build-verifier**, reviewer, QA/e2e, hooks, and rules.
+
+## Preset feedback loop
+
+If the same issue appeared in 2+ tasks, add section **Preset updates**:
+
+- Proposed change to `.claude/rules/`, `.claude/agents/`, or `.claude/skills/`
+- One concrete diff or file path to update
+- Whether it belongs in session-start rules vs `paths:` vs skill
+
+Do not apply preset changes without user approval.

package/presets/claude/next/skills/unit-testing/SKILL.md

@@ -0,0 +1,32 @@
+---
+name: unit-testing
+description: Plans, generates, and heals unit tests for mappers, thunks, HTTP client behavior, and React components using colocated *.spec.ts files and tests-unit rules. Use for unit test planning, generation, or fixing failing unit tests.
+---
+
+# Unit Testing
+
+## Project Layout
+
+- Specs colocated with source: `*.spec.ts` / `*.spec.tsx` next to the module under test.
+- Legacy `*.test.ts` / `*.test.tsx` — do not rename without a separate task.
+- Runner: Jest or Vitest as configured in the target repo; components use `@testing-library/react`.
+
+Follow **`rules/testing/tests-unit.md`**.
+
+## Planner
+
+Write or update `.claude/team/tasks/<slug>/unit-test-plan.md`.
+
+Each scenario needs a Russian `it()` title (capital letter after each sentence). Cover mappers, thunks, client behavior branches, and component interactions per AC.
+
+## Generator
+
+Implement specs from `unit-test-plan.md`. Reuse project test-store, HTTP mocks, and existing test utilities. Do not change production code.
+
+## Healer
+
+Fix mocks, async timing, selectors, and setup — preserve business assertions. Use `unit-test-plan.md` and `brief.md` as the behavior contract.
+
+## Validation
+
+Run affected unit tests from `app/` when feasible. Report command, pass/fail, and remaining gaps vs plan.

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

@@ -4,61 +4,43 @@
 
 ## Layout
 
-```text
+```
 .claude/team/
-  active-task.json          # { "slug": "current-task-slug" }
+  active-task.json
   tasks/
     <slug>/
-      pipeline.json         # dynamic pipeline from task-router
-      brief.md              # Definition of Ready
-      decomposition.md      # Task breakdown
-      architecture.md       # optional architect output
-      debug-report.md       # optional debugger output
-      review.md             # optional code review output
-      status.json           # Phase and state machine
+      pipeline.json
+      status.json
+      brief.md
+      decomposition.md
+      debug-report.md
+      validation-report.md
+      architecture.md
+      migration-plan.md
+      ci-report.md
+      a11y-review.md
+      perf-report.md
+      security-review.md
+      api-contract-review.md
+      unit-test-plan.md
+      documentation.md
+      review.md
 ```
 
-## Slug
-
-- kebab-case, derived from task title
-- max 48 characters
-- example: `order-history-date-filter`
+## pipeline.json schema
 
-## status.json schema
-
-```json
-{
-  "slug": "order-history-date-filter",
-  "intent": "feature",
-  "pipelineIndex": 0,
-  "currentAgent": "task-analyst",
-  "phase": "executing",
-  "state": "in_progress",
-  "awaitingHumanGate": false,
-  "updatedAt": "2026-05-29T12:00:00.000Z"
-}
-```
+Same as Cursor preset — see `agents/task-router.md` for examples with `build-verifier`, `skipIf`, and `parallel` steps.
 
-### state
+## status.json
 
-| Value | Description |
-|-------|-------------|
-| `awaiting_approval` | Brief/design ready; human gate |
-| `approved` | User approved via `/task-continue` or `/feature-continue` |
-| `in_progress` | Active subagent working |
-| `completed` | Current phase/step finished |
-| `changes_requested` | Review found required fixes |
-
-## Git
-
-Commit task artifacts if you want them to survive `ai-rules clean claude`. Alternatively copy finished tasks to `docs/agent-workflow/tasks/<slug>/`.
+Use **`phase: executing`** in pipeline mode. Optional fields: `parallelCompleted`, `retryAfterFix`, `validation_failed` state.
 
 ## Workflow entry
 
 ```bash
-/task <task description>
-# review gate artifacts if requested, then:
+/task <описание>
 /task-continue <slug>
-# after pipeline:
 /technical-retro <slug>
 ```
+
+Legacy: `/feature-start`, `/feature-continue`.

package/presets/cursor/next/AGENTS.md

@@ -0,0 +1,43 @@
+# Next.js stack — Cursor agent team
+
+Краткая точка входа для Cursor. Подробные правила — `.cursor/rules/*.mdc`; сценарии — `.cursor/skills/**`.
+
+See `.cursor/rules/README.md` for the full catalog and loading strategy.
+
+## Quick start
+
+| Задача | Куда смотреть |
+|--------|----------------|
+| Любая новая work-задача | `/task` → `commands/task.md` + `agent-team-orchestrator.mdc` |
+| Новая фича end-to-end | skill `feature-delivery` + `feature-delivery-workflow.mdc` |
+| Стек и слои | `next-app-core.mdc` |
+| Эталонные фичи | `reference-features.mdc` (заполнить пути в репо) |
+| После правок кода | `post-change-lint.mdc` |
+| Code review MR | skill `code-review` + `code-review-mr.mdc` |
+| Валидация перед review | agent `build-verifier` |
+| Техническое ретро | `/technical-retro` + skill `technical-retro` |
+
+## Когда использовать `/task`
+
+- Реализация, багфикс, миграция, тесты, ревью MR, CI-fix — **предпочтительно через `/task`**.
+- Простой one-liner без архитектурного риска — можно без pipeline, если пользователь явно просит.
+- Вопросы «как работает X» — ответ без `/task`.
+
+## Intent → pipeline (кратко)
+
+| intent | Типичный pipeline |
+|--------|-------------------|
+| `feature` | analyst → developer (+ unit) → build-verifier → reviewer → e2e/QA |
+| `bugfix` | debugger → developer (skip if fixed) → build-verifier → reviewer |
+| `ci-fix` | ci-investigator → developer (skip if resolved) → build-verifier |
+| `migration` | analyst → migration-specialist → developer → build-verifier → reviewer → QA |
+
+Полная таблица — `agents/README.md`, router — `agents/task-router.md`.
+
+## Install
+
+```bash
+npx @bonesofspring/ai-rules init cursor --preset next
+```
+
+Копирует rules, commands, agents, hooks, skills, team, `hooks.json`, `BUGBOT.md`, `AGENTS.md`.

package/presets/cursor/next/BUGBOT.md

@@ -0,0 +1,14 @@
+# Cursor Bugbot Review Guidelines
+
+Follow the **`code-review` skill** and **`code-review-mr.mdc`** for the full checklist.
+
+## Priorities
+
+1. Correctness regressions and runtime bugs.
+2. Architecture boundary violations (`architecture-boundaries.mdc`).
+3. Missing unit tests for mapper/domain/store logic; e2e updates for user flows.
+4. Type safety, `@/types` / `@/api` imports, barrel exports.
+
+## Review style
+
+Lead with concrete findings: file, impact, fix direction. Skip style-only nits unless they violate lint rules or project conventions.

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

@@ -2,15 +2,51 @@
 
 Ролевые subagents для командного пайплайна Cursor.
 
+## Planning and routing
+
 | Agent | Файл | Production-код |
 |-------|------|----------------|
 | Router | `task-router.md` | no |
 | Аналитик | `task-analyst.md` | no |
 | Архитектор | `solution-architect.md` | no |
+| Migration planner | `migration-specialist.md` | no |
+| API contract reviewer | `api-contract-reviewer.md` | no |
+
+## Implementation and CI
+
+| Agent | Файл | Production-код |
+|-------|------|----------------|
 | 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 |
+
+## Review specialists
+
+| Agent | Файл | Production-код |
+|-------|------|----------------|
 | Ревьюер | `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 |
+|-------|------|----------------|
 | QA | `qa-tester.md` | tests only |
+| Unit planner | `unit-test-planner.md` | no |
+| Unit generator | `unit-test-generator.md` | tests only |
+| Unit healer | `unit-test-healer.md` | tests only |
+| Playwright planner | `playwright-test-planner.md` | e2e plans only |
+| Playwright generator | `playwright-test-generator.md` | e2e tests only |
+| Playwright healer | `playwright-test-healer.md` | e2e fixes only |
+
+## Documentation
+
+| Agent | Файл | Production-код |
+|-------|------|----------------|
+| Tech writer | `tech-writer.md` | docs only |
 
 Копируется в `.cursor/agents/` при `ai-rules init cursor --preset next`.
 
@@ -23,3 +59,19 @@
 | `/feature-start`, `/feature-continue` | Legacy (совместимость) |
 
 Правило: `agent-team-orchestrator.mdc`. План: `pipeline.json` в `.cursor/team/tasks/<slug>/`.
+
+## Intent → pipeline (кратко)
+
+| intent | Типичный pipeline |
+|--------|-------------------|
+| `feature` | analyst → developer (+ unit) → build-verifier → reviewer → e2e/QA |
+| `bugfix` | debugger → developer (skipIf fixed) → build-verifier → reviewer |
+| `ci-fix` | ci-investigator → developer (skipIf resolved) → build-verifier |
+| `migration` | analyst → migration-specialist → developer → reviewer → QA |
+| `perf-audit` | performance-auditor |
+| `a11y` | analyst → developer → a11y-reviewer → code-reviewer |
+| `unit-only` | unit-planner → unit-generator (или healer) |
+| `e2e-only` | playwright planner → generator (или healer) |
+| `docs-only` | analyst → tech-writer |
+
+Опциональные шаги (router добавляет по контексту): `api-contract-reviewer`, `accessibility-reviewer`, `security-reviewer`, `performance-auditor`, `tech-writer`.