@bonesofspring/ai-rules 0.1.42 → 0.2.1

package/CHANGELOG.md

@@ -0,0 +1,22 @@
+# Changelog
+
+## 0.2.0
+
+### Breaking
+
+- **Import rules merged:** `types-public-imports.mdc` and `api-public-imports.mdc` → **`public-imports.mdc`** (Claude: `architecture/public-imports.md`). Old filenames remain as deprecated stubs for one release cycle.
+- **`feature-delivery-flow.mdc` removed** — content merged into `feature-delivery-workflow.mdc`.
+- **`agent-team-intake`** no longer always-on (Cursor: `alwaysApply: false`; Claude: `paths:` on commands/team). Use orchestrator or `/task`.
+
+### Changed
+
+- Slimmed always-on rules: `next-app-core`, `code-quality-and-refactoring`, `post-change-lint`, `package-manager` (~9 KB baseline vs ~21 KB).
+- Narrowed globs: `css-property-order-stylelint`, `no-type-assertion-as-import-export`, `reference-features`, `public-imports`.
+- `css-property-order` stub — property list delegated to Stylelint `--fix`.
+- Slimmed `task-router` agent; pipeline JSON examples moved to `agents/README.md`.
+- Agents reference skills as SSOT; scoped lint for `feature-developer` when next step is `build-verifier`.
+- Orchestrator: explicit fast-path when to skip pipeline.
+
+## 0.1.42
+
+Prior releases — see git history.

package/CONTRIBUTING.md

@@ -0,0 +1,102 @@
+# Contributing to @bonesofspring/ai-rules
+
+## Layout
+
+```
+packages/ai-rules/
+  bin/cli.js              # init / clean
+  fragments/              # shared source (e.g. BUGBOT.md)
+  presets/
+    cursor/next/          # .mdc rules, agents, commands, …
+    claude/next/          # .md rules with paths:, same semantics
+```
+
+## Manual sync: Cursor ↔ Claude
+
+Пресеты **не генерируются** автоматически. Любое изменение, затрагивающее оба инструмента, требует ручной синхронизации.
+
+### Checklist перед PR / publish
+
+- [ ] **Семантика:** одно и то же правило/агент/skill в обоих пресетах (разный формат, тот же смысл).
+- [ ] **Имена пар** — сверить по таблице ниже.
+- [ ] **Loading:** Cursor `globs` / `alwaysApply` ↔ Claude `paths:` / отсутствие frontmatter (session start).
+- [ ] **Session start:** только 4 базовых правила (см. `rules/README.md` в каждом пресете).
+- [ ] **Orchestrator + code-review** — on-demand, не session start (Claude: `paths:` на commands/team).
+- [ ] **BUGBOT:** правка `fragments/BUGBOT.md` → копия в `presets/cursor/next/BUGBOT.md` и `presets/claude/next/BUGBOT.md` (платформенные ссылки в теле).
+- [ ] **cli.js:** если добавлен root-файл (`hooks.json`, `BUGBOT.md`, …) — обновить `PRESETS.cursor` / `PRESETS.claude` и help text.
+- [ ] **package.json `files`:** новые top-level dirs (`fragments/`) включены в publish.
+- [ ] **CHANGELOG.md:** запись с intent пользователя (token opt, parity, breaking init).
+- [ ] **Version bump** в `package.json` при publish.
+
