@bonesofspring/ai-rules 0.2.4 → 0.2.6

package/presets/cursor/ios-swift/rules/technical-retro.mdc

@@ -3,10 +3,12 @@ description: Роль агента для проведения техничес
 alwaysApply: false
 ---
 
+<!-- shared-core: review/technical-retro.md -->
+
 # Техническое ретро — rule alias
 
-Полный сценарий (включая блок **«Работа агентов»** для slug из `.cursor/team/tasks/`) — в slash-команде:
+Полный сценарий (включая блок **«Работа агентов»** для slug из team tasks) — в slash-команде:
 
-**`.cursor/commands/technical-retro.md`** → `/technical-retro`
+**`commands/technical-retro.md`** → `/technical-retro`
 
 Используй rule только если command недоступен. Не дублируй содержимое command в ответе — следуй command-файлу и skill `technical-retro`.

package/presets/cursor/ios-swift/skills/code-review/SKILL.md

@@ -25,3 +25,7 @@ Use the local repository as the source of truth: `git status`, `git diff`, task
 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 `.cursor/team/tasks/<slug>/review.md` and set `status.json` to `completed` or `changes_requested`.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

package/presets/cursor/ios-swift/skills/debug-investigation/SKILL.md

@@ -28,3 +28,7 @@ For agent team tasks, write `.cursor/team/tasks/<slug>/debug-report.md` with:
 Update `status.json` when complete.
 
 Do not use browser/Playwright tooling — this is an Xcode stack.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

package/presets/cursor/ios-swift/skills/feature-delivery/SKILL.md

@@ -25,3 +25,7 @@ When editing **ai-rules ios-swift preset** sources (agents, hooks, rules) rather
 ## Handoff
 
 Summarize by layer, validation results, and known gaps. Agent team: update `.cursor/team/tasks/<slug>/status.json`.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

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/README.md

@@ -0,0 +1,46 @@
+# Next.js preset (Cursor)
+
+Правила и agent-team surface для Next.js / React / TypeScript.
+
+## Install
+
+```bash
+npx @bonesofspring/ai-rules init cursor --preset next
+```
+
+Копирует:
+
+| Path | Содержание |
+|------|------------|
+| `AGENTS.md` | Quick-start |
+| `BUGBOT.md` | Cursor Bugbot review priorities (Next) |
+| `rules/**` | `.mdc` + README (alwaysApply ≤3) |
+| `agents/**` | **21** ролей (+ README) |
+| `skills/**` | 7 skills (в т.ч. `playwright-e2e`) |
+| `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)
+
+`next-app-core`, `package-manager`, `code-quality-and-refactoring`.
+
+Requestable (не always-on): `post-change-lint`, `agent-team-*`, `code-review-mr`, `feature-delivery-workflow`, `reference-features`, domain globs.
+
+## Preset taxonomy & contributing
+
+- **Layers:** Core → Stack → Platform — [`../../_shared/README.md`](../../_shared/README.md)
+- **Contribution guide:** [`../../docs/PRESET-CONTRIBUTION.md`](../../docs/PRESET-CONTRIBUTION.md) (SoT, twins, token budget, PR checklist)
+- **Author meta-rules:** `preset-*.mdc` (globs `packages/ai-rules/presets/**`, never alwaysApply)
+- **Core→stack mapping:** [`rules/README.md`](./rules/README.md) § Shared core
+
+## Sync with Claude
+
+SoT = этот Cursor-пресет. После правок `.mdc` / agents / skills — обновить twin в `presets/claude/next/` **в том же PR**.
+
+`BUGBOT.md` — **Cursor-only** (нет Claude twin); для Claude Code — skill `code-review` + `tooling-and-review/code-review.md`.
+
+Claude→Cursor map: `presets/claude/next/rules/README.md`.
+
+См. также `AGENTS.md`.

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/build-verifier.md

@@ -26,6 +26,30 @@ Use **`package-manager.mdc`** for the repo package manager.
 
 Prefer **`lint`** (= js + css + type-check) before handoff on large changes.
 
