claudecode-omc 4.8.4 → 4.9.4

package/docs/ko/REFERENCE.md

@@ -232,8 +232,6 @@ Task 도구를 통해 호출할 때는 항상 `oh-my-claudecode:` 접두사를
 | `orchestrate` | 멀티 에이전트 오케스트레이션 모드             | -                              |
 | `autopilot`   | 아이디어에서 작동하는 코드까지 완전 자율 실행 | `/oh-my-claudecode:autopilot`  |
 | `ultrawork`   | 병렬 에이전트를 통한 최대 성능                | `/oh-my-claudecode:ultrawork`  |
-| `ultrapilot`  | 3-5배 빠른 병렬 autopilot                     | `/oh-my-claudecode:ultrapilot` |
-| `swarm`       | 작업 클레이밍을 가진 N개의 조정된 에이전트    | `/oh-my-claudecode:swarm`      |
 | `pipeline`    | 순차적 에이전트 체이닝                        | `/oh-my-claudecode:pipeline`   |
 | ``            | 토큰 효율적 병렬 실행                         | `/oh-my-claudecode:`           |
 | `ralph`       | 완료될 때까지 자기 참조적 개발                | `/oh-my-claudecode:ralph`      |
@@ -281,8 +279,6 @@ Task 도구를 통해 호출할 때는 항상 `oh-my-claudecode:` 접두사를
 | `/oh-my-claudecode:orchestrate <task>`       | 멀티 에이전트 오케스트레이션 모드 활성화  |
 | `/oh-my-claudecode:autopilot <task>`         | 완전 자율 실행                            |
 | `/oh-my-claudecode:ultrawork <task>`         | 병렬 에이전트를 통한 최대 성능 모드       |
-| `/oh-my-claudecode:ultrapilot <task>`        | 병렬 autopilot (3-5배 빠름)               |
-| `/oh-my-claudecode:swarm <N>:<agent> <task>` | 조정된 에이전트 swarm                     |
 | `/oh-my-claudecode:pipeline <stages>`        | 순차적 에이전트 체이닝                    |
 | `/oh-my-claudecode: <task>`                  | 토큰 효율적 병렬 실행                     |
 | `/oh-my-claudecode:ralph-init <task>`        | 구조화된 작업 추적을 위한 PRD 초기화      |
@@ -317,9 +313,7 @@ oh-my-claudecode에는 Claude Code의 동작을 향상시키는 31개의 라이
 | `autopilot`       | 아이디어에서 작동하는 코드까지 완전 자율 실행    |
 | `ultrawork`       | 최대 병렬 에이전트 실행                          |
 | `ralph`           | 검증 완료까지 지속                               |
-| `ultrapilot`      | 파일 소유권이 있는 병렬 autopilot                |
 | `ultraqa`         | 목표 달성까지 QA 사이클링                        |
-| `swarm`           | SQLite 작업 클레이밍을 가진 조정된 멀티 에이전트 |
 | `mode-registry`   | 활성 실행 모드 추적 (ecomode 포함)               |
 | `persistent-mode` | 세션 간 모드 상태 유지                           |
 
@@ -377,7 +371,6 @@ oh-my-claudecode에는 Claude Code의 동작을 향상시키는 31개의 라이
 | `ultrawork`, `ulw`, `uw`                        | 병렬 에이전트 오케스트레이션 활성화 |
 | ``, `eco`, `efficient`, `save-tokens`, `budget` | 토큰 효율적 병렬 실행               |
 | `autopilot`, `build me`, `I want a`             | 완전 자율 실행                      |
-| `ultrapilot`, `parallel build`, `swarm build`   | 병렬 autopilot (3-5배 빠름)         |
 | `ralph`, `don't stop`, `must complete`          | 검증 완료까지 지속                  |
 | `plan this`, `plan the`                         | 플래닝 인터뷰 워크플로우            |
 | `ralplan`                                       | 반복적 플래닝 합의                  |
@@ -385,7 +378,6 @@ oh-my-claudecode에는 Claude Code의 동작을 향상시키는 31개의 라이
 | `analyze`, `investigate`, `debug`               | 심층 분석 모드                      |
 | `sciomc`                                        | 병렬 리서치 오케스트레이션          |
 | `tdd`, `test first`, `red green`                | TDD 워크플로우 강제                 |
-| `swarm N agents`                                | 조정된 에이전트 swarm               |
 | `pipeline`, `chain agents`                      | 순차적 에이전트 체이닝              |
 | `stop`, `cancel`, `abort`                       | 통합 취소                           |
 
