agestra 4.11.0 → 4.12.0

package/.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "name": "agestra",
       "source": "./",
       "description": "Orchestrate Ollama, Gemini, and Codex for multi-AI debates, code review, and cross-validation",
-      "version": "4.11.0",
+      "version": "4.12.0",
       "author": {
         "name": "mua-vtuber"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agestra",
-  "version": "4.11.0",
+  "version": "4.12.0",
   "description": "Claude Code plugin — orchestrate Ollama, Gemini, and Codex for multi-AI debates, code review, and cross-validation",
   "mcpServers": {
     "agestra": {

package/.gemini/commands/agestra/implement.toml

@@ -9,8 +9,9 @@ Use the shared workflow spec below as the source of truth and adapt it to the cu
 @{commands/implement.md}
 
 Gemini-specific rules:
-- Start with `environment_check` and `provider_list`.
+- Start with `setup_status`, then `environment_check` and `provider_list`.
 - Prefer Agestra MCP tools and worker orchestration over ad-hoc shell-heavy implementation plans.
-- Translate Claude-specific wording into leader-host wording when Gemini is the active host.
+- Treat "Leader-host only" as the Gemini-led local path when Gemini is the active host.
+- Use the shared `agestra-implementer` role semantics for host-local code edits.
 - Keep the final answer in the user's language.
 """

package/AGENTS.md

@@ -13,7 +13,7 @@ This repository includes a Codex-friendly host wrapper for Agestra.
 - Treat `commands/*.md` as the source of truth for Agestra workflows.
 - When the user asks for review, design, idea, or implementation help, start with `environment_check` and `provider_list`.
 - Prefer Agestra MCP tools over ad-hoc multi-provider prompting.
-- If a workflow mentions "Claude only", interpret that as the current leader-host-only path when Claude is not the active host.
+- If any legacy workflow text mentions "Claude only", interpret that as the current leader-host-only path when Claude is not the active host.
 
 ## Workflow Mapping
 

package/GEMINI.md

@@ -24,7 +24,7 @@ Each command delegates to the shared workflow specs in `commands/*.md`.
 - Start orchestration requests with `environment_check` and `provider_list`.
 - Prefer Agestra MCP tools instead of rebuilding workflows in free-form prompts.
 - Treat `commands/*.md` and `agents/*.md` as the canonical workflow and role assets.
-- If a shared workflow mentions "Claude only", translate that to the current leader-host-only path when Gemini is the active host.
+- If any legacy shared workflow text mentions "Claude only", translate that to the current leader-host-only path when Gemini is the active host.
 
 ## Core MCP Tools
 

package/README.ja.md

@@ -84,7 +84,7 @@ Gemini ではリポジトリ直下の [GEMINI.md](GEMINI.md) と、[`.gemini/com
 | `/agestra setup` | 初期 AI プロバイダー選択とセットアップ |
 | `/agestra implement [task]` | Claude only または Multi-AI モードで実装を進める |
 
-外部プロバイダーが利用可能な場合、テキストコマンド（review、design、idea）は直接ディベートモードに入り、マルチ AI クロスバリデーションを行います。プロバイダーが検出されない場合、Claude が自動的に単独で作業します。
+外部プロバイダーが利用可能な場合、テキストコマンド（review、design、idea）は直接徹底討論モードに入り、マルチ AI クロスバリデーションを行います。プロバイダーが検出されない場合、Claude が自動的に単独で作業します。
 
 ## エージェント
 
@@ -106,8 +106,11 @@ Gemini ではリポジトリ直下の [GEMINI.md](GEMINI.md) と、[`.gemini/com
 | `cancel` | ワーカー、ディベート、チェーン、タスクの安全な停止 |
 | `build-fix` | build/typecheck/lint エラーの自動診断と修正 |
 | `trace` | エージェント実行タイムラインとフローダイアグラムの表示 |
+| `setup` | 初期プロバイダー選択と `providers.config.json` 書き込み |
 | `design` | Multi-AI モード選択を含む設計探索ワークフロー |
 | `idea` | Multi-AI モード選択を含む改善案発見ワークフロー |
+| `review` | Multi-AI モード選択を含むコード品質・セキュリティ・ハードコーディングレビューワークフロー |
+| `leader` | マルチAI/プロバイダーオーケストレーションのエントリーポイント — 明示的なプロバイダー、ディベート、合意形成、相互検証シグナルを検知し、ドメイン分類後 `agestra-team-lead` へ委譲 |
 
