@bonesofspring/ai-rules 0.2.9 → 0.2.11

package/presets/cursor/ios-swift/rules/preset-no-cross-stack-leakage.mdc

@@ -17,7 +17,8 @@ alwaysApply: false
 
 - `next` must not require iOS-only agents/tooling (`xcuitest-*`, `xcodebuild` as required handoff, Keychain-only rules).
 - `ios-swift` must not ship Playwright handoffs or Next lint recipes as required commands.
-- `go` / `java` must not ship Playwright, XCUITest, Next lint recipes, or `xcodebuild`/`SwiftLint` as required handoffs.
+- `go` / `java` / `mcp-ts` must not ship Playwright, XCUITest, Next lint recipes, or `xcodebuild`/`SwiftLint` as required handoffs.
+- `mcp-ts` must not ship Go tool commands (`go test`, `go vet`, `golangci-lint`) or `integration-test-*` agents as required delivery gates.
 - Shared core must not embed stack paths (`app/src/**`, `Features/**`, `playwright`, `xcodebuild`).
 
 ## Forbidden in ios-swift hooks/agents (FAIL)
@@ -46,6 +47,18 @@ Shared backend-stack bans (both `go` and `java`):
 
 Required instead: `integration-test-*`; build-verifier / `post-change-test` plus stack tooling — `go-tooling` (`go test`, `go vet`) or `java-tooling` (`mvn test` / `./gradlew test`).
 
+## Forbidden in mcp-ts hooks/agents (FAIL)
+
+Same UI/mobile bans as backend stacks, plus:
+
+- `playwright-test-`, `playwright-agents`, `playwright-e2e`, `user-playwright`, `app/__tests__/e2e`
+- Positive yarn recipes `lint:js` / `lint:css` as required gates
+- `xcuitest-test-`, `xcodebuild`, `SwiftLint` as required handoffs
+- Go tool commands as required MCP delivery gates: `go test`, `go vet`, `golangci-lint`
+- Agent files: `playwright-test-*`, `xcuitest-test-*`, `integration-test-*`, `accessibility-reviewer`
+
+Required instead: package-manager–discovered typecheck/test (`mcp-ts-tooling`, `post-change-test`); Phase 1 gates `build-verifier` + `security-reviewer`.
+
 ## Soft / document
 
 - Mentioning the other stack in **docs** comparing presets is OK.
@@ -53,4 +66,4 @@ Required instead: `integration-test-*`; build-verifier / `post-change-test` plus
 
 ## Chain fork
 
-`hooks/chain-team-phases.sh` must differ **byte-wise** pairwise among `next`, `ios-swift`, `go`, and `java` (per platform).
+`hooks/chain-team-phases.sh` must differ **byte-wise** pairwise among `next`, `ios-swift`, `go`, `java`, and `mcp-ts` (per platform).

package/presets/cursor/ios-swift/rules/preset-token-budget.mdc

@@ -22,7 +22,7 @@ alwaysApply: false
 
 **Claude Option A (README exclusion):** when counting Claude rules without `paths:` / session-start, **exclude `**/README.md`** (topic indexes are not session-start rules). The intended session-start trio remains **exactly 3**; body budget sums **only those 3** rules.
 
-Session-start body budget (где задокументировано): ≤120 строк суммарно (stretch ≤100).
+Session-start body budget (где задокументировано): ≤140 строк суммарно (stretch ≤120).
 
 ## Meta / author rules
 

package/presets/cursor/ios-swift/rules/preset-twin-sync.mdc

@@ -21,6 +21,7 @@ Cursor `.mdc` — **SoT per stack**. Claude topic `.md` — derived twin.
 | `ios-swift` | `presets/cursor/ios-swift/rules/*.mdc` | `presets/claude/ios-swift/rules/<topic>/` | Keep in `claude/ios-swift/rules/README.md` |
 | `go` | `presets/cursor/go/rules/*.mdc` | `presets/claude/go/rules/<topic>/` | Keep in `claude/go/rules/README.md` |
 | `java` | `presets/cursor/java/rules/*.mdc` | `presets/claude/java/rules/<topic>/` | Keep in `claude/java/rules/README.md` |
+| `mcp-ts` | `presets/cursor/mcp-ts/rules/*.mdc` | `presets/claude/mcp-ts/rules/<topic>/` | Keep in `claude/mcp-ts/rules/README.md` |
 
 ## Same-PR checklist
 
@@ -40,5 +41,6 @@ Cursor `.mdc` — **SoT per stack**. Claude topic `.md` — derived twin.
 - **ios-swift:** missing Claude twin for a changed Cursor rule → **FAIL**.
 - **go:** missing Claude twin for a changed Cursor rule → **FAIL** (same as next / ios-swift; mapping table required).
 - **java:** missing Claude twin for a changed Cursor rule → **FAIL** (same as next / ios-swift / go; mapping table required).
+- **mcp-ts:** missing Claude twin for a changed Cursor rule → **FAIL** (same as next / ios-swift / go / java; mapping table required).
 
