claude-nexus 0.23.1 → 0.24.0

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": "0.23.1",
+      "version": "0.24.0",
       "author": {
         "name": "kih"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-nexus",
-  "version": "0.23.1",
+  "version": "0.24.0",
   "description": "Agent orchestration plugin for Claude Code — optimized context injection per role",
   "author": {
     "name": "kih"

package/README.en.md

@@ -22,7 +22,7 @@ claude plugin install claude-nexus@nexus
 
 **2. Onboard your project**
 
-Run `/claude-nexus:nx-init` — scans your project and auto-generates structured knowledge under `.nexus/core/`.
+Run `/claude-nexus:nx-init` — scans your project and auto-generates structured knowledge under `.nexus/`.
 
 **3. Start using**
 
@@ -39,6 +39,9 @@ Tag your message to route it to the right workflow:
 | `[run]` | Execution (subagent composition) | `[run] Refactor payment module` |
 | `[d]` | Record a decision (within plan session) | `[d] Use PostgreSQL for primary storage` |
 | `[rule]` | Save a rule | `[rule] Always use bun instead of npm` |
+| `[m]` | Add a memo | `[m] Revisit this pattern later` |
+| `[m:gc]` | Garbage-collect memos | `[m:gc]` |
+| `[sync]` | Sync context/ | `[sync]` |
 
 Typical flow: `[plan]` to discuss and align → `[d]` to decide (within plan) → `[run]` to execute.
 
@@ -76,7 +79,7 @@ Typical flow: `[plan]` to discuss and align → `[d]` to decide (within plan)
 | **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 |
-| **nx-sync** | `/claude-nexus:nx-sync` | Core knowledge sync. Reflects source changes into .nexus/core/ docs |
+| **nx-sync** | `/claude-nexus:nx-sync` | Context sync. Reflects source changes into .nexus/context/ docs |
 
 ## Advanced
 
@@ -85,12 +88,10 @@ Typical flow: `[plan]` to discuss and align → `[d]` to decide (within plan)
 
 Claude-callable tools exposed by the Nexus MCP server.
 
-### Core (14 tools)
+### Core (12 tools)
 
 | Tool | Purpose |
 |------|---------|
-| `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, plan) |
 | `nx_task_list/add/update/close` | Task management + history.json archiving |
 | `nx_artifact_write` | Save artifacts (branch-isolated) |
@@ -143,30 +144,30 @@ Project knowledge and rules are stored under `.nexus/` and tracked by git.
 
 ```
 .nexus/
-├── core/               ← Project knowledge (4 layers)
-│   ├── identity/       ← Project identity and purpose
-│   ├── codebase/       ← Architecture and structure
-│   ├── reference/      ← Reference materials
-│   └── memory/         ← Session memory and context
-├── rules/              ← Team custom rules (created via nx_rules_write)
-└── config.json         ← Nexus configuration
+  memory/    — lessons learned, references
+  context/   — design principles, architecture philosophy
+  state/     — plan.json, tasks.json
+  rules/     — project custom rules
+  history.json
 ```
 
+- `memory/`, `context/`, `rules/` — git-tracked.
+- `state/` — runtime state. git-ignored.
+- `history.json` — cycle archive. git-tracked.
+
 </details>
 
 <details>
 <summary>Runtime State</summary>
 
-Runtime state is stored under `.nexus/state/` and is excluded from git. `history.json` is at `.nexus/` root and git-tracked.
+Runtime state is stored under `.nexus/state/` and is excluded from git.
 
 ```
-.nexus/
-├── history.json            ← Cycle archive (git-tracked, created by nx_task_close)
-└── state/                  ← Runtime state (git-ignored)
-    ├── tasks.json          ← Task list ([run] cycle)
-    ├── plan.json           ← Planning session ([plan] cycle)
-    ├── agent-tracker.json  ← Subagent lifecycle tracking
-    └── artifacts/          ← Artifacts
+.nexus/state/
+├── tasks.json          ← Task list ([run] cycle)
+├── plan.json           ← Planning session ([plan] cycle)
+├── agent-tracker.json  ← Subagent lifecycle tracking
+└── artifacts/          ← Artifacts
 ```
 
 </details>

package/README.md

@@ -22,7 +22,7 @@ claude plugin install claude-nexus@nexus
 
 **온보딩**
 
-`/claude-nexus:nx-init`을 처음 실행하면 프로젝트를 스캔해 `.nexus/core/`에 지식을 자동 생성합니다.
+`/claude-nexus:nx-init`을 처음 실행하면 프로젝트를 스캔해 `.nexus/`에 지식을 자동 생성합니다.
 
 > **Important**: 하나의 워크스페이스에서 동시에 여러 Claude Code 세션을 실행하는 것은 지원되지 않습니다. 상태 파일 충돌이 발생할 수 있습니다.
 
