@bonesofspring/ai-rules 0.2.14 → 0.2.16

package/presets/claude/android-kotlin/team/README.md

@@ -0,0 +1,54 @@
+# Agent team artifacts (android-kotlin)
+
+Artifact directory for the Android agent-team pipeline.
+
+## Layout
+
+```
+.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` = **Android instrumentation** |
+| `feature-light.json` | developer → build-verifier |
+| `bugfix-standard.json` | debugger → developer (skipIf) → verifier → reviewer |
+
+### `skipped[]` in fixtures
+
+`pipeline.json` / fixture `skipped` is **documentation of forbidden or non-applicable template stems** from other stacks (Playwright, XCUITest, JVM `integration-test-*`) — **not** agents that ran and were skipped at runtime, and **not** steps to schedule. Routers must never promote these stems into `steps[]`. For UI-test-only intents use `instrumentation-test-*`.
+
+**Never** schedule Playwright-only steps without skip rationale. Use `instrumentation-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).
+
+## Artifact manifest and receipts
+
+Each slug stores one context index at `.claude/team/tasks/<slug>/artifact-manifest.json`. Schema v1 is defined by shared core `agent-team/agent-artifact-contracts.md`: every entry declares its producer, status, authoritative paths, acceptance-criteria IDs, decomposition task IDs, timestamps, and a terminal completion receipt.
+
+Producer/consumer rules:
+
+- Read the manifest first and use only the authoritative inputs needed by the current step; fall back to `brief.md`, `decomposition.md`, and `pipeline.json` when it is missing or stale, and report that gap.
+- Producers upsert only their stable entry IDs, preserve foreign entries, and finish with `completed`, `blocked`, `changes_requested`, or `validation_failed` receipt evidence.
+- The router owns `pipeline.json` and its routing entry; analyst, developer, verifier, and reviewer own their named outputs and receipts. Consumers do not edit another producer's receipt.
+- Agents do not mutate `status.json` or `metrics.json`. The orchestration runtime/hook is their single writer. Parallel receipt merges are serialized by the parent/orchestrator.
+
+## Local metrics ledger
+
+`metrics.json` is an append-only schema-v1 event ledger for one task run. It contains only allowlisted IDs, task dimensions, timestamps, outcomes, and attribution confidence—never prompts, secrets, file paths, or contents. The orchestration runtime writes `task_started` / `attempt_started`; the hook records host-clock completion and human-gate edges under a per-task lock with temp-and-rename.
+
+`status.json.activeAttempts` is a transient timing bridge keyed by `attemptId`; `lastCompletedAttempt` is diagnostic; `parallelOutcomes` holds per-agent outcomes for the current parallel join until the step advances. For parallel stops, the hook must use a stable payload identity or the sole active attempt. Otherwise an explicit `.metrics-receipts.json` receipt is fallback data marked `source: agent`, `attributionConfidence: fallback`; it must never guess from `currentAgent`.
+
+Aggregate with `node packages/ai-rules/scripts/aggregate-agent-task-metrics.mjs --team-root .claude/team`. It reports role/agent count, completed count, total/average duration, distinct completed run IDs, separate human-gate wait, and incomplete artifacts.

package/presets/claude/android-kotlin/team/conventions.md

@@ -0,0 +1,17 @@
+# Team conventions (consumer-local)
+
+After installing this preset, document **local** names and paths here. Do not put vendor/brand names into the shared preset packages.
+
+## Suggested entries
+
+| Concern | Local name / path |
+|---------|-------------------|
+| ViewModel base class | _(fill)_ |
+| Feature DI holder / component types | _(fill)_ |
+| Design-system package | _(fill)_ |
+| App shell module(s) under `applications/` | _(fill)_ |
+| Default product flavor / variant for local builds | _(fill)_ |
+| Instrumentation test base / robot pattern | _(fill)_ |
+| Documented Gradle wrapper (if not `./gradlew`) | _(fill)_ |
+
+Keep this file consumer-owned; `ai-rules init` may overwrite other preset files but conventions are meant to accumulate local decisions.