 Dogfood: sync packages → root `.cursor/` after Cursor SoT changes (not the reverse). Use `packages/ai-rules/scripts/sync-dogfood-cursor.sh`.

package/presets/cursor/java/README.md

@@ -10,7 +10,7 @@ npx @bonesofspring/ai-rules init cursor --preset java
 
 | Path | Role |
 |------|------|
-| `rules/*.mdc` | Cursor SoT (~32 stems); always-on trio ≤120 lines |
+| `rules/*.mdc` | Cursor SoT (~32 stems); always-on trio ≤140 lines |
 | `agents/` | 21 agents + README (no a11y / Playwright / XCUITest) |
 | `skills/` | 8 skills + README |
 | `commands/` | 5 slash commands |

package/presets/cursor/java/agents/build-verifier.md

@@ -30,7 +30,7 @@ Hard gates for the **java** stack:
 | Gate | FAIL when |
 |------|-----------|
 | **twin-map** | `java` missing from `STACKS`, or Cursor↔Claude orphan/missing twins |
-| **token-budget** | Cursor `alwaysApply` ≠ 3 or Claude session-start (excl. README) ≠ 3, or trio body sum > 120 |
+| **token-budget** | Cursor `alwaysApply` ≠ 3 or Claude session-start (excl. README) ≠ 3, or trio body sum > 140 |
 | **leakage** | `JAVA_FORBIDDEN_*` hits (Playwright/XCUITest/`lint:js`/`accessibility-reviewer` as required handoffs) |
 | **chain fork** | `hooks/chain-team-phases.sh` byte-identical to **next**, **ios-swift**, or **go** (same platform) |
 

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

@@ -8,13 +8,13 @@
 | `architecture-boundaries` | Hexagonal invariants |
 | `code-quality-and-refactoring` | Shared quality + Java notes |
 
-**Session-start body budget:** sum of the 3 always-on bodies ≤ **120** lines (stretch ≤100).
+**Session-start body budget:** sum of the 3 always-on bodies ≤ **140** lines (stretch ≤120).
 
 ## Twin depth (Cursor↔Claude)
 
 - **Domain** rules: target ≥15 non-empty body lines (FAIL soft when undocumented stubs).
 - **Thin aliases** (may be shorter): `agent-team-intake`, `technical-retro`.
-- **Documented stubs** (v1): `api-grpc`, `messaging-adapters` — catalog Depth=`stub`; bodies carry an in-file stub banner + when-to-use.
+- **Documented stubs** (v1): `api-grpc` — catalog Depth=`stub`; body carries stub banner + when-to-use. `messaging-adapters` expanded to **full** for dogfood J3.
 
 ## Loading strategy
 
@@ -78,7 +78,7 @@ Claude twins + Cursor→Claude map: `presets/claude/java/rules/README.md`. Cross
 | `composition-root` | full | Spring `@Configuration` + plain Java bootstrap |
 | `api-http` | full | Spring MVC/Jakarta; DTO validation/mapping |
 | `persistence-adapters` | full | JPA/JDBC; entities do not leak upward |
-| `messaging-adapters` | stub | optional; stub banner + when-to-use |
+| `messaging-adapters` | full | publisher/consumer, idempotency, ack/DLQ |
 | `module-public-api` | full | package/module boundaries |
 | `java-conventions` | full | records, exceptions, naming, no invented APIs |
 | `java-tooling` | full | requestable Maven/Gradle detect |
@@ -94,6 +94,6 @@ Claude twins + Cursor→Claude map: `presets/claude/java/rules/README.md`. Cross
 
 - Spring Boot hexagonal = public default; plain Java / Quarkus / Micronaut / Jakarta = documented variants
 - Layer-first single-module = default; multi-module = documented variant
-- gRPC/messaging = documented stubs in v1
+- gRPC = documented stub in v1; messaging adapters = full (broker-agnostic)
 - MCP = Context7 only
 - Static analysis = discover from repo/CI (no mandated Checkstyle/SpotBugs/Error Prone)

package/presets/cursor/java/rules/architecture-boundaries.mdc

@@ -24,6 +24,12 @@ alwaysApply: true
 - Domain never imports adapters or frameworks.
 - Cross-feature access — only via public ports / module API, not deep imports of another feature's internals.
 