+## Preset-structure validation (when scope is preset / packages/ai-rules)
+
+When validating **preset packaging** changes (paths under `packages/ai-rules/presets/**`, or `scope: preset-structure-validation` / `preset-artifacts-only`), run these checks. Skip app lint if there are **no** `app/**` changes.
+
+### FAIL (all stacks)
+
+1. **Token budget:** Cursor `alwaysApply: true` count ≤ **3**; Claude rules without `paths:` === **3** (**exclude `**/README.md`** — Option A). Meta `preset-*` rules must **not** be `alwaysApply: true`.
+2. **Leakage (next):** hooks/agents must not require `xcuitest-test-*` handoffs or `xcodebuild` as the default Next post-change gate. See `preset-no-cross-stack-leakage.mdc`.
+3. **Mapping / README:** `claude/next/rules/README.md` must include a Cursor→Claude mapping table; stack `rules/README.md` should document core→stack mapping when `_shared` consumers exist.
+4. **shared-core consumers:** if `_shared/core/**` changed, every file with matching `<!-- shared-core: … -->` in this PR must be updated (or intentional fork documented in validation-report).
+5. **Twin presence:** Cursor rule change without Claude twin same PR → **FAIL** (next, ios-swift, and go). Domain twin body ≥15 lines; thin aliases (`agent-team-intake`, `technical-retro`) may be shorter.
+6. **Session-start body budget (soft→document, FAIL if grossly over):** sum body lines of the **3** intended always-on / session-start rules ≤ **120** (stretch ≤100); do **not** include `**/README.md`. Record the sum in validation-report.
+7. **Embed drift (soft by default):** run `packages/ai-rules/scripts/check-shared-core-drift.sh`. Document DRIFT; set `AI_RULES_DRIFT_FAIL=1` only when enforcing. Lineage stems are excluded from body equality.
+8. **Dogfood (monorepo soft):** if root `.cursor/` is in the PR, prefer sync via `packages/ai-rules/scripts/sync-dogfood-cursor.sh`; mass deletion of tracked dogfood without migration doc → note as risk / FAIL for maintainers.
+
+### Soft notes
+
+- Thin aliases may be &lt;15 body lines.
+- Embed vs lineage modes: see `docs/PRESET-CONTRIBUTION.md` and `_shared/README.md`.
+
+### ios-swift-only checks
+
+Not required for next-only PRs. When both stacks touched, also apply ios-swift verifier checks (chain fork, Playwright leakage, XCUITest stems) — **FAIL**.
+
 ## Output
 
 Write `.cursor/team/tasks/<slug>/validation-report.md`:

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

@@ -62,3 +62,7 @@ Update `status.json`:
 If **REQUEST_CHANGES**, set `"state": "changes_requested"` (hook will re-invoke feature-developer).
 
 Do not mix this output with retrospective facilitation — keep review and retro separate.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

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

@@ -62,3 +62,7 @@ Update `status.json`:
 Handoff summary: root cause, recommended fix, files touched (if any).
 
 Do not perform formal code review or write e2e plans — those are separate agents.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

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

@@ -26,3 +26,7 @@ You are a senior frontend developer working in a Next.js monorepo with strict la
 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.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

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.
@@ -69,3 +69,7 @@ Update `status.json`:
 ```
 
 Hand off: orchestrator runs human gate (if configured), then `feature-developer` executes phases from the plan.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

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.
@@ -68,3 +68,7 @@ Update `status.json`:
 For standalone `perf-audit` intent, suggest `/technical-retro` or a follow-up `/task` to implement fixes.
 
 Do not modify production code.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

package/presets/cursor/next/agents/qa-tester.md

@@ -56,3 +56,7 @@ Provide summary:
 - Test run results
 - Gaps vs acceptance criteria
 - Suggest `/technical-retro` with the slug when done
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

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).
@@ -69,3 +69,7 @@ Update `status.json`:
 For `spike` intent with human gate after architect: set `"state": "awaiting_approval"` if design needs user sign-off.
 
 Handoff: summary of design decisions and recommended next steps for developer.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

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

@@ -110,3 +110,7 @@ When DoR is reached and artifacts are saved:
 3. **Stop** and ask the user to review artifacts. Tell them to run `/task-continue <slug>` after approval or reply with corrections.
 
 Do not invoke the developer or any implementation subagent.
+
+## Design guidance (optional)
+
+- Optional: Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit — only when decomposing refactor/architecture tasks (not default).

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)
 

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

@@ -37,3 +37,7 @@ Update `status.json`:
   "updatedAt": "<ISO8601>"
 }
 ```
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

