@bonesofspring/ai-rules 0.2.4 → 0.2.6

package/presets/cursor/go/rules/reference-features.mdc

@@ -0,0 +1,31 @@
+---
+description: Reference paths for Go hexagonal layout (fill after init)
+globs:
+  - internal/**/*
+  - cmd/**/*
+alwaysApply: false
+---
+
+<!-- shared-core: architecture/reference-features.template.md -->
+
+# Reference features (Go)
+
+Fill TBD paths after adopting this preset in a real service repo.
+
+| Area | Example path (TBD) | Glob hint |
+|------|--------------------|-----------|
+| Domain | `internal/domain/` | `**/domain/**` |
+| Application / ports | `internal/application/` | `**/application/**` |
+| HTTP adapter | `internal/adapters/http/` | `**/adapters/http/**` |
+| Persistence | `internal/adapters/persistence/` | `**/adapters/persistence/**` |
+| Composition root | `cmd/<service>/`, `internal/app/` | `cmd/**`, `internal/app/**` |
+| Unit tests | `*_test.go` beside packages | `**/*_test.go` |
+| Integration | `**/integration/` | `**/*_integration_test.go` |
+
+## Dogfood scenarios
+
+1. `/task` new use case — domain → ports → adapters → wire → `post-change-test`.
+2. Bug in handler mapping — debugger + httptest unit.
+3. Repository contract — integration-test trio.
+4. OpenAPI/proto drift — api-contract-reviewer.
+5. Secrets in logs — security-reviewer + `security-go`.

package/presets/cursor/go/rules/security-go.mdc

@@ -0,0 +1,23 @@
+---
+description: Security basics for Go backends (secrets, auth, PII, TLS)
+globs:
+  - "**/middleware/**/*"
+  - "**/auth/**/*"
+  - "**/config/**/*"
+alwaysApply: false
+---
+
+
+# Security (Go)
+
+- Secrets from env/secret manager — never commit keys; do not log tokens/passwords.
+- Validate and canonicalize untrusted input at the driving adapter edge.
+- Prefer prepared statements / parameterized queries in persistence adapters.
+- TLS and secure cookie/header defaults when exposing HTTP.
+- AuthN/AuthZ in middleware or driving adapters; pass identity into use cases as domain value (user ID / claims), not raw headers.
+- Minimize PII in logs; redact where needed.
+
+## Config
+
+- Distinguish public vs secret config fields in types.
+- Fail closed when auth is misconfigured in production builds.

package/presets/cursor/go/rules/technical-retro.mdc

@@ -0,0 +1,14 @@
+---
+description: Technical retro alias — use /technical-retro command
+alwaysApply: false
+---
+
+<!-- shared-core: review/technical-retro.md -->
+
+# Техническое ретро — rule alias
+
+Полный сценарий (включая блок **«Работа агентов»** для slug из team tasks) — в slash-команде:
+
+**`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/go/rules/tests-e2e.mdc

@@ -0,0 +1,19 @@
+---
+description: End-to-end HTTP smoke tests for Go services
+globs:
+  - "**/e2e/**/*_test.go"
+  - "**/*_e2e_test.go"
+alwaysApply: false
+---
+
+
+# E2E / HTTP smoke
+
+- Black-box against a running server (httptest with full composition root, or localhost in CI).
+- Cover critical paths only; prefer integration + unit for breadth.
+- Stable test data; avoid depending on wall-clock flakiness.
+- Do not use browser/Playwright tooling in this preset.
+
+## Placement
+
+- `e2e/` package or `*_e2e_test.go` with build tags if needed.

package/presets/cursor/go/rules/tests-integration.mdc

@@ -0,0 +1,24 @@
+---
+description: Integration / adapter contract tests for Go hexagonal services
+globs:
+  - "**/integration/**/*_test.go"
+  - "**/*_integration_test.go"
+alwaysApply: false
+---
+
+
+# Integration tests
+
+- Exercise driven adapters against real infra doubles (testcontainers, docker compose test DB, miniredis, etc.).
+- Or exercise HTTP adapter with `httptest` + wired use case + fake/real ports — still no full prod cluster required.
+- Build tags (`//go:build integration`) if the repo separates CI jobs.
+- Keep fixtures deterministic; clean up data between tests.
+
+## Scope
+
+- Contract of a port implementation (repo save/load roundtrip).
+- Not a substitute for domain unit tests.
+
+## Agents
+
+- Planning/generation: `integration-test-{planner,generator,healer}` + skill `integration-testing`.

package/presets/cursor/go/rules/tests-unit.mdc

@@ -0,0 +1,25 @@
+---
+description: Unit testing conventions for Go hexagonal services
+globs:
+  - "**/*_test.go"
+alwaysApply: false
+---
+
+
+# Unit tests
+
+- Table-driven tests; clear arrange/act/assert.
+- Domain and application: mock/fake **ports** only — no real DB/network.
+- Prefer fakes over heavy mocking frameworks when simple.
+- Skip integration/e2e files matching `*_integration_test.go`, `*_e2e_test.go`, or dirs `integration/`, `e2e/` — those use other rules.
+
+## Forbidden smells
+
+- `gin.Context` / `http.Request` in domain tests.
+- SQL or live HTTP in use-case unit tests.
+- Brittle tests on unexported adapter internals without need.
+- Structural smells vocabulary (Feature Envy, Message Chains, …): see requestable `design-guidance` — do not duplicate the catalog here.
+
+## Naming
+
+- `TestUseCase_DoX` / `TestEntity_Invariant`.

package/presets/cursor/go/skills/README.md

@@ -0,0 +1,5 @@
+# Skills (preset go)
+
+7 skills: `feature-delivery`, `unit-testing`, `integration-testing`, `ci-investigation`, `debug-investigation`, `code-review`, `technical-retro`.
+
+No `playwright-e2e` / `xcuitest-e2e`.

package/presets/cursor/go/skills/ci-investigation/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: ci-investigation
+description: Investigates failing CI checks on PRs and branches — go test, vet, lint, integration, preset-structure — with local reproduction and minimal fixes. Use when CI is red or for ci-fix pipeline tasks.
+---
+
+# CI investigation (Go)
+
+1. Identify job + log excerpt.
+2. Reproduce locally with the same commands.
+3. Minimal fix; for ai-rules preset PRs run `yarn check:preset-structure`.
+4. Do not treat Playwright/xcodebuild/`lint:js` as default Go gates.

package/presets/cursor/go/skills/code-review/SKILL.md

@@ -0,0 +1,16 @@
+---
+name: code-review
+description: Reviews pull requests and branch diffs for Go hexagonal services using architecture, ports/adapters, networking, and testing standards. Use when the user asks for review or when code-reviewer runs.
+---
+
+# Code review (Go)
+
+1. Diff-first; load `code-review-mr.mdc` + hexagonal rules.
+2. Check layer leaks, port ownership, composition root purity, tests, security-sensitive bits.
+3. Write `review.md` with APPROVE or REQUEST_CHANGES.
+
+Never require iOS/Next-only gates (XCUITest, Playwright, `lint:js`).
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

package/presets/cursor/go/skills/debug-investigation/SKILL.md

@@ -0,0 +1,15 @@
+---
+name: debug-investigation
+description: Investigates bugs, failing tests, and unexpected behavior in Go services with runtime evidence before applying minimal fixes. Use for bugfix tasks, debugger agent runs, or regressions.
+---
+
+# Debug investigation (Go)
+
+1. Capture failing `go test` / logs / stack traces.
+2. Hypothesize layer (domain vs adapter vs wiring).
+3. Minimal fix + regression test when appropriate.
+4. Document in `debug-report.md`.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

package/presets/cursor/go/skills/feature-delivery/SKILL.md

@@ -0,0 +1,26 @@
+---
+name: feature-delivery
+description: Delivers Go hexagonal backend features end-to-end across domain, application/ports, adapters, composition root, tests, and post-change-test validation. Use when implementing or extending a feature, especially through /task or feature-developer.
+---
+
+# Feature Delivery (Go hexagonal)
+
+1. Read brief, AC, and decomposition.
+2. Follow `feature-delivery-workflow.mdc` + `reference-features.mdc`: domain → application/ports → driven adapters → driving adapters → composition root → tests.
+3. Wire DI only in `cmd/` / `internal/app`.
+4. Add unit tests for domain/use cases; integration tests for risky adapters.
+5. After Go edits: **invoke** `post-change-test.mdc` (+ `go-tooling.mdc`).
+
+## Do / Don't
+
+- **Do** keep ports owned by application; map wire types at adapters.
+- **Don't** put SQL/business rules in HTTP handlers or frameworks in domain.
+- **Don't** use Playwright, XCUITest, or yarn lint as this stack's gate.
+
+## Handoff
+
+Summarize by layer + validation. Update `.cursor/team/tasks/<slug>/status.json`.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

package/presets/cursor/go/skills/integration-testing/SKILL.md

@@ -0,0 +1,15 @@
+---
+name: integration-testing
+description: Plans, generates, and heals Go integration and adapter contract tests (httptest, testcontainers). Use for integration-test-* agents or adapter/e2e coverage.
+---
+
+# Integration testing (Go)
+
+1. Read `tests-integration` / `tests-e2e` rules and task brief.
+2. Prefer testing driven adapters behind ports; HTTP adapters with `httptest` + fakes.
+3. Use build tags / CI job split if the repo already does.
+4. Do not introduce Playwright or XCUITest.
+
+## Agents
+
+`integration-test-planner` → `integration-test-generator` → `integration-test-healer` as needed.

package/presets/cursor/go/skills/technical-retro/SKILL.md

@@ -0,0 +1,10 @@
+---
+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
+
+Same structure as next technical-retro skill. For `/task` pipelines include router, analyst, developer, **build-verifier** (go test), reviewer, QA/integration tests, hooks, rules.
+
+Preset feedback: propose updates to `.cursor/rules|agents|skills` — do not apply without approval.

package/presets/cursor/go/skills/unit-testing/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: unit-testing
+description: Plans, generates, and heals table-driven Go unit tests for domain, use cases, and mappers using *_test.go and tests-unit rules. Use for unit-test planning, generation, or healing.
+---
+
+# Unit testing (Go)
+
+1. Prefer table-driven `testing` packages beside code under test.
+2. Fake outbound ports for use cases; no real DB/network.
+3. Follow `tests-unit.mdc`; heal with `unit-test-healer` when red.
+
+## Agents
+
+`unit-test-planner` → `unit-test-generator` → `unit-test-healer`.

package/presets/cursor/go/team/README.md

@@ -0,0 +1,31 @@
+# Agent team artifacts (go)
+
+Каталог артефактов пайплайна «команда агентов» для Go backend (hexagonal / ports & adapters).
+
+## Layout
+
+```
+.cursor/team/   # Claude: .claude/team/
+  active-task.json
+  fixtures/
+  tasks/<slug>/
+    pipeline.json
+    status.json
+    brief.md
+    decomposition.md
+    …
+```
+
+## Fixtures
+
+| Fixture | Notes |
+|---------|-------|
+| `feature-full.json` | Full profile; QA scope `e2e-only` = **adapter/integration tests** (not UI e2e); Playwright/XCUITest stems in `skipped` |
+| `feature-light.json` | developer → build-verifier (`go test` / `go vet` / golangci-lint) |
+| `bugfix-standard.json` | debugger → developer (skipIf) → verifier → reviewer |
+
+**Never** schedule Playwright/XCUITest-only steps for this preset. Use `integration-test-*` (or QA with `e2e-only` = integration) for adapter-level coverage.
+
+## 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/go/team/fixtures/bugfix-standard.json

@@ -0,0 +1,37 @@
+{
+  "slug": "example-bugfix-standard",
+  "intent": "bugfix",
+  "profile": "standard",
+  "summary": "Regression fix with review",
+  "steps": [
+    {
+      "agent": "debugger",
+      "label": "Root cause"
+    },
+    {
+      "agent": "feature-developer",
+      "label": "Fix if needed",
+      "skipIf": "debugger.fixed"
+    },
+    {
+      "agent": "build-verifier",
+      "label": "go test / go vet / golangci-lint"
+    },
+    {
+      "agent": "code-reviewer",
+      "label": "Code review"
+    }
+  ],
+  "humanGates": [],
+  "autoChain": true,
+  "skipped": [
+    {
+      "agent": "playwright-test-planner",
+      "reason": "Go backend uses integration-test-* — not in this bugfix path"
+    },
+    {
+      "agent": "xcuitest-test-planner",
+      "reason": "Go backend uses integration-test-* — not in this bugfix path"
+    }
+  ]
+}

package/presets/cursor/go/team/fixtures/feature-full.json

@@ -0,0 +1,43 @@
+{
+  "slug": "example-feature-full",
+  "intent": "feature",
+  "profile": "full",
+  "summary": "Multi-layer Go use case with integration-test 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": "go test / go vet / golangci-lint", "model": "cheap" },
+    { "agent": "security-reviewer", "label": "Security review", "model": "strong" },
+    { "agent": "code-reviewer", "label": "Code review", "model": "cheap" },
+    { "agent": "qa-tester", "label": "Integration tests", "scope": "e2e-only" }
+  ],
+  "humanGates": ["after:task-analyst"],
+  "autoChain": true,
+  "skipped": [
+    {
+      "agent": "playwright-test-planner",
+      "reason": "Go backend uses integration-test-* — not Playwright"
+    },
+    {
+      "agent": "playwright-test-generator",
+      "reason": "Go backend uses integration-test-*"
+    },
+    {
+      "agent": "playwright-test-healer",
+      "reason": "Go backend uses integration-test-*"
+    },
+    {
+      "agent": "xcuitest-test-planner",
+      "reason": "Go backend uses integration-test-* — not XCUITest"
+    },
+    {
+      "agent": "xcuitest-test-generator",
+      "reason": "Go backend uses integration-test-*"
+    },
+    {
+      "agent": "xcuitest-test-healer",
+      "reason": "Go backend uses integration-test-*"
+    }
+  ]
+}

package/presets/cursor/go/team/fixtures/feature-light.json

@@ -0,0 +1,17 @@
+{
+  "slug": "example-feature-light",
+  "intent": "feature",
+  "profile": "light",
+  "summary": "Trivial single-package change with explicit AC",
+  "steps": [
+    { "agent": "feature-developer", "label": "Implement", "model": "cheap" },
+    { "agent": "build-verifier", "label": "go test / go vet / golangci-lint", "model": "cheap" }
+  ],
+  "humanGates": [],
+  "autoChain": true,
+  "skipped": [
+    { "agent": "task-analyst", "reason": "Explicit AC and single-package scope" },
+    { "agent": "code-reviewer", "reason": "Light profile — non-trivial module/service changes should use standard" },
+    { "agent": "qa-tester", "reason": "No integration-test AC" }
+  ]
+}

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

@@ -28,6 +28,13 @@ npx @bonesofspring/ai-rules init cursor --preset ios-swift
 
 Requestable (не always-on): `post-change-build`, `xcode-tooling`, `agent-team-*`, `code-review-mr`, `feature-delivery-workflow`, `reference-features`.
 
+## 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)
+
 ## Sync with Claude
 
 SoT = этот Cursor-пресет. После правок `.mdc` / agents / skills — обновить twin в `presets/claude/ios-swift/` **в том же PR**.

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/build-verifier.md

@@ -26,17 +26,26 @@ Never require yarn/`lint:js`/Playwright for iOS app work.
 