package/presets/claude/android-kotlin/team/fixtures/bugfix-standard.json

@@ -0,0 +1,47 @@
+{
+  "slug": "example-bugfix-standard",
+  "intent": "bugfix",
+  "profile": "standard",
+  "summary": "Bugfix with unit coverage and optional instrumentation",
+  "steps": [
+    {
+      "agent": "task-analyst",
+      "label": "Clarify repro and AC"
+    },
+    {
+      "agent": "debugger",
+      "label": "Reproduce and locate root cause"
+    },
+    {
+      "agent": "feature-developer",
+      "label": "Minimal fix + unit test",
+      "scope": "unit-in-dev"
+    },
+    {
+      "agent": "build-verifier",
+      "label": "Gradle compile + lint + unit smoke",
+      "model": "cheap"
+    },
+    {
+      "agent": "code-reviewer",
+      "label": "Code review",
+      "model": "cheap"
+    }
+  ],
+  "humanGates": [],
+  "autoChain": true,
+  "skipped": [
+    {
+      "agent": "playwright-test-planner",
+      "reason": "Android uses instrumentation-test-*"
+    },
+    {
+      "agent": "xcuitest-test-planner",
+      "reason": "iOS-only"
+    },
+    {
+      "agent": "instrumentation-test-planner",
+      "reason": "No UI AC \u2014 add if regression is UI-only"
+    }
+  ]
+}

package/presets/claude/android-kotlin/team/fixtures/feature-full.json

@@ -0,0 +1,97 @@
+{
+  "slug": "example-feature-full",
+  "intent": "feature",
+  "profile": "full",
+  "summary": "Multi-layer feature with Android instrumentation 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": "Gradle compile + lint + unit smoke",
+      "model": "cheap"
+    },
+    {
+      "agent": "security-reviewer",
+      "label": "Security review",
+      "model": "strong"
+    },
+    {
+      "agent": "code-reviewer",
+      "label": "Code review",
+      "model": "cheap"
+    },
+    {
+      "agent": "accessibility-reviewer",
+      "label": "Compose a11y",
+      "model": "cheap"
+    },
+    {
+      "agent": "instrumentation-test-planner",
+      "label": "Plan instrumentation UI tests"
+    },
+    {
+      "agent": "instrumentation-test-generator",
+      "label": "Generate instrumentation tests"
+    },
+    {
+      "agent": "instrumentation-test-healer",
+      "label": "Heal flaky instrumentation",
+      "model": "cheap"
+    }
+  ],
+  "humanGates": [
+    "after:task-analyst"
+  ],
+  "autoChain": true,
+  "skipped": [
+    {
+      "agent": "playwright-test-planner",
+      "reason": "Android uses instrumentation-test-* \u2014 not Playwright"
+    },
+    {
+      "agent": "playwright-test-generator",
+      "reason": "Android uses instrumentation-test-*"
+    },
+    {
+      "agent": "playwright-test-healer",
+      "reason": "Android uses instrumentation-test-*"
+    },
+    {
+      "agent": "xcuitest-test-planner",
+      "reason": "iOS-only"
+    },
+    {
+      "agent": "xcuitest-test-generator",
+      "reason": "iOS-only"
+    },
+    {
+      "agent": "xcuitest-test-healer",
+      "reason": "iOS-only"
+    },
+    {
+      "agent": "integration-test-planner",
+      "reason": "JVM backend pattern \u2014 not Android UI"
+    },
+    {
+      "agent": "integration-test-generator",
+      "reason": "JVM backend pattern"
+    },
+    {
+      "agent": "integration-test-healer",
+      "reason": "JVM backend pattern"
+    }
+  ]
+}

package/presets/claude/android-kotlin/team/fixtures/feature-light.json

@@ -0,0 +1,38 @@
+{
+  "slug": "example-feature-light",
+  "intent": "feature",
+  "profile": "light",
+  "summary": "Trivial single-file change with explicit AC",
+  "steps": [
+    {
+      "agent": "feature-developer",
+      "label": "Implement",
+      "model": "cheap"
+    },
+    {
+      "agent": "build-verifier",
+      "label": "Gradle compile + 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 \u2014 non-trivial app changes should use standard"
+    },
+    {
+      "agent": "instrumentation-test-planner",
+      "reason": "No UI AC"
+    },
+    {
+      "agent": "playwright-test-planner",
+      "reason": "Android uses instrumentation-test-*"
+    }
+  ]
+}

package/presets/claude/go/MCP.md

@@ -1,16 +1,16 @@
 # MCP (preset `go`, Claude)
 
-Копируется в `.mcp.json` при `ai-rules init claude --preset go`.
+Copied to `.mcp.json` on `ai-rules init claude --preset go`.
 