@@ -40,6 +40,9 @@ claude plugin install claude-nexus@nexus
 | `[d]` | 결정 기록 (plan 세션 내) | `응 그 방향으로 [d]` |
 | `[run]` | 실행 (서브에이전트 구성) | `[run] 결제 모듈 리팩토링` |
 | `[rule]` | 규칙 저장 | `[rule] npm 대신 bun 사용` |
+| `[m]` | 메모 추가 | `[m] 이 패턴은 나중에 참고` |
+| `[m:gc]` | 메모 정리 | `[m:gc]` |
+| `[sync]` | context/ 동기화 | `[sync]` |
 
 ## 에이전트
 
@@ -63,7 +66,7 @@ claude plugin install claude-nexus@nexus
 | **nx-run** | `[run]` | 동적 에이전트 구성 실행 |
 | **nx-init** | `/claude-nexus:nx-init` | 프로젝트 온보딩. 코드 스캔 → 지식 생성 |
 | **nx-setup** | `/claude-nexus:nx-setup` | 대화형 설정 |
-| **nx-sync** | `/claude-nexus:nx-sync` | 코어 지식 동기화. 소스 변경사항을 .nexus/core/ 문서에 반영 |
+| **nx-sync** | `/claude-nexus:nx-sync` | context/ 동기화. 소스 변경사항을 .nexus/context/ 문서에 반영 |
 
 ## 고급 기능
 
@@ -72,12 +75,10 @@ claude plugin install claude-nexus@nexus
 
 Claude가 직접 호출하는 도구입니다.
 
-### Core (14개)
+### Core (12개)
 
 | 도구 | 용도 |
 |------|------|
-| `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, 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/`) |
@@ -128,11 +129,18 @@ Gate 단일 모듈로 동작합니다.
 
 `.nexus/`에 프로젝트 지식과 런타임 상태를 저장합니다.
 
-- `core/` — 4계층 지식 (identity/codebase/reference/memory). git 추적.
-- `rules/` — 팀 커스텀 규칙. git 추적.
-- `config.json` — Nexus 설정. git 추적.
+```
+.nexus/
+  memory/    — 학습한 교훈, 참고 자료
+  context/   — 설계 원칙, 아키텍처 철학
+  state/     — plan.json, tasks.json
+  rules/     — 프로젝트 커스텀 규칙
+  history.json
+```
+
+- `memory/`, `context/`, `rules/` — git 추적.
+- `state/` — 런타임 상태. git 무시.
 - `history.json` — 사이클 아카이브. git 추적.
-- `state/` — 런타임 상태 (tasks, plan 등). git 무시.
 
 </details>
 

package/VERSION

@@ -1 +1 @@
-0.23.1
+0.24.0

package/agents/architect.md

@@ -48,7 +48,7 @@ When evaluating options:
 2. Is this the simplest solution that works? (YAGNI, avoid premature abstraction)
 3. What breaks if this goes wrong? (risk surface)
 4. Does this introduce new dependencies or coupling? (maintainability)
-5. Is there a precedent in the codebase or decisions log? (check nx_core_read, nx_context)
+5. Is there a precedent in the codebase or decisions log? (check .nexus/context/ and .nexus/memory/ via Read/Glob)
 
 ## Critical Review Process
 When reviewing code or design proposals:

package/agents/designer.md

@@ -47,7 +47,7 @@ When evaluating UX options:
 2. Is this the simplest interaction that accomplishes the goal?
 3. What confusion or frustration could this cause?
 4. Is this consistent with existing patterns in the product?
-5. Is there precedent in decisions log? (check nx_core_read, nx_context)
+5. Is there precedent in decisions log? (check .nexus/context/ and .nexus/memory/ via Read/Glob)
 
 ## Collaboration with Architect
 Architect owns technical structure; Designer owns user experience. These are complementary:

package/agents/researcher.md

@@ -119,14 +119,16 @@ All claims about impossibility, infeasibility, or platform limitations MUST incl
 When writing findings reports or other deliverables to a file, use `nx_artifact_write` (filename, content) instead of Write. This ensures the file is saved to the correct branch workspace.
 
 ## Reference Recording
-When you complete an investigation and find meaningful results, record them immediately using `nx_core_write(layer: "reference")`.
+When you complete an investigation and find meaningful results, consider whether they are worth preserving for future use.
 
 Record when:
 - You find a source with high reuse value (authoritative reference, key data, foundational paper)
 - You find a result that future researchers on this topic would need
 - You find a null result that would save future effort (searched extensively, found nothing on X)
 
-Do not defer recording. Record while the context is fresh, immediately after completing the search. The reference layer is a shared resource — your recordings benefit future investigations.
+To persist findings, either:
+- Suggest to the user that they use the `[m]` tag to save the finding to memory, or
+- Write directly to `.nexus/memory/{topic}.md` using the Write tool if you have permission
 
-Format for reference entries: include the research question, key findings, source URLs, and date searched.
+Format for memory entries: include the research question, key findings, source URLs, and date searched.
 </guidelines>

package/agents/strategist.md

@@ -47,7 +47,7 @@ When evaluating strategic options:
 2. How does this compare to what competitors offer?
 3. What is the adoption path — who uses this first and how does it spread?
 4. What is the strategic risk if this doesn't work?
-5. Is there precedent in decisions log? (check nx_core_read, nx_context)
+5. Is there precedent in decisions log? (check .nexus/context/ and .nexus/memory/ via Read/Glob)
 
 ## Collaboration with Lead
 Lead owns scope and project goals; Strategist informs those decisions with market reality: