@bonesofspring/ai-rules 0.2.3 → 0.2.5

package/presets/claude/next/mcp.json

@@ -0,0 +1,20 @@
+{
+  "mcpServers": {
+    "context7": {
+      "command": "npx",
+      "args": ["-y", "@upstash/context7-mcp"]
+    },
+    "playwright-test": {
+      "command": "npx",
+      "args": ["-y", "@playwright/mcp@latest"]
+    },
+    "chrome-devtools": {
+      "command": "npx",
+      "args": ["-y", "chrome-devtools-mcp@latest"]
+    },
+    "figma": {
+      "type": "http",
+      "url": "https://mcp.figma.com/mcp"
+    }
+  }
+}

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

@@ -102,6 +102,7 @@ flowchart TD
 | `skipIf` | `debugger.fixed` / `ci-investigator.resolved` |
 | `parallel: true` | `agent` array — invoke all in one parent turn |
 | `scope` | e.g. `unit-in-dev`, `e2e-only` |
+| `model` | `cheap` \| `standard` \| `strong` — optional tier override |
 
 ## Rules (strict)
 
@@ -109,15 +110,28 @@ flowchart TD
 2. Read `pipeline.json` before every subagent invocation.
 3. One role per subagent call — **except** parallel steps.
 4. **Never** skip `humanGates` without `/task-continue` or explicit user approval.
-5. Persist handoffs including `validation-report.md`.
+5. Persist handoffs including `validation-report.md` (write files; do not rely on Shell `mkdir` alone).
 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.
 
+## Team artifact I/O
+
+Create `.claude/team/tasks/<slug>/**` by writing files (Write/Edit). Avoid Shell-only `mkdir` as the bootstrap step.
+
 ## Invoking agents
 
-Use the available Claude Code subagent mechanism. Pass: slug, artifact paths, step `scope` if set.
+Use the available Claude Code subagent / Agent tool. Pass: slug, artifact paths, step `scope` if set.
+
+### Model when invoking
+
+1. Read `steps[i].model` if present; else use the agent’s frontmatter `model` (see `agents/README.md` matrix).
+2. Map abstract tiers for the Agent tool `model` param:
+   - **`cheap`** → `haiku` (or rely on frontmatter `fast`).
+   - **`standard`** → omit / `sonnet` / inherit.
+   - **`strong`** → `opus` (matches strong-agent frontmatter). Prefer explicit per-invocation `model` when frontmatter pins are flaky.
+3. Parallel steps: apply the step-level `model` to each agent (or omit → each frontmatter).
 
 After each agent completes, ensure `status.json` has `state: completed` (or `awaiting_approval` if gate applies).
 

package/presets/claude/next/team/fixtures/feature-full.json

@@ -5,9 +5,11 @@
   "summary": "Multi-layer feature with e2e coverage",
   "steps": [
     { "agent": "task-analyst", "label": "Clarify and decompose" },
+    { "agent": "solution-architect", "label": "Design boundaries", "model": "strong" },
     { "agent": "feature-developer", "label": "Implement + unit tests", "scope": "unit-in-dev" },
-    { "agent": "build-verifier", "label": "Validation gate" },
-    { "agent": "code-reviewer", "label": "Code review" },
+    { "agent": "build-verifier", "label": "Validation gate", "model": "cheap" },
+    { "agent": "security-reviewer", "label": "Security review", "model": "strong" },
+    { "agent": "code-reviewer", "label": "Code review", "model": "cheap" },
     { "agent": "qa-tester", "label": "E2E", "scope": "e2e-only" }
   ],
   "humanGates": ["after:task-analyst"],

package/presets/claude/next/team/fixtures/feature-light.json

@@ -4,8 +4,8 @@
   "profile": "light",
   "summary": "Trivial single-file change with explicit AC",
   "steps": [
-    { "agent": "feature-developer", "label": "Implement" },
-    { "agent": "build-verifier", "label": "Validation gate" }
+    { "agent": "feature-developer", "label": "Implement", "model": "cheap" },
+    { "agent": "build-verifier", "label": "Validation gate", "model": "cheap" }
   ],
   "humanGates": [],
   "autoChain": true,