 ## Servers
 
-| Name | Package | Зачем |
+| Name | Package | Why |
 |------|---------|--------|
-| `context7` | `@upstash/context7-mcp` | Актуальная документация Go / stdlib / популярных библиотек |
-| `figma` | remote `https://mcp.figma.com/mcp` | Design context при необходимости; OAuth в Claude |
+| `context7` | `@upstash/context7-mcp` | Up-to-date Go / stdlib / popular library docs |
+| `figma` | remote `https://mcp.figma.com/mcp` | Design context when needed; OAuth in Claude |
 
-Browser e2e MCP (Playwright / Chrome DevTools) **не** входят в go-пресет.
+Browser e2e MCP (Playwright / Chrome DevTools) are **not** part of the go preset.
 
-Секреты в файл не кладём. Опционально: `CONTEXT7_API_KEY` в окружении. Figma — OAuth (токен не коммитим).
+Do not put secrets in the file. Optional: `CONTEXT7_API_KEY` in the environment. Figma — OAuth (do not commit the token).
 
-После init: Claude Code MCP → включить серверы. `init` перезаписывает одноимённый `mcp.json`.
+After init: Claude Code MCP → enable servers. `init` overwrites the same-named `mcp.json`.

package/presets/claude/go/README.md

@@ -8,12 +8,12 @@ Derived twin of `presets/cursor/go/`. Mapping: [`rules/README.md`](./rules/READM
 npx @bonesofspring/ai-rules init claude --preset go
 ```
 
-| Path | Содержание |
+| Path | Contents |
 |------|------------|
 | `CLAUDE.md` | Thin session entry |
 | `rules/**` | Topic `.md` + `paths:` (session-start = 3) |
-| `agents/**` | **21** ролей (+ `codebase-analyzer`) |
-| `skills/**` | **7** skills (в т.ч. `integration-testing`) |
+| `agents/**` | **21** roles (+ `codebase-analyzer`) |
+| `skills/**` | **7** skills (incl. `integration-testing`) |
 | `commands/**` | task, task-continue, feature-start/continue, technical-retro |
 | `hooks/**` | guard-shell + chain-team-phases |
 | `team/**` | fixtures + README |

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

@@ -1,10 +1,10 @@
 # `.claude/agents` (preset go)
 
-Ролевые subagents для командного пайплайна Claude Code (Go hexagonal).
+Role subagents for the Claude Code agent-team pipeline (Go hexagonal).
 
 ## Analysis (on-demand)
 
-| Agent | Файл | Production-код |
+| Agent | File | Production code |
 |-------|------|----------------|
 | Codebase analyzer | `codebase-analyzer.md` | no (explain-as-is only) |
 

package/presets/claude/go/agents/task-router.md

@@ -17,21 +17,21 @@ You are a task router for a **Go hexagonal backend** agent team. You **do not**
 
 | intent | Signals | Default steps |
 |--------|---------|---------------|
-| `feature` | «добавь», «новая», «реализуй», use case/API/adapter | task-analyst → feature-developer → build-verifier → code-reviewer → qa-tester or **integration-test** trio when adapter AC |
-| `bugfix` | «баг», «fix», «не работает», «падает» | debugger → feature-developer (skipIf debugger.fixed) → build-verifier → code-reviewer |
-| `ci-fix` | «CI», «красный PR», «failing check» | ci-investigator → feature-developer (skipIf resolved) → build-verifier → code-reviewer |
-| `migration` | «миграция», «upgrade», «обнови Go/module» | task-analyst → migration-specialist → feature-developer → build-verifier → code-reviewer |
-| `perf-audit` | «производительность», «pprof», «медленно» | performance-auditor |
-| `review-only` | «ревью», «review MR», «проверь diff» | code-reviewer |
-| `test-only` | «покрой тестами» (unit+integration, no impl) | task-analyst → qa-tester |
-| `unit-only` | «unit», «юнит», «покрой use case» | unit-test-planner → unit-test-generator, or unit-test-healer |
+| `feature` | «добавь» (add), «новая» (new), «реализуй» (implement), use case/API/adapter | task-analyst → feature-developer → build-verifier → code-reviewer → qa-tester or **integration-test** trio when adapter AC | <!-- i18n-keep: E4 -->
+| `bugfix` | «баг» (bug), «fix», «не работает» (doesn't work), «падает» (crashes) | debugger → feature-developer (skipIf debugger.fixed) → build-verifier → code-reviewer | <!-- i18n-keep: E4 -->
+| `ci-fix` | «CI», «красный PR» (red PR), «failing check» | ci-investigator → feature-developer (skipIf resolved) → build-verifier → code-reviewer | <!-- i18n-keep: E4 -->
+| `migration` | «миграция» (migration), «обнови Go/module» (upgrade), "update Go/module" | task-analyst → migration-specialist → feature-developer → build-verifier → code-reviewer | <!-- i18n-keep: E4 -->
+| `perf-audit` | «производительность» (performance), «pprof», «медленно» (slow) | performance-auditor | <!-- i18n-keep: E4 -->
+| `review-only` | «ревью» (review), «проверь diff» (review MR), "check diff" | code-reviewer | <!-- i18n-keep: E4 -->
+| `test-only` | «покрой тестами» (cover with tests), (unit+integration, no impl) | task-analyst → qa-tester | <!-- i18n-keep: E4 -->
+| `unit-only` | «юнит» (unit), «покрой use case» (cover use case) | unit-test-planner → unit-test-generator, or unit-test-healer | <!-- i18n-keep: E4 -->
 | `e2e-only` / integration | «integration», «e2e», «httptest», «testcontainers» | **integration-test-planner** → **integration-test-generator**, or **integration-test-healer** |
-| `docs-only` | «документация», «README», «changelog» | task-analyst → tech-writer |
-| `refactor` | «рефакторинг», «без изменения поведения» | task-analyst → feature-developer → build-verifier → code-reviewer |
-| `spike` | «исследуй», «spike», proof of concept | task-analyst → solution-architect |
-| `retro` | «ретро», «postmortem» | (orchestrator → `/technical-retro`) |
+| `docs-only` | «документация» (docs), "README", "changelog" | task-analyst → tech-writer | <!-- i18n-keep: E4 -->
+| `refactor` | «рефакторинг» (refactor), «без изменения поведения» (no behavior change) | task-analyst → feature-developer → build-verifier → code-reviewer | <!-- i18n-keep: E4 -->
+| `spike` | «исследуй» (explore), "spike", proof of concept | task-analyst → solution-architect | <!-- i18n-keep: E4 -->
+| `retro` | «ретро» (retro), "postmortem" | (orchestrator → `/technical-retro`) | <!-- i18n-keep: E4 -->
 
-**Never schedule** Playwright (`playwright-test-*`), XCUITest (`xcuitest-test-*`), or `accessibility-reviewer`. Put them in `skipped` with reason «Go backend uses integration-test trio».
+**Never schedule** Playwright (`playwright-test-*`), XCUITest (`xcuitest-test-*`), or `accessibility-reviewer`. Put them in `skipped` with reason "Go backend uses integration-test trio".
 
 ## Pipeline profiles
 

package/presets/claude/go/commands/README.md

@@ -1,13 +1,13 @@
 # `.claude/commands` (preset go)
 
-Определения slash-команд и on-demand сценариев. Копируются в `.claude/commands/` при `ai-rules init claude --preset go`.
+Slash-command and on-demand scenario definitions. Copied to `.claude/commands/` on `ai-rules init claude --preset go`.
 
-| Файл | Назначение |
+| File | Purpose |
 |------|------------|
-| `task.md` | Единая точка входа: router → dynamic pipeline → первый agent |
-| `task-continue.md` | Продолжение после human gate / паузы по `pipeline.json` |
-| `feature-start.md` | Legacy analyst-only старт без router |
-| `feature-continue.md` | Legacy продолжение; для `pipeline.json` делегирует смысл `/task-continue` |
-| `technical-retro.md` | Фасилитация технического ретро, включая блок «Работа агентов» |
+| `task.md` | Single entry point: router → dynamic pipeline → first agent |
+| `task-continue.md` | Continue after human gate / pause per `pipeline.json` |
+| `feature-start.md` | Legacy analyst-only start without router |
+| `feature-continue.md` | Legacy continue; for `pipeline.json` delegates to `/task-continue` semantics |
+| `technical-retro.md` | Facilitate a technical retro, including the “Agent work” block |
 
-См. также корневой `README.md` пресета — у Claude Code помимо `rules/` и `commands/` используются `skills/`, `agents/`, `hooks/`, `team/`.
+See also the preset root `README.md` — Claude Code also uses `skills/`, `agents/`, beyond `rules/` and `commands/`; `hooks/`, `team/`.

package/presets/claude/go/commands/feature-continue.md

@@ -3,25 +3,25 @@ name: feature-continue
 description: Legacy alias for /task-continue that resumes a feature pipeline after human approval or pause.
 ---
 
-# Feature continue — продолжение после утверждения brief
+# Feature continue — resume after brief approval
 
-Legacy-команда для продолжения после human gate. Для новых пайплайнов с `pipeline.json` используй те же правила, что в `/task-continue`.
+Legacy command to continue after a human gate. For new pipelines with `pipeline.json`, use the same rules as `/task-continue`.
 
-## Аргументы
+## Arguments
 
-`<slug>` — идентификатор задачи из `.claude/team/tasks/<slug>/`.
+`<slug>` — task id under `.claude/team/tasks/<slug>/`.
 
 ## Preconditions
 
-1. Прочитай `.claude/team/tasks/<slug>/brief.md` и `decomposition.md`.
-2. Если есть `pipeline.json`, делегируй поведение `/task-continue <slug>`.
-3. Если `pipeline.json` нет, прочитай `status.json`. Продолжай только если:
+1. Read `.claude/team/tasks/<slug>/brief.md` and `decomposition.md`.
+2. If `pipeline.json` exists, delegate behavior to `/task-continue <slug>`.
+3. If there is no `pipeline.json`, read `status.json`. Continue only if:
    - `phase` is `analysis` and `state` is `awaiting_approval` (user explicitly approved via this command), **or**
    - `phase` is `development`/`review`/`testing` and work should resume.
 
-## Legacy алгоритм без `pipeline.json`
+## Legacy algorithm without `pipeline.json`
 
-1. Обнови `status.json`:
+1. Update `status.json`:
    ```json
    {
      "slug": "<slug>",
@@ -30,22 +30,22 @@ Legacy-команда для продолжения после human gate. Дл
      "updatedAt": "<ISO8601>"
    }
    ```
-   Затем сразу установи `"state": "in_progress"` перед вызовом developer.
+   Then immediately set `"state": "in_progress"` before calling the developer.
 
-2. Запиши `.claude/team/active-task.json` → `{ "slug": "<slug>" }`.
+2. Write `.claude/team/active-task.json` → `{ "slug": "<slug>" }`.
 
-3. Вызови subagent **feature-developer** с контекстом:
-   - пути к `brief.md`, `decomposition.md`, `status.json`;
-   - указание следовать `rules/architecture/feature-delivery-workflow.md`.
+3. Call subagent **feature-developer** with context:
+   - paths to `brief.md`, `decomposition.md`, `status.json`;
+   - instruction to follow `rules/architecture/feature-delivery-workflow.md`.
 
-4. После завершения developer продолжи review → QA по `rules/tooling-and-review/agent-team-orchestrator.md`.
+4. After the developer finishes, continue review → QA per `rules/tooling-and-review/agent-team-orchestrator.md`.
 
-## Если review вернул changes_requested
+## If review returned changes_requested
 
-- Верни `phase` в `development`, `state` в `in_progress`.
-- Снова вызови **feature-developer** с списком правок от reviewer.
+- Set `phase` back to `development`, `state` to `in_progress`.
+- Call **feature-developer** again with the reviewer’s change list.
 
-## Не делать
+## Do not
 
-- Не пропускать human gate без явного `/feature-continue`.
-- Не совмещать роли developer и reviewer в одном subagent-вызове.
+- Skip the human gate without an explicit `/feature-continue`.
+- Combine developer and reviewer roles in one subagent call.

package/presets/claude/go/commands/feature-start.md

@@ -3,28 +3,28 @@ name: feature-start
 description: Legacy analyst-only feature intake. Prefer /task for new work because it uses router and dynamic pipeline.
 ---
 
-# Feature start — legacy команда агентов
+# Feature start — legacy agent command
 
-Запуск **фазы анализа** для новой задачи. Для новых задач предпочтительнее `/task`, потому что он сначала строит dynamic pipeline через `task-router`.
+Starts the **analysis phase** for a new task. For new work, prefer `/task` because it builds a dynamic pipeline via `task-router` first.
 
-## Что делать
+## What to do
 
-1. Извлеки описание задачи из аргументов команды (всё после `/feature-start`).
-2. Сгенерируй **slug** (kebab-case, до 48 символов) из заголовка задачи.