+### File pair map (preset next)
+
+| Cursor | Claude |
+|--------|--------|
+| `rules/*.mdc` (flat) | `rules/<topic>/*.md` |
+| `architecture-boundaries.mdc` | `architecture/architecture-boundaries.md` |
+| `architecture-boundaries-ui.mdc` | `architecture/architecture-boundaries-ui.md` |
+| `layer-barrel-exports.mdc` | `architecture/layer-barrel-exports.md` |
+| `navigation-router-stack.mdc` | `stack/navigation-router.md` |
+| `navigation-router-ui.mdc` | `stack/navigation-router-ui.md` |
+| `no-cross-component-styles-import.mdc` (stub → react-ui) | удалён; контент в `ui-and-accessibility/react-ui.md` |
+| `react-ui.mdc` | `ui-and-accessibility/react-ui.md` |
+| `code-review-mr.mdc` | `tooling-and-review/code-review-mr.md` |
+| `agent-team-orchestrator.mdc` | `tooling-and-review/agent-team-orchestrator.md` |
+| `AGENTS.md` | `CLAUDE.md` |
+| `agents/*.md` | `agents/*.md` (same names) |
+| `skills/**/SKILL.md` | `skills/**/SKILL.md` |
+| `team/fixtures/*.json` | `team/fixtures/*.json` |
+
+### Loading parity cheatsheet
+
+| Tier | Cursor | Claude |
+|------|--------|--------|
+| Always-on | `alwaysApply: true` | no YAML / no `paths:` |
+| Path-scoped | `globs: …` | `paths: …` |
+| On-demand (no auto) | `alwaysApply: false`, empty globs | `paths:` on commands/team/agents |
+| Procedure | skill | skill |
+
+### UI globs consolidation (P2)
+
+На UI edit не должны грузиться широкие `app/src/**/*` rules. Сверить:
+
+- `architecture-boundaries` → api/store/types/lib only
+- `architecture-boundaries-ui` → `app/src/ui/**`
+- `layer-barrel-exports` → `**/index.ts` only
+- `navigation-router-stack` → `app/src/app/**`
+- `navigation-router-ui` → `app/src/ui/**/*.tsx`
+- Стили колокации — в `react-ui`, не отдельный rule с UI globs
+
+### Validate locally
+
+```bash
+cd packages/ai-rules
+
+# Full static regression (parity, always-on, globs, BUGBOT, fixtures, golden schema)
+yarn validate
+
+# + init smoke (cursor + claude into temp dirs)
+yarn validate:init
+
+# Router golden prompts — schema + agent refs
+yarn validate:golden
+
+# Manual router regression checklist
+./scripts/validate-preset.sh --print-golden
+# → run /task per row, save pipeline.json to scripts/regression-results/<id>.json
+./scripts/validate-preset.sh --check-golden --compare-pipeline scripts/regression-results/
+```
+
+See **`scripts/README.md`** for golden-prompts workflow.
+
+Legacy one-liners (covered by `validate-preset.sh`):
+
+```bash
+node --check packages/ai-rules/bin/cli.js
+```
+
+### Do not sync blindly
+
+- Cursor `.mdc` frontmatter ≠ Claude YAML 1:1 (разные поля).
+- Стили компонентов — только в `react-ui` / `react-ui.mdc`; не создавать отдельный rule без узких globs/paths.
+- Playwright agents: не копировать vendor boilerplate в Claude — использовать cursor-aligned slim prompts.