package/presets/cursor/ios-swift/AGENTS.md

@@ -44,4 +44,4 @@ Intent detection, profiles (`full` / `standard` / `light`), and default steps
 npx @bonesofspring/ai-rules init cursor --preset ios-swift
 ```
 
-Копирует rules, commands, agents, hooks, skills, team, `hooks.json`, `BUGBOT.md`, `AGENTS.md`.
+Копирует rules, commands, agents, hooks, skills, team, `hooks.json`, `BUGBOT.md`, `AGENTS.md`, `MCP.md`, `mcp.json` → `.cursor/mcp.json`.

package/presets/cursor/ios-swift/MCP.md

@@ -0,0 +1,16 @@
+# MCP (preset `ios-swift`, Cursor)
+
+Копируется в `.cursor/mcp.json` при `ai-rules init cursor --preset ios-swift`.
+
+## Servers
+
+| Name | Package | Зачем |
+|------|---------|--------|
+| `context7` | `@upstash/context7-mcp` | Актуальная документация Swift / SwiftUI / Apple frameworks |
+| `figma` | remote `https://mcp.figma.com/mcp` | Design context → SwiftUI; OAuth в Cursor |
+
+Playwright / Chrome DevTools **не** входят в ios-пресет (browser e2e запрещены agent team).
+
+Секреты в файл не кладём. Опционально: `CONTEXT7_API_KEY` в окружении. Figma — OAuth (токен не коммитим).
+
+После init: Settings → MCP → включить серверы. `init` перезаписывает одноимённый `mcp.json`.

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

@@ -20,6 +20,7 @@ npx @bonesofspring/ai-rules init cursor --preset ios-swift
 | `commands/**` | task, task-continue, feature-start/continue, technical-retro |
 | `hooks.json` + `hooks/**` | guard-shell + chain-team-phases |
 | `team/**` | fixtures + README |
+| `mcp.json` + `MCP.md` | Context7 + Figma MCP → `.cursor/mcp.json` |
 
 ## alwaysApply (≤3)
 

package/presets/cursor/ios-swift/agents/README.md

@@ -29,6 +29,18 @@ When copying next pipeline templates: put Playwright stems in `skipped` with rea
 
 Все agents — **`readonly: false`** (нужна запись в `.cursor/team/**`). Ограничения production — в теле промпта.
 
+## Model matrix (frontmatter `model`)
+
+Same tiers as **cursor/next** (see that README for full notes). Defaults in this preset:
+
+| Tier | Frontmatter | Agents |
+|------|-------------|--------|
+| **cheap** | `fast` | router, analyst, build-verifier, code-reviewer, tech-writer |
+| **standard** | `inherit` | developer, debugger, ci-investigator, api-contract, a11y, qa, unit-*, xcuitest-* |
+| **strong** | `claude-opus-4-8[effort=high]` | solution-architect, migration-specialist, security-reviewer, performance-auditor |
+
+Optional `steps[].model`: `cheap` \| `standard` \| `strong` (router/orchestrator policy — same as next).
+
 ## Pipeline routing
 
 **SoT:** intent table / profiles — **`task-router.md`**. Schema — ниже (same as next).
@@ -43,8 +55,8 @@ When copying next pipeline templates: put Playwright stems in `skipped` with rea
   "steps": [
     { "agent": "task-analyst", "label": "Clarify and decompose" },
     { "agent": "feature-developer", "label": "Implement + unit tests", "scope": "unit-in-dev" },
-    { "agent": "build-verifier", "label": "xcodebuild + lint + unit smoke" },
-    { "agent": "code-reviewer", "label": "Code review" }
+    { "agent": "build-verifier", "label": "xcodebuild + lint + unit smoke", "model": "cheap" },
+    { "agent": "code-reviewer", "label": "Code review", "model": "cheap" }
   ],
   "humanGates": ["after:task-analyst"],
   "autoChain": true,
@@ -52,4 +64,6 @@ When copying next pipeline templates: put Playwright stems in `skipped` with rea
 }
 ```
 