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

@@ -38,3 +38,7 @@ Update `status.json`:
   "updatedAt": "<ISO8601>"
 }
 ```
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

package/presets/cursor/next/agents/unit-test-planner.md

@@ -62,3 +62,7 @@ Update `status.json`:
 ```
 
 Do not write `*.spec.ts` files — that is `unit-test-generator`'s job.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

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

@@ -42,7 +42,7 @@ Slash-команды копируются в `.cursor/commands/` при `ai-rule
 
 ## Связанные файлы
 
-- Subagents: `../agents/` (20 ролей, включая `task-router.md`)
+- Subagents: `../agents/` (**21** ролей, включая `task-router.md`)
 - Оркестратор: `../rules/agent-team-orchestrator.mdc`
 - Skills: `../skills/` (`feature-delivery`, `code-review`, `debug-investigation`, `ci-investigation`, `unit-testing`, `playwright-e2e`, `technical-retro`)
 - Артефакты: `../team/README.md` (`pipeline.json`, `status.json`)

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

@@ -21,9 +21,28 @@
 
 - **`alwaysApply: true`** (Cursor) / **без `paths:`** (Claude) — только базовые инварианты (**3**):
   - `next-app-core`, `package-manager`, `code-quality-and-refactoring`
-- **On-demand / requestable** — `post-change-lint` (**обязателен после правок кода**, не always-on), `agent-team-intake` (через orchestrator/commands), `agent-team-orchestrator`, architecture, imports, UI, tests, feature-delivery-workflow, reference-features, next-app-router, react-a11y-coding
+- **On-demand / requestable** — `post-change-lint` (**обязателен после правок кода**, не always-on), `agent-team-intake` (через orchestrator/commands), `agent-team-orchestrator`, architecture, imports, UI, tests, feature-delivery-workflow, `design-guidance`, reference-features, next-app-router, react-a11y-coding, `technical-retro`
+- **Preset author meta** (globs `packages/ai-rules/presets/**`, never alwaysApply): `preset-layering`, `preset-twin-sync`, `preset-token-budget`, `preset-pr-checklist`, `preset-no-cross-stack-leakage`
 - **Skills** — длинные процедуры (`feature-delivery`, `code-review`, …)
 
+### Shared core → stack mapping
+
+SoT prose: `packages/ai-rules/presets/_shared/core/**` (see `_shared/README.md`). Adapters carry `<!-- shared-core: … -->`.
+
+| Shared core | This stack adapter | Delta |
+|-------------|--------------------|-------|
+| `quality/code-quality-and-refactoring.md` | `code-quality-and-refactoring.mdc` | Stack notes: ESLint/stylelint, CSS tokens |
+| `quality/design-guidance.md` | `design-guidance.mdc` | requestable smells/GoF; globs `app/src/**/*.{ts,tsx}` |
+| `agent-team/agent-team-orchestrator.md` | `agent-team-orchestrator.mdc` | Roles (Playwright trio); preset PR pointer |
+| `agent-team/agent-team-intake.md` | `agent-team-intake.mdc` | thin |
+| `architecture/feature-delivery-workflow.md` | `feature-delivery-workflow.mdc` | Next layer checklist |
+| `architecture/reference-features.template.md` | `reference-features.mdc` | `app/src/**` table |
+| `review/code-review-mr.md` | `code-review-mr.mdc` | Next checklist refs |
+| `review/technical-retro.md` | `technical-retro.mdc` | thin alias |
+| `meta/preset-*.md` | `preset-*.mdc` | author-only globs |
+
+Claude twins + Cursor→Claude map: `presets/claude/next/rules/README.md`.
+
 ### UI edit bundle (consolidated globs)
 
 При правке `app/src/ui/**/*.tsx` подгружается **уменьшенный** набор (не весь `app/src/**`):
@@ -56,6 +75,7 @@
 | `agent-team-intake.mdc` | Подсказка `/task` при work-запросе (on-demand, через orchestrator) |
 | `package-manager.mdc` | Перед `install` / `run` в терминале определить менеджер пакетов репо (lockfile, `packageManager`) и использовать только его |
 | `agent-team-orchestrator.mdc` | `/task`, router, `pipeline.json`, build-verifier, parallel steps |
+| `preset-pr-checklist.mdc` (+ sibling `preset-*`) | Чеклист PR авторов пресетов (twin, budget, leakage) |
 | `next-app-core.mdc` | Стек, слои, карта каталогов (alwaysApply) |
 | `post-change-lint.mdc` | Прогон ESLint + Stylelint после изменений кода (**requestable**, обязателен после code edits) |
 | `architecture-boundaries-ui.mdc` | Slim границы UI при правках компонентов |

package/presets/cursor/next/rules/agent-team-intake.mdc

@@ -3,6 +3,8 @@ description: Use when user posts a work request without /task — suggest or use
 alwaysApply: false
 ---
 