 ---
 
@@ -137,7 +140,7 @@ Turborepo モノレポで、9 パッケージ構成です:
 
 ### 作業モード
 
-**Text work**（レビュー、設計、アイデア）: プロバイダーあり → ディベートモード; なし → Claude only
+**Text work**（レビュー、設計、アイデア）: プロバイダーあり → 徹底討論モード; なし → Claude only
 
 **Implementation work**（team-lead orchestration）:
 - **Claude만으로** — Claude がプロジェクト/グローバルエージェントを使って直接実装します。
@@ -314,7 +317,12 @@ agestra/
 │   ├── worker-manage.md     # CLI ワーカー管理
 │   ├── cancel.md            # 安全な操作キャンセル
 │   ├── build-fix.md         # ビルドエラー自動修復
-│   └── trace.md             # 実行タイムラインビューア
+│   ├── trace.md             # 実行タイムラインビューア
+│   ├── setup.md             # 初期プロバイダー選択
+│   ├── design.md            # 設計探索ワークフロー
+│   ├── idea.md              # 改善案発見ワークフロー
+│   ├── review.md            # コード品質レビューワークフロー
+│   └── leader.md            # マルチAIオーケストレーションルーター
 ├── hooks/
 │   └── user-prompt-submit.md  # ツール推奨フック
 ├── dist/

package/README.ko.md

@@ -148,8 +148,11 @@ winget install BurntSushi.ripgrep.MSVC
 | `cancel` | 워커, 토론, 체인, 작업의 정상 종료 |
 | `build-fix` | 빌드/타입체크/린트 에러 자동 진단 및 수정 |
 | `trace` | 에이전트 실행 타임라인 및 흐름 다이어그램 조회 |
+| `setup` | 초기 공급자 선택 및 `providers.config.json` 작성 |
 | `design` | 멀티 AI 모드 선택이 포함된 아키텍처 탐색 워크플로우 |
 | `idea` | 멀티 AI 모드 선택이 포함된 개선점 발굴 워크플로우 |
+| `review` | 멀티 AI 모드 선택이 포함된 코드 품질·보안·하드코딩 리뷰 워크플로우 |
+| `leader` | 멀티 AI/프로바이더 오케스트레이션 진입점 — 명시적인 프로바이더, 토론, 합의, 교차 검증 신호를 잡아 도메인을 분류한 뒤 `agestra-team-lead`에 위임 |
 
 ---
 
@@ -357,7 +360,12 @@ agestra/
 │   ├── worker-manage.md     # CLI 워커 관리
 │   ├── cancel.md            # 정상 작업 취소
 │   ├── build-fix.md         # 빌드 에러 자동 수정
-│   └── trace.md             # 실행 타임라인 조회
+│   ├── trace.md             # 실행 타임라인 조회
+│   ├── setup.md             # 초기 공급자 선택
+│   ├── design.md            # 아키텍처 탐색 워크플로우
+│   ├── idea.md              # 개선점 발굴 워크플로우
+│   ├── review.md            # 코드 품질 리뷰 워크플로우
+│   └── leader.md            # 멀티 AI 오케스트레이션 라우터
 ├── hooks/
 │   └── user-prompt-submit.md  # 도구 추천 hook
 ├── dist/

package/README.md

@@ -124,15 +124,16 @@ All three hosts drive the same MCP server and shared workflow specs from `comman
 | `/agestra idea [topic]` | Discover improvements by comparing with similar projects |
 | `/agestra design [subject]` | Explore architecture and design trade-offs before implementation |
 | `/agestra setup` | Initial AI provider selection and setup |
-| `/agestra implement [task]` | Execute implementation in Claude-only or Multi-AI mode |
+| `/agestra implement [task]` | Execute implementation through Leader-host-only or suggested AI distribution mode |
 
-When external providers are available, text commands (review, design, idea) go directly to debate mode for multi-AI cross-validation. When no providers are detected, Claude works alone automatically.
+When external providers are available, text commands (review, design, idea) go directly to consensus debate mode for multi-AI cross-validation. When no providers are detected, the current leader host works with its local specialist agent automatically. Implementation requests first classify the task and can ask whether to propose an AI task distribution.
 
 ## Agents
 
 | Agent | Model | Role |
 |-------|-------|------|
 | `agestra-team-lead` | Sonnet | Full orchestrator — environment check, quality-based provider routing, work mode selection, CLI worker supervision, QA loop |
+| `agestra-implementer` | Sonnet | Scoped implementation executor — code edits, test updates, local verification |
 | `agestra-reviewer` | Opus | Strict quality verifier — security, orphans, spec drift, test gaps |
 | `agestra-designer` | Opus | Architecture explorer — Socratic questioning, trade-off analysis |
 | `agestra-ideator` | Sonnet | Improvement discoverer — web research, competitive analysis |
@@ -148,8 +149,11 @@ When external providers are available, text commands (review, design, idea) go d
 | `cancel` | Graceful stop for workers, debates, chains, tasks |
 | `build-fix` | Auto-diagnose and fix build/typecheck/lint errors |
 | `trace` | View agent execution timeline and flow diagrams |
+| `setup` | Initial provider selection and `providers.config.json` write |
 | `design` | Architecture exploration workflow with multi-AI mode selection |
 | `idea` | Improvement discovery workflow with multi-AI mode selection |
+| `review` | Code quality / security / hardcoding review workflow with multi-AI mode selection |
+| `leader` | Multi-AI/provider orchestration entry — catches explicit provider, debate, consensus, or cross-validation signals, classifies the domain, and hands off to `agestra-team-lead` |
 
 ---
 
@@ -179,11 +183,11 @@ Turborepo monorepo with 9 packages:
 
 ### Work Modes
 
-**Text work** (review, design, idea): providers available → debate mode; no providers → Claude only
+**Text work** (review, design, idea): providers available → consensus debate mode; no providers → Leader-host only
 
 **Implementation work** (team-lead orchestration):
-- **Claude만으로** — Claude implements directly with project/global agents.
-- **다른 AI도 함께** — CLI workers (Codex/Gemini) do autonomous coding in isolated git worktrees, Ollama handles simple tasks, Claude supervises and merges.
+- **Leader-host only** — `agestra-implementer` applies scoped code changes; reviewer/QA verify.
+- **Suggested AI distribution** — the team lead proposes a routing table, asks for approval, then dispatches Codex/Gemini CLI workers for suitable code edits and Ollama for simple/repetitive proposal work.
 
 ---
 
@@ -349,6 +353,7 @@ agestra/
 │   ├── agestra-reviewer.md  # Strict quality verifier (Opus)
 │   ├── agestra-designer.md  # Architecture explorer (Opus)
 │   ├── agestra-ideator.md   # Improvement discoverer (Sonnet)
+│   ├── agestra-implementer.md # Scoped implementation executor (Sonnet)
 │   ├── agestra-moderator.md # Multi-mode facilitator (Sonnet)
 │   ├── agestra-qa.md        # QA verifier (Opus, no code writes)
 │   └── agestra-team-lead.md # Full orchestrator (Sonnet, no code writes)
@@ -357,7 +362,12 @@ agestra/
 │   ├── worker-manage.md     # CLI worker management
 │   ├── cancel.md            # Graceful operation cancellation
 │   ├── build-fix.md         # Build error auto-repair
-│   └── trace.md             # Execution timeline viewer
+│   ├── trace.md             # Execution timeline viewer
+│   ├── setup.md             # Initial provider selection
+│   ├── design.md            # Architecture exploration workflow
+│   ├── idea.md              # Improvement discovery workflow
+│   ├── review.md            # Code quality review workflow
+│   └── leader.md            # Multi-AI orchestration entry router
 ├── hooks/
 │   └── user-prompt-submit.md  # Tool recommendation hook
 ├── dist/

package/README.zh.md

@@ -84,7 +84,7 @@ Gemini 会结合仓库根目录下的 [GEMINI.md](GEMINI.md) 与 [`.gemini/comma
 | `/agestra setup` | 初始 AI 提供方选择与设置 |
 | `/agestra implement [task]` | 以 Claude only 或 Multi-AI 模式执行实现 |
 
-当外部提供方可用时，文本命令（review、design、idea）直接进入辩论模式，进行多 AI 交叉验证。当未检测到提供方时，Claude 自动独立工作。
+当外部提供方可用时，文本命令（review、design、idea）直接进入终极辩论模式，进行多 AI 交叉验证。当未检测到提供方时，Claude 自动独立工作。
 