package/README.md

@@ -4,6 +4,8 @@ Presets for Cursor and Claude Code: rules, commands, plus optional `agents`, `ho
 
 Node 18+.
 
+Contributing and Cursor↔Claude sync checklist: **[CONTRIBUTING.md](./CONTRIBUTING.md)**.
+
 ```bash
 # from the project root
 npx @bonesofspring/ai-rules init cursor --preset next

package/bin/cli.js

@@ -25,6 +25,8 @@ const PRESETS = {
     relBase: ['presets', 'claude'],
     optionalClaudeDirs: ['skills', 'agents', 'hooks', 'team'],
     claudeMdSrc: 'CLAUDE.md',
+    hooksJsonSrc: 'hooks.json',
+    toolRootFiles: ['BUGBOT.md'],
   },
 };
 
@@ -51,7 +53,7 @@ Options:
 Notes:
   init merges into the target directory; same-named files are overwritten.
   Cursor init copies rules, commands, agents, hooks, skills, team, hooks.json, BUGBOT.md, AGENTS.md.
-  Claude init copies rules, commands, skills, agents, hooks, team, and CLAUDE.md when present.
+  Claude init copies rules, commands, skills, agents, hooks, team, hooks.json, BUGBOT.md, and CLAUDE.md when present.
   Command forms: "init cursor --preset next", "init cursor next", "--preset next init cursor", "cursor init --preset next".
 
 Examples:
@@ -344,7 +346,7 @@ function cmdInit(tool, preset, cwdOption) {
       }
     }
 
-    if (tool === 'cursor' && cfg.hooksJsonSrc) {
+    if (cfg.hooksJsonSrc) {
       const hooksFrom = path.join(base, cfg.hooksJsonSrc);
       if (fs.existsSync(hooksFrom)) {
         fs.copyFileSync(hooksFrom, path.join(toolRootAbs, 'hooks.json'));

package/fragments/BUGBOT.md

@@ -0,0 +1,23 @@
+# Bugbot / Automated Review Guidelines
+
+Follow the **`code-review` skill** and the on-demand **code-review rule** for the full checklist.
+
+## Priorities
+
+1. Correctness regressions and runtime bugs.
+2. Architecture boundary violations.
+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.
+
+## Platform rules (on-demand)
+
+| Platform | Code review rule | Architecture |
+|----------|------------------|--------------|
+| Cursor | `code-review-mr.mdc` | `architecture-boundaries.mdc` |
+| Claude | `rules/tooling-and-review/code-review-mr.md` | `rules/architecture/architecture-boundaries.md` |
+
+**Sync:** edit this file in `packages/ai-rules/fragments/`, then copy to both presets before publish.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@bonesofspring/ai-rules",
-  "version": "0.1.42",
+  "version": "0.2.1",
   "description": "Presets of Cursor and Claude rules/commands for Revy Ross personal use",
   "license": "MIT",
   "author": "Revy Ross",
@@ -18,11 +18,19 @@
   "bin": {
     "ai-rules": "bin/cli.js"
   },
+  "scripts": {
+    "validate": "bash scripts/validate-preset.sh",
+    "validate:init": "bash scripts/validate-preset.sh --init-smoke",
+    "validate:golden": "bash scripts/validate-preset.sh --check-golden"
+  },
   "files": [
     "README.md",
     "CHANGELOG.md",
+    "CONTRIBUTING.md",
     "bin",
-    "presets"
+    "fragments",
+    "presets",
+    "scripts"
   ],
   "engines": {
     "node": ">=18"

package/presets/claude/next/BUGBOT.md

@@ -0,0 +1,16 @@
+# Claude Bugbot Review Guidelines
+
+Follow the **`code-review` skill** and **`rules/tooling-and-review/code-review-mr.md`** for the full checklist.
+
+## Priorities
+
+1. Correctness regressions and runtime bugs.
+2. Architecture boundary violations (`rules/architecture/architecture-boundaries.md`).
+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.
+
+**Source of truth:** `packages/ai-rules/fragments/BUGBOT.md` — sync manually when updating.

package/presets/claude/next/CLAUDE.md

@@ -7,7 +7,7 @@ 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** — только базовые инварианты (`next-app-core`, lint, package manager, intake, code-quality).
+- **Session-start rules** — только базовые инварианты (`next-app-core`, lint, package manager, code-quality).
 - **Domain-specific rules** — YAML frontmatter `paths:` (подгружаются при работе с matching-файлами).
 - Slash-команды — в `commands/`; сценарии — в `skills/`; subagents — в `agents/`.
 
@@ -32,4 +32,8 @@ See @rules/README.md for the full catalog and loading strategy.
 npx @bonesofspring/ai-rules init claude --preset next
 ```
 
-Копирует `CLAUDE.md`, `rules/**`, `commands/**`, `agents/**`, `hooks/**`, `team/**` и др. в `.claude/` целевого репозитория.
+Копирует `CLAUDE.md`, `rules/**`, `commands/**`, `agents/**`, `hooks/**`, `team/**`, `hooks.json`, `BUGBOT.md` и др. в `.claude/` целевого репозитория.
+
+## Pipeline routing
+
+Intent detection, profiles (`full` / `standard` / `light`), and default steps — **only** in `agents/task-router.md`. Schema and examples — `agents/README.md`.

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

@@ -52,18 +52,80 @@
 
 Оркестрация: `/task`, `/task-continue`, `rules/tooling-and-review/agent-team-orchestrator.md`, артефакты `.claude/team/**`.
 
-## Intent → pipeline (кратко)
-
-| intent | Типичный pipeline |
-|--------|-------------------|
-| `feature` | analyst → developer → reviewer → QA |
-| `bugfix` | debugger → developer → reviewer → QA |
-| `ci-fix` | ci-investigator → developer → reviewer |
-| `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`.
+## Pipeline routing
+
+**Source of truth:** intent table, profiles (`full` / `standard` / `light`), and default steps — **`task-router.md`** only. Do not duplicate intent→pipeline tables in entry docs.
+
+## pipeline.json reference
+
+### Top-level fields
+
+| Field | Required | Description |
+|-------|----------|-------------|
+| `slug` | yes | Task identifier |
+| `intent` | yes | From router intent detection |
+| `profile` | no | `full` \| `standard` \| `light` — see `task-router.md` § Pipeline profiles |
+| `summary` | yes | One-line task summary |
+| `steps` | yes | Ordered agent steps |
+| `humanGates` | no | e.g. `["after:task-analyst"]` |
+| `autoChain` | no | Default `true` |
+| `skipped` | no | Roles skipped with reason |
+
+### Step fields
+
+| Field | Required | Description |
+|-------|----------|-------------|
+| `agent` | yes | Subagent name (kebab-case) or array for `parallel: true` |
+| `label` | yes | Short human-readable step name |
+| `scope` | no | e.g. `unit-in-dev`, `e2e-only`, `regression`, `full` |
+| `skipIf` | no | `debugger.fixed` \| `ci-investigator.resolved` |
+| `parallel` | no | When `true` and `agent` is array — invoke all in one turn |
+
+### Minimal template
+
+```json
+{
+  "slug": "<slug>",
+  "intent": "feature",
+  "summary": "One-line task summary",
+  "steps": [
+    { "agent": "task-analyst", "label": "Clarify and decompose" },
+    { "agent": "feature-developer", "label": "Implement + unit tests", "scope": "unit-in-dev" },
+    { "agent": "build-verifier", "label": "Lint, type-check, unit smoke" },
+    { "agent": "code-reviewer", "label": "Code review" }
+  ],
+  "humanGates": ["after:task-analyst"],
+  "autoChain": true,
+  "skipped": []
+}
+```
+
+### Example: bugfix skipIf
+
+```json
+{
+  "intent": "bugfix",
+  "steps": [
+    { "agent": "debugger", "label": "Root cause" },
+    { "agent": "feature-developer", "label": "Fix if needed", "skipIf": "debugger.fixed" },
+    { "agent": "build-verifier", "label": "Validation" },
+    { "agent": "code-reviewer", "label": "Review" }
+  ],
+  "humanGates": []
+}
+```
+
+### Initial status.json
+
+```json
+{
+  "slug": "<slug>",
+  "intent": "<intent>",
+  "pipelineIndex": 0,
+  "currentAgent": "<steps[0].agent>",
+  "phase": "executing",
+  "state": "in_progress",
+  "awaitingHumanGate": false,
+  "updatedAt": "<ISO8601>"
+}
+```

package/presets/claude/next/agents/api-contract-reviewer.md

@@ -12,7 +12,7 @@ You are an API contract reviewer for a layered Next.js frontend (`@/types`, `@/a
 2. OpenAPI/Swagger spec, ticket API description, or backend contract docs from the user.
 3. Changed files in `app/src/types/**`, `app/src/api/**`, mocks, store thunks.
 
-Apply **`rules/architecture/types-public-imports.md`**, **`rules/architecture/api-public-imports.md`**, **`rules/api-and-data/api-services.md`**, **`rules/api-and-data/http-client.md`**.
+Apply **`rules/architecture/public-imports.md`**, **`rules/api-and-data/api-services.md`**, **`rules/api-and-data/http-client.md`**.
 
 ## Review scope
 

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

@@ -6,6 +6,8 @@ model: fast
 
 You are a build verification specialist. You **validate** implementation quality before code review — you do not edit production code or tests.
 
+**SSOT for full validation in pipeline:** run complete **`lint:js`**, **`lint:css`**, and **`type-check`** from `app/` even if feature-developer ran scoped checks.
+
 ## Inputs
 
 1. `.claude/team/tasks/<slug>/brief.md` and `decomposition.md`.

package/presets/claude/next/agents/code-reviewer.md

@@ -1,7 +1,7 @@
 ---
 name: code-reviewer
 description: Expert code review specialist. Reviews after feature development using code-review-mr checklist. Use proactively after feature-developer completes or when the user asks for MR/diff review on a team task slug. Writes only review artifacts/status; never edits production code.
-model: inherit
+model: fast
 ---
 
 You are a senior code reviewer. You may write only review artifacts under `.claude/team/**` and update task `status.json`; do not modify production code.

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

@@ -8,33 +8,20 @@ You are a senior frontend developer working in a Next.js monorepo with strict la
 
 ## Before coding
 
-1. Read `.claude/team/tasks/<slug>/brief.md` and `decomposition.md`.
-2. Read `architecture.md`, `migration-plan.md`, `api-contract-review.md`, `debug-report.md`, `validation-report.md`, and `review.md` if present.
-3. Read `status.json` — proceed if `state` is `in_progress`, `approved`, or continuing after fix loop (`retryAfterFix`).
-4. Read **`architecture/reference-features.md`** and mirror the closest reference feature structure.
-5. Use the **`feature-delivery` skill** and **`rules/architecture/feature-delivery-workflow.md`**.
+1. Read `.claude/team/tasks/<slug>/brief.md`, `decomposition.md`, and prior artifacts if present.
+2. Read `status.json` — proceed if `in_progress`, `approved`, or `retryAfterFix`.
+3. Read `pipeline.json` for step context and scope.
+4. Follow the **`feature-delivery` skill** (layer order, reference features, validation handoff).
 
 ## Task execution rules
 
 - Work tasks in dependency order (types → api → mocks → store → ui → **unit** → e2e).
-- **Unit tests are mandatory before handoff** for mappers, store logic, and non-trivial pure functions (`rules/testing/tests-unit.md`).
-- Mark completed tasks in `decomposition.md` with `[x]` or update **Done** column.
-- After code changes run **`rules/tooling-and-review/post-change-lint.md`**: `lint:js`, `lint:css`, `type-check` from `app/`.
+- **Unit tests mandatory 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/type-check on **changed files** is enough; full project lint is build-verifier's job.
 
 ## On completion
 
-Update `status.json`:
-
-```json
-{
-  "slug": "<slug>",
-  "currentAgent": "feature-developer",
-  "phase": "executing",
-  "state": "completed",
-  "updatedAt": "<ISO8601>"
-}
-```
-
-Handoff summary: tasks done, files by layer, unit specs added, lint/type-check result, known gaps.
+Update `status.json` (`currentAgent`: `feature-developer`, `state`: `completed`). Handoff: tasks done, files by layer, unit specs, validation result, gaps for build-verifier/reviewer.
 
 Do not perform formal code review — that is the code-reviewer subagent's job.

package/presets/claude/next/agents/playwright-test-generator.md

@@ -1,75 +1,26 @@
 ---
 name: playwright-test-generator
-description: 'Use this agent when you need to create automated browser tests using Playwright Examples: <example>Context: User wants to generate a test for the test plan item. <test-suite><!-- Verbatim name of the test spec group w/o ordinal like "Multiplication tests" --></test-suite> <test-name><!-- Name of the test case without the ordinal like "should add two numbers" --></test-name> <test-file><!-- Name of the file to save the test into, like tests/multiplication/should-add-two-numbers.spec.ts --></test-file> <seed-file><!-- Seed file path from test plan --></seed-file> <body><!-- Test case content including steps and expectations --></body></example>'
-tools: Glob, Grep, Read, LS, mcp__playwright-test__browser_click, mcp__playwright-test__browser_drag, mcp__playwright-test__browser_evaluate, mcp__playwright-test__browser_file_upload, mcp__playwright-test__browser_handle_dialog, mcp__playwright-test__browser_hover, mcp__playwright-test__browser_navigate, mcp__playwright-test__browser_press_key, mcp__playwright-test__browser_select_option, mcp__playwright-test__browser_snapshot, mcp__playwright-test__browser_type, mcp__playwright-test__browser_verify_element_visible, mcp__playwright-test__browser_verify_list_visible, mcp__playwright-test__browser_verify_text_visible, mcp__playwright-test__browser_verify_value, mcp__playwright-test__browser_wait_for, mcp__playwright-test__generator_read_log, mcp__playwright-test__generator_setup_page, mcp__playwright-test__generator_write_test
-model: sonnet
-color: blue
+description: Playwright e2e generation specialist. Use when converting existing *.cases.md scenarios into executable *.spec.ts tests under app/__tests__/e2e.
+model: inherit
 ---
 
-You are a Playwright Test Generator, an expert in browser automation and end-to-end testing.
-Your specialty is creating robust, reliable Playwright tests that accurately simulate user interactions and validate
-application behavior.
+You generate Playwright tests from project test plans.
 
-## Project-specific test structure (Next.js preset)
+## Inputs
 
-In this project you MUST respect the existing e2e layout:
+- The relevant `app/__tests__/e2e/**/*.cases.md` file.
+- Existing specs, page objects, and `_shared/` helpers in the same e2e area.
+- Task artifacts under `.claude/team/tasks/<slug>/` when present.
 
-- Test root: `app/__tests__/e2e`
-- Test plans/specs: `*.cases.md` files under `app/__tests__/e2e/**`
-- Executable tests: `*.spec.ts` files under `app/__tests__/e2e/**`
-- Seed test: `app/__tests__/e2e/seed.spec.ts`
+## Rules
 
-When you generate tests:
+1. Follow **`testing/playwright-agents.md`**, **`testing/tests-e2e-structure.md`**, and the **`playwright-e2e` skill**.
+2. Write specs under `app/__tests__/e2e/**`, next to the plan.
+3. Match `test.describe` and `test(...)` names to the plan sections and scenario names.
+4. Prefer existing page objects and helpers over direct selector-heavy tests.
+5. **Use `user-playwright` MCP** when available (`browser_navigate`, `browser_snapshot`, generator tools) to verify selectors before finalizing specs.
+6. Do not weaken or skip assertions from the plan without documenting a blocker.
 
-- Use the corresponding `*.cases.md` file under `app/__tests__/e2e/**` as the source plan (for example,
-  `app/__tests__/e2e/OrderHistory/order-history.cases.md`).
-- Write or update Playwright test files only under `app/__tests__/e2e/**` (for example,
-  `app/__tests__/e2e/OrderHistory/order-history.spec.ts`) instead of creating files in a separate `tests/` folder.
+## Completion
 
-# For each test you generate
-- Obtain the test plan with all the steps and verification specification
-- Run the `generator_setup_page` tool to set up page for the scenario
-- For each step and verification in the scenario, do the following:
-  - Use Playwright tool to manually execute it in real-time.
-  - Use the step description as the intent for each Playwright tool call.
-- Retrieve generator log via `generator_read_log`
-- Immediately after reading the test log, invoke `generator_write_test` with the generated source code
-  - File should contain single test
-  - File name must be fs-friendly scenario name
-  - Test must be placed in a describe matching the top-level test plan item
-  - Test title must match the scenario name
-  - Includes a comment with the step text before each step execution. Do not duplicate comments if step requires
-    multiple actions.
-  - Always use best practices from the log when generating tests.
-
-   <example-generation>
-   For following plan:
-
-   ```markdown file=specs/plan.md
-   ### 1. Adding New Todos
-   **Seed:** `tests/seed.spec.ts`
-
-   #### 1.1 Add Valid Todo
-   **Steps:**
-   1. Click in the "What needs to be done?" input field
-
-   #### 1.2 Add Multiple Todos
-   ...
-   ```
-
-   Following file is generated:
-
-   ```ts file=add-valid-todo.spec.ts
-   // spec: specs/plan.md
-   // seed: tests/seed.spec.ts
-
-   test.describe('Adding New Todos', () => {
-     test('Add Valid Todo', async { page } => {
-       // 1. Click in the "What needs to be done?" input field
-       await page.click(...);
-
-       ...
-     });
-   });
-   ```
-   </example-generation>
+Run the affected spec if feasible. Report files changed, tests run, failures, and gaps. For agent team tasks, update `.claude/team/tasks/<slug>/status.json`.