@@ -409,9 +401,6 @@ analyze why the tests are failing
 # 자율 실행
 autopilot: build a todo app with React
 
-# 병렬 autopilot
-ultrapilot: build a fullstack todo app
-
 # 지속성 모드
 ralph: refactor the authentication module
 
@@ -421,9 +410,6 @@ plan this feature
 # TDD 워크플로우
 tdd: implement password validation
 
-# 조정된 swarm
-swarm 5 agents: fix all lint errors
-
 # 에이전트 체이닝
 pipeline: analyze → fix → test this bug
 ```
@@ -432,7 +418,7 @@ pipeline: analyze → fix → test this bug
 
 ## MCP 경로 경계 규칙
 
-MCP 도구 (`ask_codex`, `ask_gemini`)는 보안을 위해 엄격한 경로 경계를 적용합니다. `prompt_file`과 `output_file` 모두 `working_directory`를 기준으로 해석됩니다.
+MCP 도구는 보안을 위해 엄격한 경로 경계를 적용합니다. `prompt_file`과 `output_file` 모두 `working_directory`를 기준으로 해석됩니다.
 
 ### 기본 동작 (엄격 모드)
 

package/docs/partials/features.md

@@ -66,35 +66,6 @@ Project-level type checking via `lsp_diagnostics_directory` tool.
 
 Background agents can be resumed with full context via `resume-session` tool.
 
-## Ultrapilot (v3.4)
-
-Parallel autopilot with up to 20 concurrent workers for 3-5x faster execution.
-
-**Trigger:** "ultrapilot", "parallel build", "swarm build"
-
-**How it works:**
-1. Task decomposition engine breaks complex tasks into parallelizable subtasks
-2. File ownership coordinator assigns non-overlapping file sets to workers
-3. Workers execute in parallel, coordinator manages shared files
-4. Results integrated with conflict detection
-
-**Best for:** Multi-component systems, fullstack apps, large refactoring
-
-**State files:**
-- `.omc/state/ultrapilot-state.json` - Session state
-- `.omc/state/ultrapilot-ownership.json` - File ownership
-
-## Swarm (v3.4)
-
-N coordinated agents with atomic task claiming from shared pool.
-
-**Usage:** `/swarm 5:executor "fix all TypeScript errors"`
-
-**Features:**
-- Shared task list with pending/claimed/done status
-- 5-minute timeout per task with auto-release
-- Clean completion when all tasks done
-
 ## Pipeline (v3.4)
 
 Sequential agent chaining with data passing between stages.
@@ -117,7 +88,7 @@ Smart cancellation that auto-detects active mode.
 
 **Usage:** `/cancel` or just say "cancelomc", "stopomc"
 
-Auto-detects and cancels: autopilot, ultrapilot, ralph, ultrawork, ultraqa, swarm, pipeline
+Auto-detects and cancels: autopilot, ralph, ultrawork, ultraqa, pipeline
 Use `--force` or `--all` to clear ALL states.
 
 ## Verification Module (v3.4)
@@ -141,12 +112,10 @@ Standardized state file locations.
 |------|-----------|
 | ralph | `ralph-state.json` |
 | autopilot | `autopilot-state.json` |
-| ultrapilot | `ultrapilot-state.json` |
 | ultrawork | `ultrawork-state.json` |
 |  | `-state.json` |
 | ultraqa | `ultraqa-state.json` |
 | pipeline | `pipeline-state.json` |
-| swarm | `swarm-summary.json` + `swarm-active.marker` |
 
 **Important:** Never store OMC state in `~/.claude/` - that directory is reserved for Claude Code itself.
 

package/docs/partials/mode-hierarchy.md

@@ -11,16 +11,6 @@ autopilot (autonomous end-to-end)
 ├── includes: ultraqa (QA cycling)
 └── includes: plan (strategic thinking)
 
-ultrapilot (parallel autopilot)
-├── includes: file ownership partitioning
-├── includes: worker coordination (up to 20 workers)
-└── falls back to: autopilot (if not parallelizable)
-
-swarm (N-agent coordination)
-├── includes: SQLite task claiming
-├── includes: heartbeat monitoring
-└── orthogonal to: autopilot/ultrapilot (different paradigm)
-
  (token efficiency ONLY)
 └── modifies: agent tier selection (prefer haiku/sonnet)
     (does NOT include persistence - that's ralph's job)
@@ -38,9 +28,7 @@ ultrawork (parallelism engine)
 
 | Mode | Type | Includes | Mutually Exclusive With |
 |------|------|----------|------------------------|
-| autopilot | Standalone | ralph, ultraqa, plan | ultrapilot |
-| ultrapilot | Standalone | file ownership, workers | autopilot |
-| swarm | Standalone | SQLite claiming | - |
+| autopilot | Standalone | ralph, ultraqa, plan | - |
 | ralph | Wrapper | ultrawork | - |
 | ultrawork | Component | - | - |
 |  | Modifier | - | - |
@@ -51,7 +39,7 @@ ultrawork (parallelism engine)
 ```
 Want autonomous execution?
 ├── YES: Is task parallelizable into 3+ independent components?
-│   ├── YES: ultrapilot (parallel autopilot with file ownership)
+│   ├── YES: team N:executor (parallel autonomous with file ownership)
 │   └── NO: autopilot (sequential with ralph phases)
 └── NO: Want parallel execution with manual oversight?
     ├── YES: Do you want cost optimization?
@@ -62,7 +50,7 @@ Want autonomous execution?
         └── NO: Standard orchestration (delegate to agents directly)
 