 ## 代理
 
@@ -106,8 +106,11 @@ Gemini 会结合仓库根目录下的 [GEMINI.md](GEMINI.md) 与 [`.gemini/comma
 | `cancel` | 安全停止 worker、辩论、链路和任务 |
 | `build-fix` | 自动诊断并修复 build/typecheck/lint 错误 |
 | `trace` | 查看代理执行时间线与流程图 |
+| `setup` | 初始提供方选择与 `providers.config.json` 写入 |
 | `design` | 包含 Multi-AI 模式选择的架构探索工作流 |
 | `idea` | 包含 Multi-AI 模式选择的改进发现工作流 |
+| `review` | 包含 Multi-AI 模式选择的代码质量·安全·硬编码审查工作流 |
+| `leader` | 多AI/提供方编排入口 — 捕获明确的提供方、辩论、共识或交叉验证信号，进行领域分类后委托给 `agestra-team-lead` |
 
 ---
 
@@ -137,7 +140,7 @@ Gemini 会结合仓库根目录下的 [GEMINI.md](GEMINI.md) 与 [`.gemini/comma
 
 ### 工作模式
 
-**文本工作**（review、design、idea）：有提供方 → 辩论模式；无提供方 → Claude only
+**文本工作**（review、design、idea）：有提供方 → 终极辩论模式；无提供方 → Claude only
 
 **实现工作**（team-lead orchestration）：
 - **Claude만으로** — Claude 直接结合项目/全局代理完成实现。
@@ -314,7 +317,12 @@ agestra/
 │   ├── worker-manage.md     # CLI Worker 管理
 │   ├── cancel.md            # 安全取消操作
 │   ├── build-fix.md         # 构建错误自动修复
-│   └── trace.md             # 执行时间线查看器
+│   ├── trace.md             # 执行时间线查看器
+│   ├── setup.md             # 初始提供方选择
+│   ├── design.md            # 架构探索工作流
+│   ├── idea.md              # 改进发现工作流
+│   ├── review.md            # 代码质量审查工作流
+│   └── leader.md            # 多AI 编排路由器
 ├── hooks/
 │   └── user-prompt-submit.md  # 工具推荐 hook
 ├── dist/

package/agents/agestra-designer.md

@@ -23,6 +23,7 @@ description: |
   </example>
 model: opus
 color: blue
+disallowedTools: Edit, NotebookEdit
 ---
 
 <Role>

package/agents/agestra-ideator.md

@@ -23,6 +23,7 @@ description: |
   </example>
 model: sonnet
 color: green
+disallowedTools: Edit, NotebookEdit
 ---
 
 <Role>

package/agents/agestra-implementer.md

@@ -0,0 +1,76 @@
+---
+name: agestra-implementer
+description: |
+  Implementation executor. Applies scoped code changes, writes or updates tests,
+  follows existing project patterns, and verifies the result. Receives tasks from
+  the team lead; does not orchestrate other providers.
+
+  <example>
+  Context: The team lead has decomposed a task and needs a host-local executor
+  user: "이 작업은 현재 호스트 구현 에이전트가 처리해"
+  assistant: "I'll use the agestra-implementer agent to apply the scoped code changes."
+  <commentary>
+  Implementation executor — modifies code within the assigned files and verifies.
+  </commentary>
+  </example>
+model: sonnet
+color: green
+---
+
+<Role>
+You are a focused implementation executor. You receive a bounded task from the
+leader, modify the code, add or update tests when needed, run verification, and
+report exactly what changed. You are not the moderator, planner, or reviewer.
+</Role>
+
+<Operating_Principles>
+- Stay inside the assigned scope. Do not perform unrelated cleanup or broad refactors.
+- Follow existing project patterns before introducing new abstractions.
+- Treat small and simple as different concepts: a small security or concurrency change may be high-risk; a large repetitive rename may be simple.
+- Prefer tests first for behavioral changes and regressions.
+- Preserve user or other-agent changes. If a file has unrelated edits, work with them rather than reverting them.
+- Do not spawn other AI providers, run debates, or approve external worker changes. Escalate those decisions to the leader.
+</Operating_Principles>
+
+<Workflow>
+
+### Phase 1: Intake
+
+Confirm the task packet contains:
+- Task goal
+- Files allowed to modify
+- Files useful to read
+- Constraints and non-goals
+- Success criteria and verification commands
+- Design/spec reference if one exists
+
+If the task packet is too vague to implement safely, ask the leader for clarification rather than guessing.
+
+### Phase 2: Inspect
+
+Read the relevant files and identify the existing local pattern. Keep the implementation approach small and compatible with surrounding code.
+
+### Phase 3: Implement
+
+Apply the minimal code changes needed to satisfy the task. Add tests when the change affects behavior, public contracts, generated output, provider routing, orchestration, or failure handling.
+
+### Phase 4: Verify
+
+Run the narrowest useful tests first, then broader checks when the change touches shared behavior. If verification fails, diagnose and fix within the assigned scope. If the failure belongs outside the task scope, report it clearly to the leader.
+
+### Phase 5: Report
+
+Report:
+- Files changed
+- Behavior changed
+- Tests or commands run, with pass/fail status
+- Any remaining risks or follow-up decisions for the leader
+
+</Workflow>
+
+<Constraints>
+- You may edit files only for the assigned implementation task.
+- Do not accept or reject CLI worker worktrees.
+- Do not write final synthesis, debate, or approval documents.
+- Do not hide failed verification. Report it and either fix it or explain why it is outside scope.
+</Constraints>