+# Edit bundles (load on matching paths)
+
+- `**/domain/**` → `domain-layer`; `**/application/**` → `application-usecases` + `ports-interfaces`
+- Inbound HTTP/gRPC → `adapters-driving` + `api-http` / `api-grpc`; outbound persistence/messaging → `adapters-driven` + matching `*-adapters`
+- `**/configuration/**`, `*Application.java` → `composition-root`; after `*.java` edits → `post-change-test` (+ `java-tooling`)
+
 # Требование к агенту
 
 - Класть файлы в правильный слой; не «коротить» слои ради скорости.

package/presets/cursor/java/rules/messaging-adapters.mdc

@@ -1,5 +1,5 @@
 ---
-description: Messaging driven/driving adapters for Java hexagonal services (stub)
+description: Messaging driven/driving adapters for Java hexagonal services
 globs:
   - "**/adapters/outbound/messaging/**/*"
   - "**/adapters/inbound/messaging/**/*"
@@ -7,20 +7,26 @@ globs:
 alwaysApply: false
 ---
 
+# Messaging adapters
 
-# Messaging adapters (documented stub)
+- **Publisher** (driven): implements an outbound port; serializes application/domain events to wire format inside the adapter.
+- **Consumer** (driving): deserializes → maps to application/domain types → calls inbound port / use case; **ack/nack** (and commit) stays in the adapter.
+- Idempotency keys, retry, and DLQ/parking-lot policy are adapter (or infra) concerns — document at-least-once vs exactly-once assumptions at the port.
+- Use the broker client already present in the repo (`KafkaTemplate`, JMS, Spring Cloud Stream, etc.) — do not invent a second stack.
 
-> **Stub (v1):** Light guidance only — not a full Kafka/Rabbit/JMS cookbook. **When to use:** editing `adapters/**/messaging/**` or adding broker publishers/consumers. Prefer expanding this rule when the consumer repo standardizes on a broker.
+## Event shapes
 
-- **Publisher** (driven): implements outbound port; serializes domain events / integration events.
-- **Consumer** (driving): deserializes → calls use case / inbound port; ack/nack policy here.
-- Idempotency keys and retry/DLQ are adapter concerns; document at-least-once assumptions.
-- Do not put broker client types (`KafkaTemplate`, JMS sessions, etc.) in domain or application signatures.
+- Prefer explicit event types in application or a small `events` package used by ports.
+- Map wire DTOs ↔ application events **only** in the adapter; never pass `ConsumerRecord` / broker payloads into domain.
 
-## Event shapes
+## Forbidden
 
-- Prefer explicit event types in application or a small `events` package used by ports — map to wire format in the adapter.
+- Broker client types (`KafkaTemplate`, JMS sessions, `MessageListener`) in domain or application signatures.
+- Business rules inside listeners beyond mapping + calling one use case.
+- Silent catch-and-ack that drops poison messages without DLQ/metrics policy.
 
 ## Tests
 
-- Unit-test mapping with fakes; integration against embedded/broker Testcontainers when the repo has them.
+- Unit-test mapping and idempotency branches with fakes.
+- Integration against embedded broker / Testcontainers **when the repo already has that setup**.
+- After edits: `post-change-test` (+ `java-tooling`); agents `integration-test-*` when adding consumer contracts.

package/presets/cursor/java/rules/preset-no-cross-stack-leakage.mdc

@@ -17,7 +17,8 @@ alwaysApply: false
 
 - `next` must not require iOS-only agents/tooling (`xcuitest-*`, `xcodebuild` as required handoff, Keychain-only rules).
 - `ios-swift` must not ship Playwright handoffs or Next lint recipes as required commands.
-- `go` / `java` must not ship Playwright, XCUITest, Next lint recipes, or `xcodebuild`/`SwiftLint` as required handoffs.
+- `go` / `java` / `mcp-ts` must not ship Playwright, XCUITest, Next lint recipes, or `xcodebuild`/`SwiftLint` as required handoffs.
+- `mcp-ts` must not ship Go tool commands (`go test`, `go vet`, `golangci-lint`) or `integration-test-*` agents as required delivery gates.
 - Shared core must not embed stack paths (`app/src/**`, `Features/**`, `playwright`, `xcodebuild`).
 
 ## Forbidden in ios-swift hooks/agents (FAIL)
@@ -46,6 +47,18 @@ Shared backend-stack bans (both `go` and `java`):
 
 Required instead: `integration-test-*`; build-verifier / `post-change-test` plus stack tooling — `go-tooling` (`go test`, `go vet`) or `java-tooling` (`mvn test` / `./gradlew test`).
 
+## Forbidden in mcp-ts hooks/agents (FAIL)
+
+Same UI/mobile bans as backend stacks, plus:
+
+- `playwright-test-`, `playwright-agents`, `playwright-e2e`, `user-playwright`, `app/__tests__/e2e`
+- Positive yarn recipes `lint:js` / `lint:css` as required gates
+- `xcuitest-test-`, `xcodebuild`, `SwiftLint` as required handoffs
+- Go tool commands as required MCP delivery gates: `go test`, `go vet`, `golangci-lint`
+- Agent files: `playwright-test-*`, `xcuitest-test-*`, `integration-test-*`, `accessibility-reviewer`
+
+Required instead: package-manager–discovered typecheck/test (`mcp-ts-tooling`, `post-change-test`); Phase 1 gates `build-verifier` + `security-reviewer`.
+
 ## Soft / document
 
 - Mentioning the other stack in **docs** comparing presets is OK.
@@ -53,4 +66,4 @@ Required instead: `integration-test-*`; build-verifier / `post-change-test` plus
 
 ## Chain fork
 
-`hooks/chain-team-phases.sh` must differ **byte-wise** pairwise among `next`, `ios-swift`, `go`, and `java` (per platform).
+`hooks/chain-team-phases.sh` must differ **byte-wise** pairwise among `next`, `ios-swift`, `go`, `java`, and `mcp-ts` (per platform).

package/presets/cursor/java/rules/preset-token-budget.mdc

@@ -22,7 +22,7 @@ alwaysApply: false
 
 **Claude Option A (README exclusion):** when counting Claude rules without `paths:` / session-start, **exclude `**/README.md`** (topic indexes are not session-start rules). The intended session-start trio remains **exactly 3**; body budget sums **only those 3** rules.
 
-Session-start body budget (где задокументировано): ≤120 строк суммарно (stretch ≤100).
+Session-start body budget (где задокументировано): ≤140 строк суммарно (stretch ≤120).
 
 ## Meta / author rules
 

package/presets/cursor/java/rules/preset-twin-sync.mdc

@@ -21,6 +21,7 @@ Cursor `.mdc` — **SoT per stack**. Claude topic `.md` — derived twin.
 | `ios-swift` | `presets/cursor/ios-swift/rules/*.mdc` | `presets/claude/ios-swift/rules/<topic>/` | Keep in `claude/ios-swift/rules/README.md` |
 | `go` | `presets/cursor/go/rules/*.mdc` | `presets/claude/go/rules/<topic>/` | Keep in `claude/go/rules/README.md` |
 | `java` | `presets/cursor/java/rules/*.mdc` | `presets/claude/java/rules/<topic>/` | Keep in `claude/java/rules/README.md` |
+| `mcp-ts` | `presets/cursor/mcp-ts/rules/*.mdc` | `presets/claude/mcp-ts/rules/<topic>/` | Keep in `claude/mcp-ts/rules/README.md` |
 
 ## Same-PR checklist
 
@@ -40,5 +41,6 @@ Cursor `.mdc` — **SoT per stack**. Claude topic `.md` — derived twin.
 - **ios-swift:** missing Claude twin for a changed Cursor rule → **FAIL**.
 - **go:** missing Claude twin for a changed Cursor rule → **FAIL** (same as next / ios-swift; mapping table required).
 - **java:** missing Claude twin for a changed Cursor rule → **FAIL** (same as next / ios-swift / go; mapping table required).
+- **mcp-ts:** missing Claude twin for a changed Cursor rule → **FAIL** (same as next / ios-swift / go / java; mapping table required).
 
 Dogfood: sync packages → root `.cursor/` after Cursor SoT changes (not the reverse). Use `packages/ai-rules/scripts/sync-dogfood-cursor.sh`.

package/presets/cursor/mcp-ts/AGENTS.md

@@ -0,0 +1,25 @@
+# TypeScript MCP stack — Cursor agent team
+
+**Repo-root agents:** see [`AGENTS.md`](../../AGENTS.md) at the project root (cross-tool setup, commands, security, living conventions pointers).
+
+| Задача | Куда смотреть |
+|--------|----------------|
+| Новая work-задача | `/task` → `commands/task.md` + `agent-team-orchestrator.mdc` |
+| Фича end-to-end | skill `feature-delivery` + `feature-delivery-workflow.mdc` |
+| Стек и границы | `mcp-ts-app-core.mdc`, `mcp-server-boundaries.mdc` |
+| После правок TS | `post-change-test.mdc` (+ `mcp-ts-tooling.mdc`) |
+| Tool/schema design | `mcp-tool-design.mdc`, `mcp-contract-testing.mdc` |
+| Code review | skill `code-review` + `code-review-mr.mdc` |
+| Security | `security-mcp.mdc` + agent `security-reviewer` |
+
+## Install
+
+```bash
+npx @bonesofspring/ai-rules init cursor --preset mcp-ts
+```
+
+## Dogfood (Phase 1)
+
+1. `/task` — add a tool (schema → handler → register → test → package).
+2. Schema validation bug — unit tests + contract fixtures.
+3. Secrets / capability review — security-reviewer + `security-mcp`.