 Have many similar independent tasks (e.g., "fix 47 errors")?
-└── YES: swarm (N agents claiming from task pool)
+└── YES: team N:executor (N agents claiming from task pool)
 ```
 
 ## Mode Differentiation Matrix
@@ -70,8 +58,7 @@ Have many similar independent tasks (e.g., "fix 47 errors")?
 | Mode | Best For | Parallelism | Persistence | Verification | File Ownership |
 |------|----------|-------------|-------------|--------------|----------------|
 | autopilot | "Build me X" | Via ralph | Yes | Yes | N/A |
-| ultrapilot | Multi-component | 20 workers | Yes | Yes | Partitioned |
-| swarm | Homogeneous tasks | N workers | Per-task | Per-task | Per-task |
+| team | Multi-component/homogeneous | N workers | Per-task | Per-task | Per-task |
 | ralph | "Don't stop" | Via ultrawork | Yes | Mandatory | N/A |
 | ultrawork | Parallel only | Yes | No | No | N/A |
 |  | Cost savings | Modifier | No | No | N/A |
@@ -79,8 +66,8 @@ Have many similar independent tasks (e.g., "fix 47 errors")?
 ## Quick Reference
 
 **Just want to build something?** → `autopilot`
-**Building multi-component system?** → `ultrapilot`
-**Fixing many similar issues?** → `swarm`
+**Building multi-component system?** → `team N:executor`
+**Fixing many similar issues?** → `team N:executor`
 **Want control over execution?** → `ultrawork`
 **Need verified completion?** → `ralph`
 **Want to save tokens?** → `` (combine with other modes)
@@ -93,7 +80,7 @@ Valid combinations:
 - `eco autopilot` = Full autonomous with cost optimization
 
 Invalid combinations:
-- `autopilot ultrapilot` = Mutually exclusive (both are standalone)
+- `autopilot team` = Mutually exclusive (both are standalone)
 - `` alone = Not useful (needs an execution mode)
 
 ## State Management
@@ -108,12 +95,10 @@ All mode state files use standardized locations:
 |------|-----------|
 | ralph | `ralph-state.json` |
 | autopilot | `autopilot-state.json` |
-| ultrapilot | `ultrapilot-state.json` |
 | ultrawork | `ultrawork-state.json` |
 |  | `-state.json` |
 | ultraqa | `ultraqa-state.json` |
 | pipeline | `pipeline-state.json` |
-| swarm | `swarm-summary.json` + `swarm-active.marker` |
 
 **Important:** Never store OMC state in `~/.claude/` - that directory is reserved for Claude Code itself.
 

package/docs/partials/verification-tiers.md

@@ -94,7 +94,7 @@ Estimated savings: ~40% reduction in verification costs by using tiered system v
 
 ## Usage in Modes
 
-All persistence modes (ralph, autopilot, ultrapilot) should use the tier-selector before spawning verification agents:
+All persistence modes (ralph, autopilot) should use the tier-selector before spawning verification agents:
 