package/presets/claude/next/agents/playwright-test-healer.md

@@ -1,61 +1,26 @@
 ---
 name: playwright-test-healer
-description: Use this agent when you need to debug and fix failing Playwright tests
-tools: Glob, Grep, Read, LS, Edit, MultiEdit, Write, mcp__playwright-test__browser_console_messages, mcp__playwright-test__browser_evaluate, mcp__playwright-test__browser_generate_locator, mcp__playwright-test__browser_network_requests, mcp__playwright-test__browser_snapshot, mcp__playwright-test__test_debug, mcp__playwright-test__test_list, mcp__playwright-test__test_run
-model: sonnet
-color: red
+description: Playwright e2e healer. Use when browser tests fail, become flaky, or need locator/setup fixes while preserving business assertions.
+model: inherit
 ---
 
-You are the Playwright Test Healer, an expert test automation engineer specializing in debugging and
-resolving Playwright test failures. Your mission is to systematically identify, diagnose, and fix
-broken Playwright tests using a methodical approach.
+You debug and fix failing Playwright e2e tests.
 
-## Project-specific test structure (Next.js preset)
+## Inputs
 
-In this project you MUST respect the existing e2e layout:
+- Failing test output and command.
+- Matching `*.spec.ts` and `*.cases.md` files under `app/__tests__/e2e/**`.
+- Existing page objects and `_shared/` helpers.
 
-- Test root: `app/__tests__/e2e`
-- Test plans/specs: `*.cases.md` files under `app/__tests__/e2e/**`
-- Executable tests: `*.spec.ts` files under `app/__tests__/e2e/**`
-- Seed test: `app/__tests__/e2e/seed.spec.ts`
+## Rules
 
-When healing tests:
+1. Follow **`testing/playwright-agents.md`**, **`testing/tests-e2e-structure.md`**, and the **`debug-investigation`** and **`playwright-e2e`** skills.
+2. Treat `*.cases.md` as the behavior contract.
+3. Fix locators, waits, setup, mocks, or page-object flows without weakening business assertions.
+4. **Use `user-playwright` MCP** when available to reproduce failures and verify fixes.
+5. Prefer targeted fixes in the affected spec/page object over broad test infrastructure changes.
+6. Re-run the affected spec when feasible.
 
-- Only read and modify `*.spec.ts` files under `app/__tests__/e2e/**`.
-- Use the `*.cases.md` file in the same folder as the failing test as the source of truth for intended behavior
-  (for example, `app/__tests__/e2e/OrderHistory/order-history.cases.md` for
-  `app/__tests__/e2e/OrderHistory/order-history.spec.ts`).
+## Completion
 
-Your workflow:
-1. **Initial Execution**: Run all tests using `test_run` tool to identify failing tests
-2. **Debug failed tests**: For each failing test run `test_debug`.
-3. **Error Investigation**: When the test pauses on errors, use available Playwright MCP tools to:
-   - Examine the error details
-   - Capture page snapshot to understand the context
-   - Analyze selectors, timing issues, or assertion failures
-4. **Root Cause Analysis**: Determine the underlying cause of the failure by examining:
-   - Element selectors that may have changed
-   - Timing and synchronization issues
-   - Data dependencies or test environment problems
-   - Application changes that broke test assumptions
-5. **Code Remediation**: Edit the test code to address identified issues, focusing on:
-   - Updating selectors to match current application state
-   - Fixing assertions and expected values
-   - Improving test reliability and maintainability
-   - For inherently dynamic data, utilize regular expressions to produce resilient locators
-6. **Verification**: Restart the test after each fix to validate the changes
-7. **Iteration**: Repeat the investigation and fixing process until the test passes cleanly
-
-Key principles:
-- Be systematic and thorough in your debugging approach
-- Document your findings and reasoning for each fix
-- Prefer robust, maintainable solutions over quick hacks
-- Use Playwright best practices for reliable test automation
-- If multiple errors exist, fix them one at a time and retest
-- Provide clear explanations of what was broken and how you fixed it
-- You will continue this process until the test runs successfully without any failures or errors.
-- If the error persists and you have high level of confidence that the test is correct, mark this test as test.fixme()
-  so that it is skipped during the execution. Add a comment before the failing step explaining what is happening instead
-  of the expected behavior.
-- Do not ask user questions, you are not interactive tool, do the most reasonable thing possible to pass the test.
-- Never wait for networkidle or use other discouraged or deprecated apis
+Report root cause, files changed, validation result, and remaining flakiness risk. For agent team tasks, update `.claude/team/tasks/<slug>/status.json`.