package/presets/cursor/mcp-ts/BUGBOT.md

@@ -0,0 +1,9 @@
+# Bugbot priorities — TypeScript MCP
+
+1. Monolithic `index.ts` mixing transport, registration, and handler logic.
+2. Tool schemas: Zod authoring vs JSON Schema protocol contract mismatch; inventing SDK APIs.
+3. Handlers accessing ambient secrets, arbitrary FS, or unbounded network.
+4. Registration without validation; duplicated schemas; unsafe error surfaces leaking internals.
+5. Missing unit/contract tests for schema + handler seams.
+6. Shipping active local server-under-dev in consumer `mcp.json` (Context7 only).
+7. Ignore Playwright / XCUITest / Next lint / Go tools as required gates — not this stack.

package/presets/cursor/mcp-ts/MCP.md

@@ -0,0 +1,37 @@
+# MCP (preset `mcp-ts`, Cursor)
+
+Копируется в `.cursor/mcp.json` при `ai-rules init cursor --preset mcp-ts`.
+
+## Servers (active in shipped config)
+
+| Name | Package | Зачем |
+|------|---------|--------|
+| `context7` | `@upstash/context7-mcp@3.2.5` (pinned in `mcp.json`) | Versioned docs for `@modelcontextprotocol/sdk` and related libraries |
+
+**No** Figma, browser automation, or Playwright MCP in this preset.
+
+### Upgrading Context7
+
+Shipped `mcp.json` pins `@upstash/context7-mcp@<version>` so `init` does not pull floating `latest` on every MCP start. To upgrade: bump the pin in both Cursor and Claude `mcp-ts/mcp.json`, note the version here, and smoke-check Context7 after dogfood sync.
+
+## Inactive example — local server under development
+
+> **INACTIVE — do not add to shipped `mcp.json` / `.mcp.json`.**
+> A server-under-development cannot be valid at preset install time. Keep this example in docs only until the package exists and the team explicitly opts in.
+
+```json
+{
+  "mcpServers": {
+    "my-mcp-server": {
+      "command": "node",
+      "args": ["dist/index.js"]
+    }
+  }
+}
+```
+
+Adjust `command`/`args` to the project's `bin` / `npx` entry after packaging. Prefer stdio for local Cursor/Claude use.
+
+Секреты в файл не кладём. Опционально: `CONTEXT7_API_KEY` в окружении.
+
+После init: Settings → MCP → включить серверы. `init` перезаписывает одноимённый MCP config.

package/presets/cursor/mcp-ts/README.md

@@ -0,0 +1,19 @@
+# Preset `mcp-ts` (Cursor)
+
+Installable guidance for **authoring TypeScript MCP servers** with `@modelcontextprotocol/sdk`.
+
+```bash
+npx @bonesofspring/ai-rules init cursor --preset mcp-ts
+```
+
+## Always-on trio
+
+1. `mcp-ts-app-core` — SDK boundary, layout, stdio-first entry
+2. `mcp-server-boundaries` — registration / handler / capability / lifecycle
+3. `code-quality-and-refactoring` — shared quality + TS MCP stack notes
+
+## Not this preset
+
+- Consumer-app wiring beyond Context7 docs MCP
+- Playwright / browser / Figma / UI a11y
+- Go/Java hexagonal layers or Next `app/src/**`

package/presets/cursor/mcp-ts/REPO_AGENTS.md

@@ -0,0 +1,49 @@
+# TypeScript MCP — agent instructions
+
+Cross-tool repo-root guide. Tool-specific maps stay under `.cursor/AGENTS.md` and `.claude/CLAUDE.md`.
+
+## Cross-tool setup
+
+- Treat this file as the **shared** entry for any agent (Cursor, Claude Code, or other).
+- Tool maps live in `.cursor/AGENTS.md` / `.claude/CLAUDE.md` when that tool is installed.
+- Install:
+
+```bash
+npx @bonesofspring/ai-rules init cursor --preset mcp-ts
+npx @bonesofspring/ai-rules init claude --preset mcp-ts
+```
+
+`init` overwrites this file from the preset (`REPO_AGENTS.md` → `AGENTS.md`). Living gotchas belong in `team/conventions.md`, not here.
+
+## Commands (test / typecheck / build)
+
+Discover the package manager from lockfile / `packageManager` (`mcp-ts-tooling`). Typical gates:
+
+| Gate | Typical command |
+|------|-----------------|
+| Typecheck | `tsc --noEmit` or project `typecheck` script |
+| Test | project `test` / `vitest` / `jest` script |
+| Build | project `build` / `tsc` as configured |
+| Package | validate `bin` / package entry for stdio server |
+
+After code edits: invoke **`post-change-test`** (requestable). Full gate: agent `build-verifier`.
+
+## Security basics
+
+- Do not commit secrets (tokens, `.env`, private keys).
+- Review destructive git before running; respect shell hooks.
+- Do not weaken CI or skip hooks unless the user explicitly asks.
+- Tool handlers must not log secrets or widen filesystem/network capability without AC.
+
+## Tool entry points
+
+| Tool | Map |
+|------|-----|
+| Cursor | `.cursor/AGENTS.md` (optional if Cursor not installed) |
+| Claude Code | `.claude/CLAUDE.md` (optional if Claude not installed) |
+
+Rules: `.cursor/rules/` or `.claude/rules/`. Skills: `.cursor/skills/` or `.claude/skills/`.
+
+## Living conventions
+
+Gotchas, local patterns, and team decisions: **`.cursor/team/conventions.md`** and/or **`.claude/team/conventions.md`** (fill after init).

package/presets/cursor/mcp-ts/agents/README.md

@@ -0,0 +1,21 @@
+# Agents (mcp-ts Phase 1)
+
+| Agent | Role |
+|-------|------|
+| `task-router` | Intent → `pipeline.json` |
+| `task-analyst` | brief + decomposition |
+| `solution-architect` | architecture.md |
+| `feature-developer` | contract→schema→handler→register→test→package |
+| `build-verifier` | typecheck/tests (+ preset-structure) |
+| `security-reviewer` | threat model / capabilities |
+
+Phase 2 adds parity agents (`contract-test-*`, `code-reviewer`, `codebase-analyzer`, `debugger`, …) — **do not** schedule them as required handoffs in Phase 1.
+
+## Review-only (Phase 1)
+
+| Diff kind | Pipeline |
+|-----------|----------|
+| Tools / auth / secrets / capabilities | `security-reviewer` → parent skill `code-review` → `review.md` |
+| Schema / style only | Parent skill `code-review` only (`security-reviewer` in `skipped`) |
+
+There is **no** `code-reviewer` agent until Phase 2.

package/presets/cursor/mcp-ts/agents/build-verifier.md

@@ -0,0 +1,39 @@
+---
+name: build-verifier
+description: Validation gate specialist. Runs repository-discovered typecheck/tests after MCP implementation; writes validation-report.md. Never fixes app source. For preset packaging tasks, also validates mcp-ts preset structure gates.
+readonly: false
+model: fast
+---
+
+You are the build verifier for **TypeScript MCP servers** (and for **ai-rules preset packaging** when scope says so).
+
+## Consumer MCP repos
+
+1. Discover package manager (`mcp-ts-tooling`).
+2. Run typecheck (`tsc --noEmit` or project script).
+3. Run tests (project `test` / Vitest / Jest / scoped).
+4. Optional Inspector smoke — not required.
+5. Write `.cursor/team/tasks/<slug>/validation-report.md` with commands + results.
+6. On failure: set status `validation_failed` — do **not** patch production code.
+
+**Never** require Playwright, XCUITest, `lint:js`/`lint:css`, `xcodebuild`/`SwiftLint`, or Go tools (`go test` / `go vet` / `golangci-lint`) as the MCP gate.
+
+## Preset-structure validation (when editing `packages/ai-rules/presets/**`)
+
+From `packages/ai-rules/`:
+
+```bash
+yarn check:preset-structure
+```
+
+Hard gates: twin-map (stacks include **mcp-ts**), token-budget (alwaysApply/session-start = 3), leakage (`MCP_TS_FORBIDDEN_IN_CHAIN`, `MCP_TS_FORBIDDEN_AGENT_STEMS`, chain forks mcp-ts≠next≠ios-swift≠go≠java), shared-core drift (`AI_RULES_DRIFT_FAIL=1` via `check:preset-structure`).
+
+Document PASS/FAIL in `validation-report.md`. Soft leakage output:
+
+- **Negation** of forbidden stems in agents → suppressed (INFO count). **Not** a merge blocker.
+- **WARN** only for non-negation packaging mentions in this verifier (and rare chain-skip WARNs). Do not treat INFO/WARN counts as FAIL.
+
+1. **Root AGENTS template:** each installable preset (`cursor|claude` × `next|ios-swift|go|java|mcp-ts`) must ship `REPO_AGENTS.md` when validating preset packaging → **FAIL** if missing.
+2. **Hooks cookbook:** default `hooks.json` must **not** reference `hooks/examples/` → **FAIL** if it does.
+3. **Forbidden agent filenames** (Playwright / XCUITest / integration-test / accessibility-reviewer / contract-test): must be absent → **FAIL** via `check:preset-leakage`.
+4. **Rule eval (WARN):** optional maintainer smoke — not part of default `check:preset-structure`.

package/presets/cursor/mcp-ts/agents/feature-developer.md

@@ -0,0 +1,47 @@
+---
+name: feature-developer
+description: Feature implementation specialist for TypeScript MCP servers. Implements tasks from decomposition.md following feature-delivery workflow. Use after brief approval or when explicitly asked to implement an approved task slug.
+readonly: false
+---
+
+Implement MCP server features following **mcp-ts** boundaries.
+
+## Mandatory flow
+
+1. **Contract** — finalize name/description/input/output (`mcp-tool-design`).
+2. **Schema** — Zod authoring + JSON Schema-compatible registration (`mcp-ts-conventions`).
+3. **Handler** — validated inputs → scoped capability → safe errors.
+4. **Registration** — wire modules; keep `src/index.ts` lifecycle-only.
+5. **Unit / contract verification** — schema + handler tests (`tests-unit`, `mcp-contract-testing`).
+6. **Package validation** — typecheck/test via `post-change-test` (+ `mcp-ts-tooling`); Inspector smoke optional.
+
+## Order
+
+1. Read `feature-delivery-workflow.mdc`, `mcp-server-boundaries.mdc`, `reference-features.mdc`.
+2. After `*.ts` edits: invoke `post-change-test.mdc` (+ `mcp-ts-tooling.mdc`).
+
+## Do / Don't
+
+- **Do** keep registration, validation, and handlers separable.
+- **Do** use `// VERIFY: @modelcontextprotocol/sdk @ <version>` when inventing SDK calls would be risky.
+- **Don't** require Playwright, XCUITest, Next lint, or Go tools as gates.
+- **Don't** register a server-under-dev into shipped consumer `mcp.json`.
+
+## Zero improvisation
+
+- Implement **only** what the brief / AC / current decomposition task require.
+- If requirements are ambiguous — **ask** before coding.
+- Forbidden without explicit AC: unrelated security hardening, extra validation, drive-by refactors, new config/env.
+- Boy scout / `design-guidance` improvements stay **within** touched files.
+
+## Will / Will not
+
+**Will:** follow contract→schema→handler→register→test→package; add required unit tests; run `post-change-test`; update task artifacts.
+
+**Will not:** formal code review; invent AC; pull Next/iOS/Go gates; auto-continue past human gates.
+
+## Design guidance / anti-sycophancy
+
+- Load `design-guidance` and `anti-sycophancy-discipline` when writing or changing code.
+
+Update `.cursor/team/tasks/<slug>/status.json` when done.

package/presets/cursor/mcp-ts/agents/security-reviewer.md

@@ -0,0 +1,21 @@
+---
+name: security-reviewer
+description: Security review specialist for TypeScript MCP servers. Audits tool capabilities, prompt-injection boundaries, secrets/redaction, path/SSRF risks. Readonly — writes security-review.md only.
+readonly: false
+---
+
+Review MCP diffs against `security-mcp.mdc` and `mcp-auth-secrets.mdc`.
+
+## Focus
+
+- Capability minimization (FS/network/shell)
+- Schema validation before side effects
+- Secrets in repo/logs/tool results
+- Path traversal / SSRF allowlists
+- Fail-closed auth for remote transports
+
+## Output
+
+`.cursor/team/tasks/<slug>/security-review.md`. Do not edit production code.
+
+Never require Keychain/ATS/iOS-only or browser CSP checklists as the primary MCP review.

package/presets/cursor/mcp-ts/agents/solution-architect.md

@@ -0,0 +1,23 @@
+---
+name: solution-architect
+description: Solution architect for TypeScript MCP servers. Designs tool/resource/prompt contracts, transport/auth choices, and module boundaries before implementation. Readonly design docs — not production code.
+readonly: false
+---
+
+Design MCP server changes for **mcp-ts**.
+
+## Deliverable
+
+Write `architecture.md` covering:
+
+- Contract surface (names, schemas, versioning)
+- Module boundaries (entry / registration / handler / capability)
+- Transport default (stdio) and any remote/auth decisions
+- Test strategy (unit + contract fixtures; Inspector optional)
+- Explicit non-goals (no UI, no browser automation)
+
+## Constraints
+
+- Follow `mcp-server-boundaries` and `mcp-tool-design`.
+- Do not invent SDK APIs — mark VERIFY or research via Context7.
+- Do not introduce Go/Java hexagonal prescriptions unless the repo already uses them.

package/presets/cursor/mcp-ts/agents/task-analyst.md

@@ -0,0 +1,25 @@
+---
+name: task-analyst
+description: Task analysis specialist. Clarifies requirements, validates acceptance criteria, and decomposes work into concrete tasks. Use for /feature-start, task intake, or when the user asks to analyze or decompose a feature before coding. Writes only team artifacts; never writes production code.
+readonly: false
+---
+
+Analyze MCP server work requests for the **mcp-ts** preset.
+
+## Deliverables
+
+1. `brief.md` — goal, AC, out of scope, assumptions, risks.
+2. `decomposition.md` — ordered tasks (contract → schema → handler → register → test → package).
+3. Update `status.json` (`awaiting_approval` when human gate applies).
+
+## Focus
+
+- Tool/resource/prompt contracts and capability scope.
+- Zod/JSON Schema obligations; stdio vs remote transport needs.
+- Security/capability questions early for FS/network tools.
+
+## Will not
+
+- Implement production code.
+- Schedule Phase 2-only agents.
+- Prescribe Go hexagonal or Next app layers.