 ```typescript
 import { selectVerificationTier, getVerificationAgent } from '../verification/tier-selector';

package/docs/plans/2026-02-26-skill-optimization-design.md

@@ -2,7 +2,7 @@
 
 **Date:** 2026-02-26
 **Scope:** oh-my-claudecode — full skill quality overhaul (description + structure + quality pipeline)
-**Inspiration:** oh-my-codex skill-development, skill-debugger, skill-quality-analyzer, skill-create patterns
+**Inspiration:** oh-my-codex skill-creator, skill-debugger, skill-quality-analyzer, skill-create patterns
 
 ---
 
@@ -16,7 +16,7 @@ The oh-my-claudecode skill ecosystem has three interconnected issues:
 
 3. **Codex-branded ported skills** — `skill-quality-analyzer` and `skill-tester` still reference "Codex CLI" and "Codex skill quality", which is confusing and slightly broken in the Claude Code context.
 
-4. **No writing standard for new skills** — No equivalent of oh-my-codex's `skill-development` guide exists for OMC. New skills get written ad hoc with inconsistent quality.
+4. **No writing standard for new skills** — No equivalent of oh-my-codex's `skill-creator` guide exists for OMC. New skills get written ad hoc with inconsistent quality.
 
 ---
 
@@ -86,7 +86,7 @@ skills/skill/
 
 ### Layer 3: `writing-skills` Skill (New)
 
-**OMC's equivalent of oh-my-codex's `skill-development`.**
+**OMC's equivalent of oh-my-codex's `skill-creator`.**
 
 ```
 skills/writing-skills/

package/docs/shared/features.md

@@ -66,35 +66,6 @@ Project-level type checking via `lsp_diagnostics_directory` tool.
 
 Background agents can be resumed with full context via `resume-session` tool.
 
-## Ultrapilot (v3.4)
-
-Parallel autopilot with up to 20 concurrent workers for 3-5x faster execution.
-
-**Trigger:** "ultrapilot", "parallel build", "swarm build"
-
-**How it works:**
-1. Task decomposition engine breaks complex tasks into parallelizable subtasks
-2. File ownership coordinator assigns non-overlapping file sets to workers
-3. Workers execute in parallel, coordinator manages shared files
-4. Results integrated with conflict detection
-
-**Best for:** Multi-component systems, fullstack apps, large refactoring
-
-**State files:**
-- `.omc/state/ultrapilot-state.json` - Session state
-- `.omc/state/ultrapilot-ownership.json` - File ownership
-
-## Swarm (v3.4)
-
-N coordinated agents with atomic task claiming from shared pool.
-
-**Usage:** `/swarm 5:executor "fix all TypeScript errors"`
-
-**Features:**
-- Shared task list with pending/claimed/done status
-- 5-minute timeout per task with auto-release
-- Clean completion when all tasks done
-