-3. Создай `.claude/team/tasks/<slug>/` если его ещё нет — через запись файла (Write / Edit), не через Shell `mkdir`.
-4. Запиши `.claude/team/active-task.json` → `{ "slug": "<slug>" }`.
-5. Вызови subagent **task-analyst** с полным описанием задачи и путём к артефактам.
-6. Дождись завершения аналитика. **Не вызывай developer** на этом этапе.
+1. Extract the task description from command arguments (everything after `/feature-start`).
+2. Generate a **slug** (kebab-case, up to 48 characters) from the task title.
+3. Create `.claude/team/tasks/<slug>/` if it does not exist — via Write / Edit, not Shell `mkdir`.
+4. Write `.claude/team/active-task.json` → `{ "slug": "<slug>" }`.
+5. Invoke subagent **task-analyst** with the full task description and artifact paths.
+6. Wait for the analyst to finish. **Do not invoke developer** at this stage.
 
 ## Human gate
 
-После аналитика:
+After the analyst:
 
-- Покажи пользователю ссылки на `brief.md` и `decomposition.md`.
-- Попроси проверить и утвердить или прислать правки.
-- Для продолжения: `/feature-continue <slug>` или `/task-continue <slug>`.
+- Show the user links to `brief.md` and `decomposition.md`.
+- Ask them to review and approve or send edits.
+- To continue: `/feature-continue <slug>` or `/task-continue <slug>`.
 
-## Если slug уже существует
+## If slug already exists
 
-- Если `status.json` в `awaiting_approval` — предложи ревью или `/feature-continue`.
-- Если задача в работе — спроси, продолжать или начать новый slug.
+- If `status.json` is `awaiting_approval` — offer review or `/feature-continue`.
+- If the task is in progress — ask whether to continue or start a new slug.

package/presets/claude/go/commands/task-continue.md

@@ -3,25 +3,25 @@ name: task-continue
 description: Continue an agent-team task after a human gate, pause, or review changes request using pipeline.json and status.json.
 ---
 
-# Task continue — после human gate или паузы
+# Task continue — after human gate or pause
 
-Продолжение пайплайна из `pipeline.json`. Алиас по смыслу: `/feature-continue`.
+Resume the pipeline from `pipeline.json`. Semantic alias: `/feature-continue`.
 
-## Аргументы
+## Arguments
 
-`<slug>` — идентификатор задачи.
+`<slug>` — task identifier.
 
 ## Preconditions
 
-1. Прочитай `.claude/team/tasks/<slug>/pipeline.json` и `status.json`.
-2. Продолжай если:
-   - `awaitingHumanGate: true` или `state: awaiting_approval`, **или**
-   - `state: changes_requested` (после review), **или**
-   - задача прервана и нужно возобновить с `pipelineIndex`.
+1. Read `.claude/team/tasks/<slug>/pipeline.json` and `status.json`.
+2. Continue if:
+   - `awaitingHumanGate: true` or `state: awaiting_approval`, **or**
+   - `state: changes_requested` (after review), **or**
+   - the task was interrupted and must resume from `pipelineIndex`.
 
-## Алгоритм
+## Algorithm
 
-1. Запиши `.claude/team/active-task.json` → `{ "slug": "<slug>" }`.
+1. Write `.claude/team/active-task.json` → `{ "slug": "<slug>" }`.
 2. **Human gate resume** (`awaitingHumanGate` / `awaiting_approval`):
    1. **Do not** manually increment `pipelineIndex` or invent `currentAgent` first.
    2. Close the gate + activate the next attempt via the **installed** hook (single authority for ledger + status):
@@ -36,10 +36,10 @@ printf '%s\n' '{"status":"completed","action":"end_human_gate","activateNext":tr
 4. **Other resume**: restore `pipelineIndex` / `currentAgent` from status and invoke that agent.
 5. After the invoked agent completes, `chain-team-phases.sh` on `subagentStop` continues the chain when `autoChain: true`.
 
-## Артефакты для handoff
+## Artifacts for handoff
 
-| Agent | Прочитать |
-|-------|-----------|
+| Agent | Read |
+|-------|------|
 | feature-developer | brief.md, decomposition.md, validation-report.md (if retry), review.md (if retry), architecture.md |
 | build-verifier | git diff, decomposition.md |
 | code-reviewer | brief.md, validation-report.md, git diff |