+`steps[].model` optional: `cheap` \| `standard` \| `strong`.
+
 Копируется в `.cursor/agents/` при `ai-rules init cursor --preset ios-swift`.

package/presets/cursor/ios-swift/agents/migration-specialist.md

@@ -2,7 +2,7 @@
 name: migration-specialist
 description: Migration planning specialist for Xcode/iOS/SPM upgrades, dependency swaps, and phased refactors with rollback. Writes migration-plan.md and team status; never writes production code.
 readonly: false
-model: inherit
+model: claude-opus-4-8[effort=high]
 ---
 
 You are a migration specialist for an **iOS Swift** codebase with Feature-module layer boundaries.

package/presets/cursor/ios-swift/agents/performance-auditor.md

@@ -2,7 +2,7 @@
 name: performance-auditor
 description: Performance audit specialist. Reviews launch path, main-thread work, SwiftUI body churn, list scrolling, image decoding, and Instruments-oriented risks. Readonly — writes perf-report.md only; never edits production code.
 readonly: false
-model: inherit
+model: claude-opus-4-8[effort=high]
 ---
 
 You are an iOS performance auditor for a Swift/SwiftUI application.

package/presets/cursor/ios-swift/agents/security-reviewer.md

@@ -2,7 +2,7 @@
 name: security-reviewer
 description: Security review specialist. Audits Keychain/token handling, ATS, PII in logs, secrets in diff, and unsafe URL/deep-link handling. Readonly — writes security-review.md only; never edits production code.
 readonly: false
-model: inherit
+model: claude-opus-4-8[effort=high]
 ---
 
 You are an iOS security reviewer for a Swift/SwiftUI application.

package/presets/cursor/ios-swift/agents/solution-architect.md

@@ -2,7 +2,7 @@
 name: solution-architect
 description: Solution architect for cross-layer features, API boundaries, and technical design before implementation. Use for spike intent or when router adds architect step for complex features. Readonly — produces design docs, not production code.
 readonly: false
-model: inherit
+model: claude-opus-4-8[effort=high]
 ---
 
 You are a solution architect for **iOS Feature modules** (Presentation / Domain / Data). Write `architecture.md` under `.cursor/team/tasks/<slug>/`. No production code.

package/presets/cursor/ios-swift/agents/task-router.md

@@ -40,6 +40,15 @@ You are a task router for an **iOS Swift/SwiftUI** agent team. You **do not** im
 
 **Never skip `build-verifier`** after developer when Swift/Xcode sources changed.
 
+## Model tiers (`steps[].model`)
+
+Optional: `"model": "cheap" | "standard" | "strong"`. Same policy as **cursor/next** `task-router.md`:
+
+- `light` → `cheap` on all steps (debugger unclear root cause → `strong`)
+- `full` / `spike` / security|perf specialists → `strong` on architect, migration, security, perf steps
+- never `strong` on build-verifier / tech-writer / task-router
+- omit on `standard` → agent frontmatter (`fast` / `inherit` / `claude-opus-4-8[effort=high]`)
+
 Fixtures: `.cursor/team/fixtures/` (feature-full, feature-light, bugfix-standard).
 
 ## humanGates (defaults)
@@ -55,7 +64,7 @@ Fixtures: `.cursor/team/fixtures/` (feature-full, feature-light, bugfix-standard
 
 ## Output
 
-Write `.cursor/team/tasks/<slug>/pipeline.json` and initial `status.json`; set `.cursor/team/active-task.json`.
+Write `.cursor/team/tasks/<slug>/pipeline.json` and initial `status.json` via the **Write** tool (creates parents; do not Shell-`mkdir`); set `.cursor/team/active-task.json`.
 
 ## Handoff
 

package/presets/cursor/ios-swift/commands/feature-start.md

@@ -13,7 +13,7 @@ description: Legacy analyst-only feature intake. Prefer /task for new work becau
 
 1. Извлеки описание задачи из аргументов команды (всё после `/feature-start`).
 2. Сгенерируй **slug** (kebab-case, до 48 символов) из заголовка задачи.
-3. Создай каталог `.cursor/team/tasks/<slug>/` если его ещё нет.
+3. Создай `.cursor/team/tasks/<slug>/` если его ещё нет — через **Write** артефакта (не Shell `mkdir`).
 4. Запиши `.cursor/team/active-task.json` → `{ "slug": "<slug>" }`.
 5. Опционально: минимальный `pipeline.json` с фиксированными steps (analyst → developer → reviewer → qa-tester).
 6. Вызови subagent **task-analyst** (Task tool) с полным описанием задачи и путём к артефактам.

package/presets/cursor/ios-swift/commands/task.md

@@ -25,7 +25,7 @@ description: Route a natural-language task through the agent-team pipeline: task
 
 ## Алгоритм
 
-1. **Slug** — kebab-case из описания (≤48 символов). Создай `.cursor/team/tasks/<slug>/`.
+1. **Slug** — kebab-case из описания (≤48 символов). Создай `.cursor/team/tasks/<slug>/` через **Write** (например сразу `status.json` или пустой placeholder) — **не** через Shell `mkdir` (песочница → `Operation not permitted`).
 2. **Router** — вызови subagent **task-router** с описанием задачи и путём к slug.
 3. **План** — покажи пользователю таблицу из `pipeline.json`: intent, steps, skipped, humanGates.
 4. **Intent retro** — если `intent === "retro"`, выполни `/technical-retro` и **остановись**.

package/presets/cursor/ios-swift/mcp.json

@@ -0,0 +1,11 @@
+{
+  "mcpServers": {
+    "context7": {
+      "command": "npx",
+      "args": ["-y", "@upstash/context7-mcp"]
+    },
+    "figma": {
+      "url": "https://mcp.figma.com/mcp"
+    }
+  }
+}

package/presets/cursor/ios-swift/rules/agent-team-orchestrator.mdc

@@ -67,12 +67,25 @@ Full prompts: `.cursor/agents/*.md`. Artifacts: `.cursor/team/README.md`.
 2. Read `pipeline.json` before every subagent invocation.
 3. One role per Task call — except parallel steps.
 4. **Never** skip `humanGates` without `/task-continue` or explicit approval.
-5. Persist handoffs to disk under `.cursor/team/tasks/<slug>/`.
+5. Persist handoffs to disk under `.cursor/team/tasks/<slug>/` via **Write** (not Shell `mkdir`).
 6. On `changes_requested`: developer → same reviewer.
 7. On `validation_failed`: developer → build-verifier.
 8. When all steps complete, suggest `/technical-retro <slug>`.
 9. If `autoChain: false`, do not rely on hook.
 
+## Model when invoking (Task)
+
+Honor optional `steps[i].model` (`cheap` \| `standard` \| `strong`); else agent frontmatter (matrix in `agents/README.md`).
+
+- `cheap` → Task `model: "fast"` when accepted.
+- `standard` → omit Task model.
+- `strong` → never pass `fast`; use agent pin `claude-opus-4-8[effort=high]` / parent Max.
+
+## Team artifact I/O (Cursor Shell sandbox)
+
+- Create/update `.cursor/team/tasks/<slug>/**` with the **Write** tool. Do **not** bootstrap slug dirs with Shell `mkdir -p` — sandbox → `Operation not permitted` (esp. macOS Desktop/Documents + TCC).
+- If Shell must touch team paths and fails with EPERM, retry with `required_permissions: ["all"]`.
+
 ## Skip pipeline when
 
 - Pure questions; typo / one-file trivial fix; user «без pipeline»; single-line docs-only.

package/presets/cursor/ios-swift/team/README.md

@@ -25,3 +25,7 @@
 | `bugfix-standard.json` | debugger → developer (skipIf) → verifier → reviewer |
 
 **Never** schedule Playwright-only steps without skip rationale. Use `xcuitest-test-*` for UI-test-only intents.
+
+## Creating task dirs
+
+Bootstrap `tasks/<slug>/` by **writing** artifacts (Write tool), not Shell `mkdir`. Cursor sandbox → `Operation not permitted` otherwise (worse on Desktop/Documents).

package/presets/cursor/ios-swift/team/fixtures/feature-full.json

@@ -4,32 +4,15 @@
   "profile": "full",
   "summary": "Multi-layer Feature with XCUITest coverage",
   "steps": [
-    {
-      "agent": "task-analyst",
-      "label": "Clarify and decompose"
-    },
-    {
-      "agent": "feature-developer",
-      "label": "Implement + unit tests",
-      "scope": "unit-in-dev"
-    },
-    {
-      "agent": "build-verifier",
-      "label": "xcodebuild + lint + unit smoke"
-    },
-    {
-      "agent": "code-reviewer",
-      "label": "Code review"
-    },
-    {
-      "agent": "qa-tester",
-      "label": "XCUITest",
-      "scope": "e2e-only"
-    }
-  ],
-  "humanGates": [
-    "after:task-analyst"
+    { "agent": "task-analyst", "label": "Clarify and decompose" },
+    { "agent": "solution-architect", "label": "Design boundaries", "model": "strong" },
+    { "agent": "feature-developer", "label": "Implement + unit tests", "scope": "unit-in-dev" },
+    { "agent": "build-verifier", "label": "xcodebuild + lint + unit smoke", "model": "cheap" },
+    { "agent": "security-reviewer", "label": "Security review", "model": "strong" },
+    { "agent": "code-reviewer", "label": "Code review", "model": "cheap" },
+    { "agent": "qa-tester", "label": "XCUITest", "scope": "e2e-only" }
   ],
+  "humanGates": ["after:task-analyst"],
   "autoChain": true,
   "skipped": [
     {

package/presets/cursor/ios-swift/team/fixtures/feature-light.json

@@ -2,35 +2,16 @@
   "slug": "example-feature-light",
   "intent": "feature",
   "profile": "light",
-  "summary": "Trivial single-file Swift change with explicit AC",
+  "summary": "Trivial single-file change with explicit AC",
   "steps": [
-    {
-      "agent": "feature-developer",
-      "label": "Implement"
-    },
-    {
-      "agent": "build-verifier",
-      "label": "Validation gate"
-    }
+    { "agent": "feature-developer", "label": "Implement", "model": "cheap" },
+    { "agent": "build-verifier", "label": "xcodebuild + lint + unit smoke", "model": "cheap" }
   ],
   "humanGates": [],
   "autoChain": true,
   "skipped": [
-    {
-      "agent": "task-analyst",
-      "reason": "Explicit AC and single-file scope"
-    },
-    {
-      "agent": "code-reviewer",
-      "reason": "Light profile"
-    },
-    {
-      "agent": "qa-tester",
-      "reason": "No XCUITest AC"
-    },
-    {
-      "agent": "playwright-test-planner",
-      "reason": "iOS uses XCUITest; not needed for light"
-    }
+    { "agent": "task-analyst", "reason": "Explicit AC and single-file scope" },
+    { "agent": "code-reviewer", "reason": "Light profile — non-trivial app changes should use standard" },
+    { "agent": "qa-tester", "reason": "No e2e AC" }
   ]
 }

package/presets/cursor/next/AGENTS.md

@@ -33,4 +33,4 @@ Intent detection, profiles (`full` / `standard` / `light`), and default steps
 npx @bonesofspring/ai-rules init cursor --preset next
 ```
 
-Копирует rules, commands, agents, hooks, skills, team, `hooks.json`, `BUGBOT.md`, `AGENTS.md`.
+Копирует rules, commands, agents, hooks, skills, team, `hooks.json`, `BUGBOT.md`, `AGENTS.md`, `MCP.md`, `mcp.json` → `.cursor/mcp.json`.

package/presets/cursor/next/MCP.md

@@ -0,0 +1,16 @@
+# MCP (preset `next`, Cursor)
+
+Копируется в `.cursor/mcp.json` при `ai-rules init cursor --preset next`.
+
+## Servers
+
+| Name | Package | Зачем |
+|------|---------|--------|
+| `context7` | `@upstash/context7-mcp` | Актуальная документация Next/React/TS и библиотек (меньше устаревших API в ответах агента) |
+| `playwright` | `@playwright/mcp` | Browser automation для e2e агентов (`playwright-test-*`) и проверки селекторов |
+| `chrome-devtools` | `chrome-devtools-mcp` | Live DOM/network/performance при отладке UI |
+| `figma` | remote `https://mcp.figma.com/mcp` | Design context → код (макеты, токены, Code Connect); OAuth в Cursor |
+
+Секреты в файл не кладём. Опционально: `CONTEXT7_API_KEY` в окружении — выше rate limits у Context7. Figma — OAuth при первом подключении (токен в конфиг не пишем).
+
+После init: Settings → MCP → включить серверы (или перезапустить Cursor). Локально можно дополнять/переопределять; `init` перезаписывает одноимённый `mcp.json`.

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

@@ -56,6 +56,23 @@
 
 Ограничение «не трогать production / `app/**`» задаётся **в теле промпта**, не флагом `readonly`. В Cursor `readonly: true` блокирует *любые* file edits (включая team) — для team-агентов это ломает пайплайн.
 
+## Model matrix (frontmatter `model`)
+
+SoT по умолчанию — YAML `model` в каждом agent-файле. Опциональный `steps[].model` (`cheap` \| `standard` \| `strong`) переопределяет тир на шаге пайплайна (см. `task-router.md`, `agent-team-orchestrator.mdc`).
+
+| Tier | Default frontmatter | Agents |
+|------|---------------------|--------|
+| **cheap** | `fast` | `task-router`, `task-analyst`, `build-verifier`, `code-reviewer`, `tech-writer` |
+| **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**
+
+- `inherit` = модель parent-чата (обычно сильнее `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
 
 | Command | Назначение |
@@ -94,6 +111,7 @@
 | `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 |
+| `model` | no | `cheap` \| `standard` \| `strong` — pipeline tier override; omit → agent frontmatter |
 
 ### Minimal template
 
@@ -114,26 +132,43 @@
 }
 ```
 
-### Example: parallel reviewers
+### Example: parallel reviewers + model tiers
 
 ```json
 {
   "intent": "feature",
+  "profile": "full",
   "steps": [
     { "agent": "task-analyst", "label": "Clarify" },
+    { "agent": "solution-architect", "label": "Design boundaries", "model": "strong" },
     { "agent": "feature-developer", "label": "Implement", "scope": "unit-in-dev" },
-    { "agent": "build-verifier", "label": "Validation gate" },
+    { "agent": "build-verifier", "label": "Validation gate", "model": "cheap" },
     {
       "agent": ["accessibility-reviewer", "security-reviewer"],
       "parallel": true,
-      "label": "A11y and security"
+      "label": "A11y and security",
+      "model": "strong"
     },
-    { "agent": "code-reviewer", "label": "Review" }
+    { "agent": "code-reviewer", "label": "Review", "model": "cheap" }
   ],
   "humanGates": ["after:task-analyst"]
 }
 ```
 