 ## Pipeline (v3.4)
 
 Sequential agent chaining with data passing between stages.
@@ -117,7 +88,7 @@ Smart cancellation that auto-detects active mode.
 
 **Usage:** `/cancel` or just say "cancelomc", "stopomc"
 
-Auto-detects and cancels: autopilot, ultrapilot, ralph, ultrawork, ultraqa, swarm, pipeline
+Auto-detects and cancels: autopilot, ralph, ultrawork, ultraqa, pipeline
 Use `--force` or `--all` to clear ALL states.
 
 ## Verification Module (v3.4)
@@ -141,12 +112,10 @@ Standardized state file locations.
 |------|-----------|
 | ralph | `ralph-state.json` |
 | autopilot | `autopilot-state.json` |
-| ultrapilot | `ultrapilot-state.json` |
 | ultrawork | `ultrawork-state.json` |
 |  | `-state.json` |
 | ultraqa | `ultraqa-state.json` |
 | pipeline | `pipeline-state.json` |
-| swarm | `swarm-summary.json` + `swarm-active.marker` |
 
 **Important:** Never store OMC state in `~/.claude/` - that directory is reserved for Claude Code itself.
 

package/docs/shared/mode-hierarchy.md

@@ -11,16 +11,6 @@ autopilot (autonomous end-to-end)
 ├── includes: ultraqa (QA cycling)
 └── includes: plan (strategic thinking)
 
-ultrapilot (parallel autopilot)
-├── includes: file ownership partitioning
-├── includes: worker coordination (up to 20 workers)
-└── falls back to: autopilot (if not parallelizable)
-
-swarm (N-agent coordination)
-├── includes: SQLite task claiming
-├── includes: heartbeat monitoring
-└── orthogonal to: autopilot/ultrapilot (different paradigm)
-
  (token efficiency ONLY)
 └── modifies: agent tier selection (prefer haiku/sonnet)
     (does NOT include persistence - that's ralph's job)
@@ -38,9 +28,7 @@ ultrawork (parallelism engine)
 
 | Mode | Type | Includes | Mutually Exclusive With |
 |------|------|----------|------------------------|
-| autopilot | Standalone | ralph, ultraqa, plan | ultrapilot |
-| ultrapilot | Standalone | file ownership, workers | autopilot |
-| swarm | Standalone | SQLite claiming | - |
+| autopilot | Standalone | ralph, ultraqa, plan | - |
 | ralph | Wrapper | ultrawork | - |
 | ultrawork | Component | - | - |
 |  | Modifier | - | - |
@@ -51,7 +39,7 @@ ultrawork (parallelism engine)
 ```
 Want autonomous execution?
 ├── YES: Is task parallelizable into 3+ independent components?
-│   ├── YES: ultrapilot (parallel autopilot with file ownership)
+│   ├── YES: team N:executor (parallel autonomous with file ownership)
 │   └── NO: autopilot (sequential with ralph phases)
 └── NO: Want parallel execution with manual oversight?
     ├── YES: Do you want cost optimization?
@@ -62,7 +50,7 @@ Want autonomous execution?
         └── NO: Standard orchestration (delegate to agents directly)
 
 Have many similar independent tasks (e.g., "fix 47 errors")?
-└── YES: swarm (N agents claiming from task pool)
+└── YES: team N:executor (N agents claiming from task pool)
 ```
 
 ## Mode Differentiation Matrix
@@ -70,8 +58,7 @@ Have many similar independent tasks (e.g., "fix 47 errors")?
 | Mode | Best For | Parallelism | Persistence | Verification | File Ownership |
 |------|----------|-------------|-------------|--------------|----------------|
 | autopilot | "Build me X" | Via ralph | Yes | Yes | N/A |
-| ultrapilot | Multi-component | 20 workers | Yes | Yes | Partitioned |
-| swarm | Homogeneous tasks | N workers | Per-task | Per-task | Per-task |
+| team | Multi-component/homogeneous | N workers | Per-task | Per-task | Per-task |
 | ralph | "Don't stop" | Via ultrawork | Yes | Mandatory | N/A |
 | ultrawork | Parallel only | Yes | No | No | N/A |
 |  | Cost savings | Modifier | No | No | N/A |
@@ -79,8 +66,8 @@ Have many similar independent tasks (e.g., "fix 47 errors")?
 ## Quick Reference
 
 **Just want to build something?** → `autopilot`
-**Building multi-component system?** → `ultrapilot`
-**Fixing many similar issues?** → `swarm`
+**Building multi-component system?** → `team N:executor`
+**Fixing many similar issues?** → `team N:executor`
 **Want control over execution?** → `ultrawork`
 **Need verified completion?** → `ralph`
 **Want to save tokens?** → `` (combine with other modes)
@@ -93,7 +80,7 @@ Valid combinations:
 - `eco autopilot` = Full autonomous with cost optimization
 
 Invalid combinations:
-- `autopilot ultrapilot` = Mutually exclusive (both are standalone)
+- `autopilot team` = Mutually exclusive (both are standalone)
 - `` alone = Not useful (needs an execution mode)
 
 ## State Management
@@ -108,12 +95,10 @@ All mode state files use standardized locations:
 |------|-----------|
 | ralph | `ralph-state.json` |
 | autopilot | `autopilot-state.json` |
-| ultrapilot | `ultrapilot-state.json` |
 | ultrawork | `ultrawork-state.json` |
 |  | `-state.json` |
 | ultraqa | `ultraqa-state.json` |
 | pipeline | `pipeline-state.json` |
-| swarm | `swarm-summary.json` + `swarm-active.marker` |
 
 **Important:** Never store OMC state in `~/.claude/` - that directory is reserved for Claude Code itself.
 

package/docs/shared/verification-tiers.md

@@ -94,7 +94,7 @@ Estimated savings: ~40% reduction in verification costs by using tiered system v
 
 ## Usage in Modes
 
-All persistence modes (ralph, autopilot, ultrapilot) should use the tier-selector before spawning verification agents:
+All persistence modes (ralph, autopilot) should use the tier-selector before spawning verification agents:
 
 ```typescript
 import { selectVerificationTier, getVerificationAgent } from '../verification/tier-selector';

package/hooks/hooks.json

@@ -7,12 +7,12 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/keyword-detector.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/keyword-detector.mjs",
             "timeout": 5
           },
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/skill-injector.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/skill-injector.mjs",
             "timeout": 3
           }
         ]
@@ -24,12 +24,12 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/session-start.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/session-start.mjs",
             "timeout": 5
           },
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/project-memory-session.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/project-memory-session.mjs",
             "timeout": 5
           }
         ]
@@ -39,7 +39,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/setup-init.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/setup-init.mjs",
             "timeout": 30
           }
         ]
@@ -49,7 +49,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/setup-maintenance.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/setup-maintenance.mjs",
             "timeout": 60
           }
         ]
@@ -61,17 +61,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/pre-tool-enforcer.mjs\"",
-            "timeout": 3
-          }
-        ]
-      },
-      {
-        "matcher": "ExitPlanMode",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/context-safety.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/pre-tool-enforcer.mjs",
             "timeout": 3
           }
         ]
@@ -83,7 +73,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/permission-handler.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/permission-handler.mjs",
             "timeout": 5
           }
         ]
@@ -95,12 +85,12 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/post-tool-verifier.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/post-tool-verifier.mjs",
             "timeout": 3
           },
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/project-memory-posttool.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/project-memory-posttool.mjs",
             "timeout": 3
           }
         ]
@@ -112,7 +102,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/post-tool-use-failure.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/post-tool-use-failure.mjs",
             "timeout": 3
           }
         ]
@@ -124,7 +114,7 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/subagent-tracker.mjs\" start",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/subagent-tracker.mjs start",
             "timeout": 3
           }
         ]
@@ -136,12 +126,12 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/subagent-tracker.mjs\" stop",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/subagent-tracker.mjs stop",
             "timeout": 5
           },
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/verify-deliverables.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/verify-deliverables.mjs",
             "timeout": 5
           }
         ]
@@ -153,12 +143,12 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/pre-compact.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/pre-compact.mjs",
             "timeout": 10
           },
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/project-memory-precompact.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/project-memory-precompact.mjs",
             "timeout": 5
           }
         ]
@@ -170,17 +160,17 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/context-guard-stop.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/context-guard-stop.mjs",
             "timeout": 5
           },
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/persistent-mode.cjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/persistent-mode.cjs",
             "timeout": 10
           },
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/code-simplifier.mjs\"",
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/code-simplifier.mjs",
             "timeout": 5
           }
         ]
@@ -192,8 +182,8 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/run.cjs\" \"${CLAUDE_PLUGIN_ROOT}/scripts/session-end.mjs\"",
-            "timeout": 10
+            "command": "node \"$CLAUDE_PLUGIN_ROOT\"/scripts/run.cjs \"$CLAUDE_PLUGIN_ROOT\"/scripts/session-end.mjs",
+            "timeout": 30
           }
         ]
       }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claudecode-omc",
-  "version": "4.8.4",
+  "version": "4.9.4",
   "description": "Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode",
   "type": "module",
   "main": "dist/index.js",

package/scripts/cleanup-orphans.mjs

@@ -71,20 +71,23 @@ function findOrphanProcesses(filterTeam) {
       const output = execSync('ps aux', { encoding: 'utf-8', timeout: 10000 });
 
       for (const line of output.split('\n')) {
-        // Match claude agent processes with team context
-        if ((line.includes('claude') || line.includes('node')) &&
-            (line.includes('--team-name') || line.includes('team_name'))) {
-
-          // Restrict team name match to valid slug characters
-          const match = line.match(/--team-name[=\s]+([\w][\w-]{0,63})/i) || line.match(/team_name[=:]\s*"?([\w][\w-]{0,63})"?/i);
-          if (match) {
-            const procTeam = match[1];
+        // Match OMC agent processes with team context (exclude bare 'node' to avoid over-matching)
+        if ((line.includes('claude') || line.includes('codex') || line.includes('gemini') || line.includes('omc') || line.includes('oh-my-claude'))) {
+          // Restrict team name match to valid slug characters.
+          // Support both native TeamDelete-style args and tmux worker env assignments.
+          const match =
+            line.match(/--team-name[=\s]+([\w][\w-]{0,63})/i)
+            || line.match(/team_name[=:]\s*"?([\w][\w-]{0,63})"?/i)
+            || line.match(/OM[CX]_TEAM_NAME=(['"]?)([\w][\w-]{0,63})\1/i)
+            || line.match(/OM[CX]_TEAM_WORKER=(['"]?)([\w][\w-]{0,63})\/worker-\d+\1/i);
+          const procTeam = match?.[2] || match?.[1];
+          if (procTeam) {
             if (filterTeam && procTeam !== filterTeam) continue;
 
             const parts = line.trim().split(/\s+/);
             const pid = parseInt(parts[1], 10);
             if (pid && pid !== process.pid && pid !== process.ppid) {
-              orphans.push({ pid, team: procTeam, cmd: line.trim().substring(0, 200) });
+              orphans.push({ pid, team: procTeam, cmd: '(redacted)' });
             }
           }
         }