package/presets/cursor/mcp-ts/agents/task-router.md

@@ -0,0 +1,73 @@
+---
+name: task-router
+description: Task routing specialist. Analyzes user prompt, detects intent, and writes pipeline.json with ordered agent steps. Use first for /task or when determining which subagents to run and in what order. No production code — writes team artifacts only.
+readonly: false
+model: fast
+---
+
+You are a task router for a **TypeScript MCP server** agent team. You **do not** implement tasks — you classify intent and plan the agent pipeline.
+
+## Inputs
+
+- User task description (from `/task` or orchestrator).
+- Optional: existing files under `.cursor/team/tasks/<slug>/`.
+- Pipeline JSON schema — **`agents/README.md`**.
+
+## Intent detection (Phase 1 roster)
+
+| intent | Signals | Default steps |
+|--------|---------|---------------|
+| `feature` | «добавь tool», «новая», «реализуй», schema/handler | task-analyst → feature-developer → build-verifier → **security-reviewer** when [sensitive](#security-reviewer-routing); else document skip |
+| `bugfix` | «баг», «fix», «не работает», «падает» | task-analyst → feature-developer → build-verifier → **security-reviewer** when [sensitive](#security-reviewer-routing); else document skip |
+| `review-only` | «ревью», «review MR», «проверь diff» | `security-reviewer` for threat/capability/auth/secrets diffs; **plus** parent applies skill `code-review` (write `review.md`) — no `code-reviewer` agent in Phase 1. Pure schema/style-only diffs: skip security step, parent skill only (document in `skipped`) |
+| `spike` | «исследуй», «spike», proof of concept | task-analyst → solution-architect |
+| `refactor` | «рефакторинг», «без изменения поведения» | task-analyst → feature-developer → build-verifier → **security-reviewer** when [sensitive](#security-reviewer-routing); else document skip |
+| `retro` | «ретро», «postmortem» | (orchestrator → `/technical-retro`) |
+
+### Security-reviewer routing
+
+Append **`security-reviewer` after `build-verifier`** for `feature` / `bugfix` / `refactor` when **any** of:
+
+- Diff touches `auth/**`, secrets/config (`.env*`, `**/secrets/**`), or stems `security-mcp` / `mcp-auth-secrets`
+- Tool FS/network capability changes (new or widened allowlists, adapters, SSRF surface)
+- User signals auth, secrets, bearer/OAuth, or capability expansion
+
+**Documented skip only** for proven schema/style-only changes (no auth/secrets/capability). Put `security-reviewer` in `skipped` with that reason — never silent omit.
+
+**`profile: light` is invalid** when FS/net/auth expands — use `standard`/`full` and include `security-reviewer`.
+
+**Phase 1 available agents only:** `task-router`, `task-analyst`, `solution-architect`, `feature-developer`, `build-verifier`, `security-reviewer`.
+
+**Never schedule** Playwright (`playwright-test-*`), XCUITest (`xcuitest-test-*`), `accessibility-reviewer`, `integration-test-*`, or Phase 2 `contract-test-*`. Put them in `skipped` with reason «mcp-ts Phase 1 roster».
+
+## Pipeline profiles
+
+`"profile": "full" | "standard" | "light"`. Default: **standard** for feature/refactor/bugfix; **light** for tiny single-file fixes with **no** FS/net/auth expansion.
+
+**Never skip `build-verifier`** after developer when TypeScript sources changed.
+
+## Model tiers (`steps[].model`)
+
+Optional: `"model": "cheap" | "standard" | "strong"`.
+
+- `light` → `cheap` on all steps
+- security-sensitive / spike architect → `strong` on those steps
+- never `strong` on build-verifier / task-router
+
+Fixtures: `.cursor/team/fixtures/` (feature-full, feature-light, bugfix-standard).
+
+## humanGates (defaults)
+
+| Intent | Default humanGates |
+|--------|-------------------|
+| feature, refactor | `["after:task-analyst"]` |
+| spike | `["after:solution-architect"]` |
+| bugfix, review-only | `[]` |
+
+## Output
+
+Write `.cursor/team/tasks/<slug>/pipeline.json` and initial `status.json` via the **Write** tool; set `.cursor/team/active-task.json`.
+
+## Handoff
+
+Intent + steps table + skipped + gates → invoke `steps[0].agent` (unless retro).