package/agents/agestra-moderator.md

@@ -24,6 +24,7 @@ description: |
   </example>
 model: sonnet
 color: cyan
+disallowedTools: Edit, NotebookEdit
 ---
 
 <Role>
@@ -221,15 +222,15 @@ Invoked when multiple AIs have independently analyzed the same target and their
 ## Integrated Analysis
 
 ### Consensus Findings (agreed by all/most)
-- [finding] — agreed by: Claude, Gemini, Codex
-- [finding] — agreed by: Claude, Ollama
+- [finding] — agreed by: host/reviewer, Gemini, Codex
+- [finding] — agreed by: host/specialist, Ollama
 
 ### Notable Findings (unique perspectives)
 - [finding] — source: Gemini (unique insight)
-- [finding] — source: Claude/reviewer (unique insight)
+- [finding] — source: host/reviewer (unique insight)
 
 ### Disputed Points
-- [topic]: Claude says X, Codex says Y
+- [topic]: host/reviewer says X, Codex says Y
   - Evidence for X: ...
   - Evidence for Y: ...
 
@@ -260,7 +261,7 @@ Invoked after Independent Aggregation has produced an initial working document.
 
 **Input:** Current working doc + ordered participant list.
 
-**Turn order within a round:** external providers alphabetical first, Claude last. Providers are invoked sequentially so the ledger can record one validated turn at a time and later providers can see the current item state.
+**Turn order within a round:** external providers alphabetical first, host-backed specialist last when present. Providers are invoked sequentially so the ledger can record one validated turn at a time and later providers can see the current item state.
 
 **Per round `N` procedure:**
 
@@ -272,7 +273,7 @@ Invoked after Independent Aggregation has produced an initial working document.
    - Current consensus item index from the ledger.
    - JSON response contract from the turn packet.
 
-   b. Send the review request through the MCP moderator engine. For Claude, spawn the appropriate specialist agent (`agestra-ideator`, `agestra-reviewer`, etc.) only when the engine requests the Claude-backed participant turn. For external providers, use provider MCP calls controlled by the engine.
+   b. Send the review request through the MCP moderator engine. For the host-backed specialist, spawn the appropriate specialist agent (`agestra-ideator`, `agestra-reviewer`, etc.) only when the engine requests that participant turn. For external providers, use provider MCP calls controlled by the engine.
 
    c. Validate the JSON response and append accepted stance/comment records to the consensus ledger. The debate markdown is regenerated from the ledger; do not create one markdown document per provider turn.
 
@@ -321,7 +322,7 @@ The idea/review final doc is for **humans skimming after the fact**, not for mac
 #### 2. 참여자 및 라운드 요약
 
 Plain list (not a table):
-- **참여자:** `claude/ideator`, `codex`, … — one line per participant, with a short note if any dropped out mid-flow and why.
+- **참여자:** `host/ideator`, `codex`, ... — one line per participant, with a short note if any dropped out mid-flow and why.
 - **라운드:** `{N}/{max}` with a one-sentence arc ("Round 1: big-picture disagreement on tool scope. Round 2: narrowed to implementation priorities. Round 3: consensus.").
 - **사용자 제약:** every binding constraint the user gave during Phase 1, verbatim.
 
@@ -339,7 +340,7 @@ One **subsection per accepted idea** (not a single table row). For each idea:
 **노력 · 우선순위.** {effort} · {priority} — 협의 결과면 그렇게 표기 ("Round 2 protocol: 노력 S→M, codex 근거 채택").
 
 **동의 현황.**
-- 🟢 agree: claude/ideator, codex
+- 🟢 agree: host/ideator, codex
 - 🟡 agree-with-note: gemini — "MEDIUM이 더 현실적, HIGH는 낙관적"
 - 모두가 agree이면 "전원 agree — 이견 없음." 한 줄로 대체.
 ```
@@ -371,7 +372,7 @@ One subsection per item where Round `N-final` still had any `disagree`. Format:
 마지막에 한 번만 나오는 축약 표 — 3~5번 섹션의 중복이 아니라 **스캔용**. 열은 아이디어 ID, 행은 프로바이더, 셀은 🟢/🟡/🔴만.
 
 ```markdown
-| Idea | claude/ideator | codex | gemini |
+| Idea | host/ideator | codex | gemini |
 |------|----------------|-------|--------|
 | IDEA-01 Auto-focus on Create | 🟢 | 🟢 | 🟢 |
 | IDEA-02 숫자 키 타입 선택 | 🟢 | 🟡 | 🟢 |
@@ -427,9 +428,9 @@ Invoked by team-lead when CLI workers have produced overlapping file changes tha
 <Turn_Management>
 The order within each round (Structured Debate and Document Review modes):
 1. External providers first (alphabetical order)
-2. Claude last (host-backed in moderated mode, or with specialist perspective via `claude_comment` in manual mode)
+2. Host-backed specialist last (or with specialist perspective via `claude_comment` in legacy manual mode)
 
-This ensures Claude can respond to external opinions while the JSON ledger records one validated provider turn at a time. In Structured Debate the participant list is taken **verbatim** from the caller (subject only to `auto_inject_specialists` in D13 and `exclude_participants`); no automatic provider filtering is applied.
+This ensures the host specialist can respond to external opinions while the JSON ledger records one validated provider turn at a time. In Structured Debate the participant list is taken **verbatim** from the caller (subject only to `auto_inject_specialists` in D13 and `exclude_participants`); no automatic provider filtering is applied.
 </Turn_Management>
 
 <Consensus_Criteria>
@@ -441,12 +442,12 @@ If `max_rounds` is hit with open proposals, the moderator surfaces the choice to
 <Constraints>
 - Default `max_rounds = 10`. On hitting the limit the moderator MUST call `AskUserQuestion` — it does not silently extend or truncate.
 - Do NOT express your own opinion on the debate topic. You are a facilitator, not a participant.
-- When a registered host-backed Claude provider is available, include Claude's turn. Otherwise either use manual `claude_comment` turns or proceed without Claude and state that limitation clearly.
+- When a registered host-backed provider is available, include the host specialist turn. Otherwise either use manual `claude_comment` turns for legacy compatibility or proceed without a host specialist and state that limitation clearly.
 - When a specialist or reviewer agent is running in the background, wait for its actual output. Do not substitute your own analysis or stop it after a short empty-output check.
 - Poll long-running background reviewers at reasonable intervals (about once per minute). Treat them as stalled only on explicit error, user cancellation, or no visible progress for at least 8 minutes; allow up to 15 minutes for large review scopes.
 - Summarize neutrally. Do not favor any provider's position.
-- If only one external provider is available, still run the process (Claude + 1 provider is a valid 2-party discussion).
-- If no external providers are available, inform the user and suggest "Claude only" mode instead.
+- If only one external provider is available, still run the process (host specialist + 1 provider is a valid 2-party discussion).
+- If no external providers are available, inform the user and suggest "Leader-host only" mode instead.
 - Never translate participant-authored content (proposal titles, vote reasons, individual-review bodies). Translate only moderator-authored narration via i18n bundles.
 - Communicate in the user's language for moderator-authored narration; respect locale resolution order.
 </Constraints>

package/agents/agestra-qa.md

@@ -199,7 +199,7 @@ Do NOT duplicate the reviewer's checklist. If you suspect code quality issues ou
 - READ-ONLY. You must not modify any files.
 - Every finding must cite a specific file and line number.
 - Do not speculate. If you cannot verify an item, mark it as UNVERIFIABLE with explanation.
-- Do not skip the cross-validation step. If no external providers are available, note it and proceed with Claude-only verification.
+- Do not skip the cross-validation step. If no external providers are available, note it and proceed with Leader-host-only verification.
 - Do not issue PASS if any design requirement is NOT IMPLEMENTED.
 - Do not issue PASS if build or tests fail.
 - Run actual commands (tsc, vitest, etc.) — do not guess test results.