+### Example: light profile with cheap models
+
+```json
+{
+  "intent": "feature",
+  "profile": "light",
+  "steps": [
+    { "agent": "feature-developer", "label": "Implement", "model": "cheap" },
+    { "agent": "build-verifier", "label": "Validation gate", "model": "cheap" }
+  ],
+  "humanGates": []
+}
+```
+
 ### Example: bugfix skipIf
 
 ```json

package/presets/cursor/next/agents/migration-specialist.md

@@ -2,7 +2,7 @@
 name: migration-specialist
 description: Migration planning specialist for library upgrades, Next.js major versions, HTTP client swaps, and phased refactors with rollback. Writes migration-plan.md and team status; never writes production code.
 readonly: false
-model: inherit
+model: claude-opus-4-8[effort=high]
 ---
 
 You are a migration specialist for a Next.js frontend with strict layer boundaries.

package/presets/cursor/next/agents/performance-auditor.md

@@ -2,7 +2,7 @@
 name: performance-auditor
 description: Performance audit specialist. Reviews bundle size, lazy loading, render patterns, data fetching waterfalls, and Core Web Vitals risks. Readonly — writes perf-report.md only; never edits production code.
 readonly: false
-model: inherit
+model: claude-opus-4-8[effort=high]
 ---
 
 You are a frontend performance auditor for a Next.js React application.

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

@@ -19,7 +19,7 @@ You generate Playwright tests from project test plans.
 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.
+5. **Use `playwright` MCP** when available (`browser_navigate`, `browser_snapshot`, generator tools; may appear as `user-playwright` if installed globally) to verify selectors before finalizing specs.
 6. Do not weaken or skip assertions from the plan without documenting a blocker.
 
 ## Completion

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

@@ -18,7 +18,7 @@ You debug and fix failing Playwright e2e tests.
 1. Follow **`playwright-agents.mdc`**, **`tests-e2e-structure.mdc`**, 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.
+4. **Use `playwright` MCP** when available (or `user-playwright` if installed globally) 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.
 

package/presets/cursor/next/agents/security-reviewer.md

@@ -2,7 +2,7 @@
 name: security-reviewer
 description: Security review specialist. Audits auth flows, token handling, XSS risks, secrets in diff, and unsafe DOM/API usage. Readonly — writes security-review.md only; never edits production code.
 readonly: false
-model: inherit
+model: claude-opus-4-8[effort=high]
 ---
 
 You are a frontend security reviewer for a Next.js TypeScript application.

package/presets/cursor/next/agents/solution-architect.md

@@ -2,7 +2,7 @@
 name: solution-architect
 description: Solution architect for cross-layer features, API boundaries, and technical design before implementation. Use for spike intent or when router adds architect step for complex features. Readonly — produces design docs, not production code.
 readonly: false
-model: inherit
+model: claude-opus-4-8[effort=high]
 ---
 
 You are a solution architect for a Next.js frontend with strict layer boundaries (types, api, store, ui).

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

@@ -65,7 +65,21 @@ Fixtures: `.cursor/team/fixtures/` (feature-full, feature-light, bugfix-standard
 - Add **tech-writer** when docs/changelog requested.
 - **Always build-verifier** after developer (or after ci-investigator/debugger if they changed code) for `feature`, `bugfix`, `refactor`, `migration`, `a11y`.
 - **skipIf:** `debugger.fixed` on developer (bugfix); `ci-investigator.resolved` (ci-fix).
-- **Model:** `inherit` when 4+ steps or cross-layer uncertainty.
+
+## Model tiers (`steps[].model`)
+
+Optional per-step field: `"model": "cheap" | "standard" | "strong"`. Omit → agent frontmatter default (see **Model matrix** in `agents/README.md`).
+
+| When | What to write |
+|------|----------------|
