claude-nexus 0.19.0 → 0.20.0

package/.claude-plugin/marketplace.json

@@ -7,7 +7,7 @@
     {
       "name": "claude-nexus",
       "description": "Agent orchestration plugin for Claude Code. Injects optimized context per agent role with minimal overhead.",
-      "version": "0.19.0",
+      "version": "0.20.0",
       "author": {
         "name": "kih"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-nexus",
-  "version": "0.19.0",
+  "version": "0.20.0",
   "description": "Agent orchestration plugin for Claude Code — optimized context injection per role",
   "author": {
     "name": "kih"

package/README.en.md

@@ -9,7 +9,7 @@ Agent orchestration plugin for Claude Code.
 
 ## Why
 
-Specialized agent teams handle development and research systematically — architect, engineer, QA, researcher, and more. One tag triggers automatic orchestration of complex tasks across the right agents without manual coordination.
+Specialized agent teams handle development and research systematically — architect, engineer, tester, researcher, and more. One tag triggers automatic orchestration of complex tasks across the right agents without manual coordination.
 
 ## Quick Start
 
@@ -26,7 +26,7 @@ Run `/claude-nexus:nx-init` — scans your project and auto-generates structured
 
 **3. Start using**
 
-- **Meet**: `[meet] How should we design the auth system?` — clarify intent and align before executing
+- **Plan**: `[plan] How should we design the auth system?` — clarify intent and align before executing
 - **Run**: `[run] Implement login API` — agent team handles analysis through implementation
 
 ## Usage
@@ -35,12 +35,12 @@ Tag your message to route it to the right workflow:
 
 | Tag | Action | Example |
 |-----|--------|---------|
-| `[meet]` | Pre-execution meeting | `[meet] Discuss DB migration strategy` |
+| `[plan]` | Pre-execution planning | `[plan] Discuss DB migration strategy` |
 | `[run]` | Execution (agent team) | `[run] Refactor payment module` |
 | `[d]` | Record a decision | `[d] Use PostgreSQL for primary storage` |
 | `[rule]` | Save a rule | `[rule] Always use bun instead of npm` |
 
-Typical flow: use `[meet]` to discuss and align → decide → use `[run]` to execute.
+Typical flow: use `[plan]` to discuss and align → decide → use `[run]` to execute.
 
 ## Agents
 
@@ -65,14 +65,14 @@ Typical flow: use `[meet]` to discuss and align → decide → use `[run]` to ex
 
 | Agent | Invocation | Role | Model |
 |-------|-----------|------|-------|
-| **QA** | `claude-nexus:qa` | Verification, testing, and security review | sonnet |
+| **Tester** | `claude-nexus:tester` | Verification, testing, and security review | sonnet |
 | **Reviewer** | `claude-nexus:reviewer` | Content verification and fact-checking | sonnet |
 
 ## Skills
 
 | Skill | Trigger | Description |
 |-------|---------|-------------|
-| **nx-meet** | `[meet]` | Structured meeting. Clarify requirements → record decisions (`[d]`) → recommend execution tag |
+| **nx-plan** | `[plan]` | Structured planning. Clarify requirements → record decisions (`[d]`) → recommend execution tag |
 | **nx-run** | `[run]` | Execution. User-directed agent composition for development, research, and more |
 | **nx-init** | `/claude-nexus:nx-init` | Full project onboarding: scan codebase, establish identity, generate core knowledge |
 | **nx-setup** | `/claude-nexus:nx-setup` | Interactive setup. Injects agent/skill/tag configuration into CLAUDE.md |
@@ -85,22 +85,20 @@ Typical flow: use `[meet]` to discuss and align → decide → use `[run]` to ex
 
 Claude-callable tools exposed by the Nexus MCP server.
 
-### Core (17 tools)
+### Core (15 tools)
 
 | Tool | Purpose |
 |------|---------|
 | `nx_briefing` | Assemble role-specific briefing (core knowledge + rules) |
 | `nx_core_read/write` | Project knowledge management (git-tracked) |
 | `nx_rules_read/write` | Team custom rules management (git-tracked) |
-| `nx_context` | Current session state lookup (branch, tasks, meet) |
+| `nx_context` | Current session state lookup (branch, tasks, plan) |
 | `nx_task_list/add/update/close` | Task management + history.json archiving |
 | `nx_artifact_write` | Save team artifacts (branch-isolated) |
-| `nx_meet_start` | Start meeting session (topic + issues, team verification) |
-| `nx_meet_status` | Query meeting state |
-| `nx_meet_update` | Modify meeting issues (add/remove/edit/reopen) |
-| `nx_meet_discuss` | Record issue discussion (speaker validation: registered attendees only) |
-| `nx_meet_decide` | Record issue decision (meet.json) |
-| `nx_meet_join` | Join an ongoing meeting |
+| `nx_plan_start` | Start plan session (topic + issues, team verification) |
+| `nx_plan_status` | Query plan state |
+| `nx_plan_update` | Modify plan issues (add/remove/edit/reopen) |
+| `nx_plan_decide` | Record issue decision (plan.json) |
 
 ### Code Intelligence (10 tools)
 
@@ -130,7 +128,7 @@ Nexus registers a single Gate module as a Claude Code hook.
 | Event | Role |
 |-------|------|
 | `UserPromptSubmit` | Tag detection → mode activation + TASK_PIPELINE injection + additionalContext guidance |
-| `PreToolUse` | Edit/Write: blocks when tasks.json missing. nx_meet_start: attendee team verification. Agent: team_name tracking |
+| `PreToolUse` | Edit/Write: blocks when tasks.json missing. nx_plan_start: attendee team verification. Agent: team_name tracking |
 | `Stop` | Blocks exit with pending tasks. Forces nx_task_close when all completed |
 
 </details>

package/README.md

@@ -28,15 +28,17 @@ claude plugin install claude-nexus@nexus
 
 **첫 사용**
 
-- **미팅**: `[meet] 인증 시스템 어떻게 설계하면 좋을까?`
+- **플랜**: `[plan] 인증 시스템 어떻게 설계하면 좋을까?`
 - **결정 기록**: `응 그 방향으로 [d]`
 
 ## 사용법
 
 | 태그 | 동작 | 예시 |
 |------|------|------|
-| `[meet]` | 미팅 모드 활성화 | `[meet] DB 마이그레이션 전략 논의` |
+| `[plan]` | 플랜 모드 활성화 | `[plan] DB 마이그레이션 전략 논의` |
 | `[d]` | 결정 기록 | `응 그 방향으로 [d]` |
+| `[run]` | 실행 (에이전트 팀) | `[run] 결제 모듈 리팩토링` |
+| `[rule]` | 규칙 저장 | `[rule] npm 대신 bun 사용` |
 
 ## 에이전트
 
@@ -49,14 +51,14 @@ claude plugin install claude-nexus@nexus
 | **Do** | Engineer | 코드 구현, 디버깅 | sonnet |
 | **Do** | Researcher | 웹 검색, 독립 조사 | sonnet |
 | **Do** | Writer | 기술 문서, 프레젠테이션 | sonnet |
-| **Check** | QA | 코드 검증, 테스트, 보안 | sonnet |
+| **Check** | Tester | 코드 검증, 테스트, 보안 | sonnet |
 | **Check** | Reviewer | 콘텐츠 검증, 출처 확인 | sonnet |
 
 ## 스킬
 
 | 스킬 | 트리거 | 설명 |
 |------|--------|------|
-| **nx-meet** | `[meet]` | 구조화된 미팅. 요구사항 정리 → 결정 기록 |
+| **nx-plan** | `[plan]` | 구조화된 플랜. 요구사항 정리 → 결정 기록 |
 | **nx-run** | (기본 동작) | 동적 에이전트 구성 실행 |
 | **nx-init** | `/claude-nexus:nx-init` | 프로젝트 온보딩. 코드 스캔 → 지식 생성 |
 | **nx-setup** | `/claude-nexus:nx-setup` | 대화형 설정 |
@@ -69,22 +71,20 @@ claude plugin install claude-nexus@nexus
 
 Claude가 직접 호출하는 도구입니다.
 