 ## Preset-structure validation (when scope is preset / packages/ai-rules)
 
-When validating **ios-swift preset** changes (or `scope: preset-structure-validation`), **also** run these checks and **FAIL** on any mismatch:
-
-1. **Chain fork check:** `hooks/chain-team-phases.sh` must **not** be byte-identical to `presets/cursor/next/hooks/chain-team-phases.sh` (Claude: vs `presets/claude/next/hooks/…`).
-2. **Forbidden handoff strings** in ios-swift `chain-team-phases.sh` (Cursor + Claude): `playwright-test-`, `playwright-agents`, `playwright-e2e`, `user-playwright`, `app/__tests__/e2e`, and positive yarn lint recipes (`lint:js` / `lint:css` as commands to run — negation prose alone is not enough; prefer zero occurrences).
-3. **Required handoff stems:** `AGENT_HANDOFF` must include `xcuitest-test-planner` (or generator/healer) and `build-verifier` text must mention `xcodebuild` or `post-change-build` / `xcode-tooling`.
-4. **Roster:** 21 agent stems; no `playwright-test-*` files under ios-swift `agents/`.
-5. **Token budget:** Cursor `alwaysApply: true` count ≤ 3; Claude rules without `paths:` === 3.
+When validating **ios-swift preset** changes (or `scope: preset-structure-validation` / `preset-artifacts-only`), **also** run these checks. Skip xcodebuild if there are **no** Swift app changes.
+
+### FAIL (all stacks + ios-specific)
+
+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. **Chain fork check:** `hooks/chain-team-phases.sh` must **not** be byte-identical to `presets/cursor/next/hooks/chain-team-phases.sh` (Claude: vs `presets/claude/next/hooks/…`).
+3. **Forbidden handoff strings** in ios-swift `chain-team-phases.sh` (Cursor + Claude): `playwright-test-`, `playwright-agents`, `playwright-e2e`, `user-playwright`, `app/__tests__/e2e`, and positive yarn lint recipes (`lint:js` / `lint:css` as commands to run — negation prose alone is not enough; prefer zero occurrences). See `preset-no-cross-stack-leakage.mdc`.
+4. **Required handoff stems:** `AGENT_HANDOFF` must include `xcuitest-test-planner` (or generator/healer) and `build-verifier` text must mention `xcodebuild` or `post-change-build` / `xcode-tooling`.
+5. **Roster:** 21 agent stems; no `playwright-test-*` files under ios-swift `agents/`.
+6. **Twin presence (hard):** Cursor rule change → Claude twin present **same PR** — **FAIL** if missing (next, ios-swift, and go).
+7. **Mapping / README:** `claude/ios-swift/rules/README.md` mapping table present; core→stack mapping documented when `_shared` consumers exist.
+8. **shared-core consumers:** if `_shared/core/**` changed, every matching `<!-- shared-core: … -->` consumer in this PR must be updated (or intentional fork documented).
+9. **Session-start body budget:** sum of the **3** intended always-on / session-start rule bodies ≤ **120** lines (stretch ≤100); do **not** include `**/README.md` — record in report.
+10. **Embed drift (soft by default):** `packages/ai-rules/scripts/check-shared-core-drift.sh`; `AI_RULES_DRIFT_FAIL=1` to enforce.
+11. **Dogfood (monorepo soft):** `packages/ai-rules/scripts/sync-dogfood-cursor.sh`; mass deletion without migration doc → risk / FAIL for maintainers.
 
 ### Soft rules (do not FAIL alone)
 
-- **AC-19 thin aliases:** `agent-team-intake` and similar thin requestable aliases may be &lt;15 body lines if they mirror next’s thin-alias pattern. Enforce ≥15 strictly on **domain** rules (navigation, persistence, security, modules, networking, UI).
+- **Thin aliases:** `agent-team-intake`, `technical-retro` may be &lt;15 body lines. Enforce ≥15 on **domain** rules (navigation, persistence, security, modules, networking, UI).
+- Embed vs lineage modes: `docs/PRESET-CONTRIBUTION.md`, `_shared/README.md`.
 
 ## Output
 

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

@@ -73,3 +73,7 @@ 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/ios-swift/agents/debugger.md

@@ -70,3 +70,7 @@ Update `status.json`:
 Handoff summary: root cause, recommended fix, files touched (if any), `fixApplied`.
 
 Do not perform formal code review or write XCUITest plans — those are separate agents.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

package/presets/cursor/ios-swift/agents/feature-developer.md

@@ -33,3 +33,7 @@ When copying from `next` into `ios-swift` (or another stack):
 ## On completion
 
 `status.json`: `currentAgent: feature-developer`, `state: completed`. Handoff by layer + gaps for verifier/reviewer. No formal code review.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

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.
@@ -71,3 +71,7 @@ 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/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.
@@ -70,3 +70,7 @@ 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/ios-swift/agents/qa-tester.md

@@ -63,3 +63,7 @@ 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/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.
@@ -15,3 +15,7 @@ You are a solution architect for **iOS Feature modules** (Presentation / Domain
 - Alternatives table + chosen design + risks; keep token-light.
 
 Handoff: architecture approved or awaiting gate → status update.
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

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

@@ -23,3 +23,7 @@ Ask only blocking questions (AC gaps, Feature scope, platforms, offline/auth, AP
 3. Update `status.json` → `awaiting_approval` if human gate after analyst.
 
 Do not invent architecture stacks (TCA, SwiftData, …) — frame «как в репо».
+
+## 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/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)

package/presets/cursor/ios-swift/agents/unit-test-generator.md

@@ -52,3 +52,7 @@ Update `status.json`:
   "updatedAt": "<ISO8601>"
 }
 ```
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.

package/presets/cursor/ios-swift/agents/unit-test-healer.md

@@ -51,3 +51,7 @@ Update `status.json`:
   "updatedAt": "<ISO8601>"
 }
 ```
+
+## Design guidance
+
+- Load `design-guidance` (rule stem) when assessing structure, smells, or pattern fit.