+<!-- shared-core: agent-team/agent-team-intake.md -->
+
 # Agent team intake
 
 When the user message looks like a **work request** (implement, add, fix, refactor, review MR, write tests, spike) — not a question about how code works:

package/presets/cursor/next/rules/agent-team-orchestrator.mdc

@@ -3,6 +3,8 @@ description: Orchestrates the agent team via task-router and pipeline.json. Use
 alwaysApply: false
 ---
 
+<!-- shared-core: agent-team/agent-team-orchestrator.md -->
+
 # Agent team orchestrator
 
 Parent agent = **manager**. Router plans; specialists execute. Artifacts: `.cursor/team/tasks/<slug>/`.
@@ -19,7 +21,9 @@ Work request без `/task` — см. **`agent-team-intake.mdc`** (когда п
 | `/feature-continue <slug>` | Alias of task-continue |
 | `/technical-retro [slug]` | Retro with agent team block |
 
-## Roles
+## Stack notes
+
+### Roles
 
 | Agent | App / prod writes | Typical intent |
 |-------|-------------------|----------------|
@@ -31,7 +35,7 @@ Work request без `/task` — см. **`agent-team-intake.mdc`** (когда п
 | `debugger` | minimal fix | bugfix |
 | `ci-investigator` | minimal CI fix | ci-fix — minimal CI repair |
 | `feature-developer` | yes | feature, bugfix, refactor, migration, a11y |
-| `build-verifier` | no (team only) | lint/type-check/unit gate after developer |
+| `build-verifier` | no (team only) | lint/type-check/unit gate after developer; preset-structure when editing presets |
 | `accessibility-reviewer` | no (team only) | a11y, UI-heavy feature |
 | `performance-auditor` | no (team only) | perf-audit, perf-sensitive feature |
 | `code-reviewer` | no (team only) | most pipelines, review-only |
@@ -49,6 +53,8 @@ Work request без `/task` — см. **`agent-team-intake.mdc`** (когда п
 
 Full prompts: `.cursor/agents/*.md`. Artifact conventions: `.cursor/team/README.md`.
 
+When editing `packages/ai-rules/presets/**`, follow **`preset-pr-checklist.mdc`** (+ twin-sync / layering / token-budget / leakage meta-rules).
+
 ## Dynamic pipeline
 
 ```mermaid
@@ -102,6 +108,7 @@ flowchart TD
 | `skipIf` | `debugger.fixed` / `ci-investigator.resolved` — hook skips step when artifact says fix applied |
 | `parallel: true` | `agent` is array — invoke **all** agents in one parent turn; each appends to `parallelCompleted` |
 | `scope` | e.g. `unit-in-dev`, `e2e-only` — passed to developer/qa |
+| `model` | `cheap` \| `standard` \| `strong` — optional tier override (see below) |
 
 ## Rules (strict)
 
@@ -125,6 +132,15 @@ flowchart TD
 
 Use Task tool or `/agent-name`. Pass: slug, artifact paths, step `scope` if set.
 
+### Model when invoking (Task)
+
+1. Read `steps[i].model` if present; else use the agent’s frontmatter `model` (see `agents/README.md` matrix).
+2. Map abstract tiers:
+   - **`cheap`** → pass Task `model: "fast"` when the tool accepts it (or rely on agent `fast`).
+   - **`standard`** → omit Task `model` (frontmatter `inherit` / mid default).
+   - **`strong`** → **never** pass `fast`; rely on agent pin (`claude-opus-4-8[effort=high]`) or parent Max model. If Task allows an explicit model ID from the allowed list, prefer the strong agent’s frontmatter ID.
+3. Parallel steps: apply the step-level `model` to **each** agent in the array (or omit → each agent’s own frontmatter).
+
 After each agent completes, ensure `status.json` has `state: completed` (or `awaiting_approval` if gate applies).
 
 ## Legacy mode