+| `profile: light` | set `cheap` on **all** steps (exception: unclear bug root cause on `debugger` → `strong`) |
+| `profile: standard` | omit (frontmatter defaults) |
+| `profile: full` | set `strong` on `solution-architect`, `migration-specialist`, `security-reviewer`, `performance-auditor` when present; omit others |
+| `intent: spike` | set `strong` on `solution-architect` (and analyst may stay default/`cheap`) |
+| `intent: perf-audit` / security-heavy feature | `strong` on auditor/reviewer step |
+| Always | **never** `strong` on `build-verifier`, `tech-writer`, `task-router` |
+
+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)
 
@@ -82,7 +96,7 @@ Fixtures: `.cursor/team/fixtures/` (feature-full, feature-light, bugfix-standard
 
 ## Output
 
-Write `.cursor/team/tasks/<slug>/pipeline.json` and initial `status.json`; set `.cursor/team/active-task.json` → `{ "slug": "<slug>" }`. Minimal template — см. **`agents/README.md`**.
+Write `.cursor/team/tasks/<slug>/pipeline.json` and initial `status.json` via the **Write** tool (creates parents; do not Shell-`mkdir`); set `.cursor/team/active-task.json` → `{ "slug": "<slug>" }`. Minimal template — см. **`agents/README.md`**.
 
 ## Handoff to orchestrator
 

package/presets/cursor/next/commands/feature-start.md

@@ -13,7 +13,7 @@ description: Legacy analyst-only feature intake. Prefer /task for new work becau
 
 1. Извлеки описание задачи из аргументов команды (всё после `/feature-start`).
 2. Сгенерируй **slug** (kebab-case, до 48 символов) из заголовка задачи.
-3. Создай каталог `.cursor/team/tasks/<slug>/` если его ещё нет.
+3. Создай `.cursor/team/tasks/<slug>/` если его ещё нет — через **Write** артефакта (не Shell `mkdir`).
 4. Запиши `.cursor/team/active-task.json` → `{ "slug": "<slug>" }`.
 5. Опционально: минимальный `pipeline.json` с фиксированными steps (analyst → developer → reviewer → qa-tester).
 6. Вызови subagent **task-analyst** (Task tool) с полным описанием задачи и путём к артефактам.

package/presets/cursor/next/commands/task.md

@@ -25,7 +25,7 @@ description: Route a natural-language task through the agent-team pipeline: task
 
 ## Алгоритм
 
-1. **Slug** — kebab-case из описания (≤48 символов). Создай `.cursor/team/tasks/<slug>/`.
+1. **Slug** — kebab-case из описания (≤48 символов). Создай `.cursor/team/tasks/<slug>/` через **Write** (например сразу `status.json` или пустой placeholder) — **не** через Shell `mkdir` (песочница → `Operation not permitted`).
 2. **Router** — вызови subagent **task-router** с описанием задачи и путём к slug.
 3. **План** — покажи пользователю таблицу из `pipeline.json`: intent, steps, skipped, humanGates.
 4. **Intent retro** — если `intent === "retro"`, выполни `/technical-retro` и **остановись**.

package/presets/cursor/next/hooks/chain-team-phases.sh

@@ -157,10 +157,10 @@ const AGENT_HANDOFF = {
     `Follow playwright-agents.mdc and the playwright-e2e skill. Update status.json when done.`,
   'playwright-test-generator': (s) =>
     `Invoke playwright-test-generator for slug "${s}". Generate/update *.spec.ts from matching *.cases.md. ` +
-    `Use user-playwright MCP when available. Follow playwright-agents.mdc and the playwright-e2e skill. Update status.json when done.`,
+    `Use playwright MCP when available. Follow playwright-agents.mdc and the playwright-e2e skill. Update status.json when done.`,
   'playwright-test-healer': (s) =>
     `Invoke playwright-test-healer for slug "${s}". Fix failing/flaky e2e while preserving cases.md assertions. ` +
-    `Use user-playwright MCP when available. Follow playwright-agents.mdc and debug-investigation. Update status.json when done.`,
+    `Use playwright MCP when available. Follow playwright-agents.mdc and debug-investigation. Update status.json when done.`,
   'tech-writer': (s) =>
     `Invoke tech-writer for slug "${s}". Write documentation.md from task artifacts. Update status.json when done.`,
 };