-### Core (17개)
+### Core (15개)
 
 | 도구 | 용도 |
 |------|------|
 | `nx_briefing` | 에이전트 역할별 브리핑 조립 (core knowledge + rules 기반) |
 | `nx_core_read/write` | 프로젝트 지식 관리 (`.nexus/core/`, git 추적) |
 | `nx_rules_read/write` | 팀 커스텀 규칙 관리 (`.nexus/rules/`, git 추적) |
-| `nx_context` | 현재 세션 상태 조회 (브랜치, 태스크, 미팅) |
+| `nx_context` | 현재 세션 상태 조회 (브랜치, 태스크, 플랜) |
 | `nx_task_list/add/update/close` | `.nexus/state/tasks.json` 기반 태스크 관리 + `.nexus/history.json` 아카이브 |
 | `nx_artifact_write` | 팀 산출물 저장 (`.nexus/state/artifacts/`) |
-| `nx_meet_start` | 미팅 세션 시작 (토픽 + 논점 등록, 참석자 팀 검증) |
-| `nx_meet_status` | 미팅 상태 조회 |
-| `nx_meet_update` | 미팅 논점 수정 (add/remove/edit/reopen) |
-| `nx_meet_discuss` | 논점 토론 기록 (speaker 검증: 등록된 참석자만 허용) |
-| `nx_meet_decide` | 논점 결정 처리 (meet.json) |
-| `nx_meet_join` | 진행 중인 미팅 참여 |
+| `nx_plan_start` | 플랜 세션 시작 (토픽 + 논점 등록, 참석자 팀 검증) |
+| `nx_plan_status` | 플랜 상태 조회 |
+| `nx_plan_update` | 플랜 논점 수정 (add/remove/edit/reopen) |
+| `nx_plan_decide` | 논점 결정 처리 (plan.json) |
 
 ### Code Intelligence (10개)
 
@@ -114,7 +114,7 @@ Gate 단일 모듈로 동작합니다.
 | 이벤트 | 역할 |
 |--------|------|
 | `UserPromptSubmit` | 태그 감지 → 모드 활성화 + TASK_PIPELINE 주입 + additionalContext 안내 |
-| `PreToolUse` | Edit/Write: tasks.json 없으면 차단. nx_meet_start: 참석자 팀 검증. Agent: team_name 트래킹 |
+| `PreToolUse` | Edit/Write: tasks.json 없으면 차단. nx_plan_start: 참석자 팀 검증. Agent: team_name 트래킹 |
 | `Stop` | pending 태스크 있으면 종료 차단. all completed면 nx_task_close 강제 |
 
 </details>

package/VERSION

@@ -1 +1 @@
-0.19.0
+0.20.0

package/agents/postdoc.md

@@ -4,7 +4,7 @@ model: opus
 description: Research methodology and synthesis — designs investigation approach, evaluates evidence quality, writes synthesis documents
 task: "Research methodology, evidence synthesis"
 maxTurns: 25
-disallowedTools: [Edit, Bash, NotebookEdit, mcp__plugin_claude-nexus_nx__nx_task_add, mcp__plugin_claude-nexus_nx__nx_task_update]
+disallowedTools: [Edit, Write, NotebookEdit, mcp__plugin_claude-nexus_nx__nx_task_add, mcp__plugin_claude-nexus_nx__nx_task_update]
 tags: [research, synthesis, methodology]
 alias_ko: 포닥
 category: how

package/agents/researcher.md

@@ -4,15 +4,16 @@ model: sonnet
 description: Independent investigation — conducts web searches, gathers evidence, and reports findings with citations
 task: "Web search, independent investigation"
 maxTurns: 20
-disallowedTools: [mcp__plugin_claude-nexus_nx__nx_task_add]
+disallowedTools: [Edit, Write, NotebookEdit, mcp__plugin_claude-nexus_nx__nx_task_add]
 tags: [research, investigation, web-search, analysis]
 alias_ko: 리서처
 category: do
 ---
 
 <role>
-You are the Researcher — the independent investigator who gathers evidence through web searches, document analysis, and structured inquiry.
+You are the Researcher — the web research specialist who gathers evidence through web searches, external document analysis, and structured inquiry.
 You receive research questions from Lead (what to find) and methodology guidance from postdoc (how to search), then investigate and report findings.
+Codebase exploration is Explore's domain — you focus on external sources (web, APIs, documentation).
 You work independently on each assigned question. When a search line proves unproductive, you recognize it and exit with what you have rather than persisting fruitlessly.
 </role>
 

package/agents/reviewer.md

@@ -4,7 +4,7 @@ model: sonnet
 description: Content verification — validates accuracy, checks facts, confirms grammar and format of non-code deliverables
 task: "Content verification, fact-checking, grammar review"
 maxTurns: 20
-disallowedTools: [mcp__plugin_claude-nexus_nx__nx_task_add]
+disallowedTools: [Edit, Write, NotebookEdit, mcp__plugin_claude-nexus_nx__nx_task_add]
 tags: [review, verification, fact-checking, content, quality]
 alias_ko: 리뷰어
 category: check
@@ -13,11 +13,12 @@ category: check
 <role>
 You are the Reviewer — the content quality guardian who verifies the accuracy, clarity, and integrity of non-code deliverables.
 You ensure that documents, reports, and presentations are factually correct, internally consistent, and appropriately formatted.
-You validate content, not code. Code verification is QA's domain.
+You validate content, not code. Code verification is Tester's domain.
+You are always paired with Writer — whenever Writer produces a deliverable, you verify it before delivery.
 </role>
 
 <constraints>
-- NEVER review code files — that is QA's domain
+- NEVER review code files — that is Tester's domain
 - NEVER rewrite content for style — flag issues and return to Writer
 - NEVER block delivery over INFO-level issues without Lead guidance
 - NEVER approve documents you haven't actually checked against source material

package/agents/{qa.md → tester.md}

@@ -1,17 +1,18 @@
 ---
-name: qa
+name: tester
 model: sonnet
-description: Quality assurance — tests, verifies, validates stability and security of implementations
+description: Testing and verification — tests, verifies, validates stability and security of implementations
 task: "Testing, verification, security review"
 maxTurns: 20
-disallowedTools: [mcp__plugin_claude-nexus_nx__nx_task_add]
+disallowedTools: [Edit, Write, NotebookEdit, mcp__plugin_claude-nexus_nx__nx_task_add]
 tags: [verification, testing, security, quality]
-alias_ko: QA
+alias_ko: 테스터
 category: check
 ---
 
 <role>
-You are the QA — the code verification specialist who tests, validates, and secures implementations.
+You are the Tester — the code verification specialist who tests, validates, and secures implementations.
+You are the primary verifier of plan acceptance criteria: you read each task's acceptance field and determine whether the implementation satisfies it before the task can be marked completed.
 You verify code: run tests, check types, review implementations, and identify security issues.
 You do NOT verify non-code deliverables (documents, reports, presentations) — that is Reviewer's domain.
 You do NOT fix application code — you report findings and write test code only.
@@ -31,13 +32,34 @@ You do NOT fix application code — you report findings and write test code only
 ## Core Principle
 Verify correctness through evidence, not assumptions. Run tests, check types, review code — then report what you found with clear severity classifications. Your job is to find problems, not hide them.
 
-## Verification Checklist (default mode)
-When verifying a completed implementation:
+## Acceptance Verification (핵심 검증)
+When an Engineer reports a task as complete, perform acceptance verification before Lead marks it completed:
+
+1. **Read the acceptance criteria** — open `tasks.json`, locate the task by ID, read its `acceptance` field
+2. **Verify each criterion individually** — for each item listed, determine PASS or FAIL with evidence
+3. **Report the verdict** — a task is only COMPLETED if every criterion passes; a single FAIL blocks completion
+
+Reporting format:
+```
+ACCEPTANCE VERIFICATION — Task <id>: <title>
+
+[ PASS | FAIL ] <criterion 1>
+  Evidence: <what you checked and found>
+[ PASS | FAIL ] <criterion 2>
+  Evidence: <what you checked and found>
+...
+
+VERDICT: PASS (all criteria met) | FAIL (<N> criteria failed)
+```
+
+If `tasks.json` does not exist or the task has no `acceptance` field, note this explicitly and proceed with basic verification only.
+
+## Basic Verification
+When verifying a completed implementation (default mode):
 1. Run the full test suite and report pass/fail (`bun test`)
 2. Run type checking and report errors (`tsc --noEmit` or `bun run build`)
 3. Verify the build succeeds end-to-end
-4. Check that the implementation matches the task's acceptance criteria
-5. Review changed files for obvious logic errors or security issues
+4. Review changed files for obvious logic errors or security issues
 
 ## Testing Mode
 When writing or improving tests: