uctm 1.4.0 → 1.5.0

package/.claude-plugin/plugin.json

@@ -0,0 +1,29 @@
+{
+  "name": "uc-taskmanager",
+  "version": "1.4.0",
+  "agents": [
+    "./agents/specifier.md",
+    "./agents/planner.md",
+    "./agents/scheduler.md",
+    "./agents/builder.md",
+    "./agents/verifier.md",
+    "./agents/committer.md"
+  ],
+  "description": "SDD WORK-PIPELINE Agent — Requirements analysis & development 6-agent full pipeline with DAG-based orchestration and sliding window context management",
+  "author": {
+    "name": "UCJung",
+    "url": "https://github.com/UCJung"
+  },
+  "homepage": "https://github.com/UCJung/uc-taskmanager-claude-agent",
+  "repository": "https://github.com/UCJung/uc-taskmanager-claude-agent",
+  "license": "GPL-3.0",
+  "keywords": [
+    "task-manager",
+    "pipeline",
+    "sub-agents",
+    "sdd",
+    "dag-orchestration",
+    "work-pipeline",
+    "automation"
+  ]
+}

package/agents/agent-flow.md

@@ -30,39 +30,35 @@
 1. Invoke specifier → creates Requirement.md + PLAN.md + TASK-00 + returns builder dispatch XML
 2. ⛔ STOP — Present summary to user and WAIT for approval (do NOT invoke builder)
 3. Invoke builder (dispatch XML as prompt) — includes self-check
-4. Invoke committer (builder result as prompt)
+4. Invoke verifier+committer (builder result as prompt) — verify then commit in one spawn
 ```
 
-> Verifier skipped: Builder performs self-check (build/lint), so separate verification is unnecessary for a single TASK.
+> Verifier+Committer combined: single spawn performs verification, then creates result.md and git commit.
 
 ---
 
 ## Pipeline Mode (Separate Planner Invocation)
 
 ```
-1. Invoke specifier → creates Requirement.md + returns planner dispatch XML
-2. ⛔ STOP — Present Requirement.md summary and WAIT for planning approval
-3. Invoke planner (dispatch XML as prompt) → creates PLAN.md + TASK-NN + determines execution-mode
-4. ⛔ STOP — Present PLAN.md + TASK list and WAIT for development approval
-5. Invoke builder (per-TASK dispatch XML as prompt)
-6. Invoke verifier (builder result as prompt)
-7. Invoke committer (verifier result as prompt)
+1. Invoke specifier+planner (single spawn) → creates Requirement.md + PLAN.md + TASK-NN + determines execution-mode
+2. ⛔ STOP — Present Requirement.md + PLAN.md + TASK list and WAIT for approval
+3. Invoke builder (per-TASK dispatch XML as prompt)
+4. Invoke verifier+committer (builder result as prompt) — verify then commit in one spawn
 ```
 
+> Specifier+Planner combined: specifier.md role first (Requirement.md), then planner.md role (PLAN.md + TASKs) in one spawn.
+
 ---
 
 ## Full Mode (With Scheduler)
 
 ```
-1. Invoke specifier → creates Requirement.md + returns planner dispatch XML
-2. ⛔ STOP — Present Requirement.md summary and WAIT for planning approval
-3. Invoke planner → PLAN.md + TASK decomposition + execution-mode: full
-4. ⛔ STOP — Present PLAN.md + TASK list and WAIT for development approval
-5. Invoke scheduler → DAG analysis + READY TASK + returns builder dispatch XML
-6. Invoke builder (dispatch XML as prompt) → implementation
-7. Invoke verifier (builder result as prompt) → verification
-8. Invoke committer (verifier result as prompt) → commit
-9. If incomplete TASKs remain, return to step 5
+1. Invoke specifier+planner (single spawn) → Requirement.md + PLAN.md + TASKs + execution-mode: full
+2. ⛔ STOP — Present Requirement.md + PLAN.md + TASK list and WAIT for approval
+3. Invoke scheduler → DAG analysis + READY TASK + returns builder dispatch XML
+4. Invoke builder (dispatch XML as prompt) → implementation
+5. Invoke verifier+committer (builder result as prompt) → verify then commit in one spawn
+6. If incomplete TASKs remain, return to step 3
 ```
 
 Parallel execution: When scheduler returns multiple READY TASKs, invoke builders concurrently.
@@ -75,32 +71,81 @@ Resume pipeline for a WORK that already has PLAN.md + TASKs:
 
 ```
 1. Invoke scheduler → check READY TASKs + return builder dispatch XML
-2. Execute builder → verifier → committer in sequence
-3. If incomplete TASKs remain, return to step 1
+2. Invoke builder → implementation
+3. Invoke verifier+committer → verify then commit in one spawn
+4. If incomplete TASKs remain, return to step 1
+```
+
+---
+
+## Combined Agent Invocation
+
+### Specifier+Planner (single spawn)
+
+When invoking specifier in pipeline/full mode, include both agent definitions:
+
+```
+Prompt to agent:
+  "You will perform two roles in sequence.
+
+   Role 1 — Specifier: Read specifier.md and create Requirement.md.
+   Role 2 — Planner: Read planner.md and create PLAN.md + TASK files.
+
+   Execute Role 1 first, then Role 2. Return the combined result."
+```
+
+- Use specifier's model (opus) for the spawn
+- Agent reads both specifier.md and planner.md from REFERENCES_DIR
+- Returns: Requirement.md + PLAN.md + TASK files + execution-mode
+
+### Verifier+Committer (single spawn)
+
+When invoking verification after builder completes:
+
+```
+Prompt to agent:
+  "You will perform two roles in sequence.
+
+   Role 1 — Verifier: Read verifier.md and verify build/lint/test.
+   Role 2 — Committer: Read committer.md and create result.md + git commit.
+
+   Execute Role 1 first. If verification PASSES, execute Role 2.
+   If verification FAILS, skip Role 2 and return FAIL result."
 ```
 
+- Use verifier's model (haiku) for the spawn
+- Agent reads both verifier.md and committer.md from REFERENCES_DIR
+- On PASS: returns verification result + commit hash
+- On FAIL: returns verification failure only (no commit)
+
 ---
 
 ## Agent Role Summary
 
-| Agent | Return Value | Invoked By |
-|-------|-------------|------------|
-| specifier | Requirement.md + (when assumed) PLAN.md/TASK + dispatch XML | Main Claude |
-| planner | PLAN.md/TASK files created + execution-mode | Main Claude |
-| scheduler | READY TASK + dispatch XML | Main Claude |
-| builder | task-result XML (including context-handoff) | Main Claude |
-| verifier | task-result XML | Main Claude |
-| committer | task-result XML + commit hash | Main Claude |
+| Agent | Role | Model | Combined With |
+|-------|------|-------|---------------|
+| specifier | Requirement analysis | opus | + planner (pipeline/full) |
+| planner | PLAN + TASK decomposition | opus | combined into specifier spawn |
+| scheduler | DAG management + dispatch | haiku | standalone |
+| builder | Code implementation | sonnet | standalone |
+| verifier | Build/lint/test verification | haiku | + committer |
+| committer | Result report + git commit | haiku | combined into verifier spawn |
 
 ---
 
-## Sub-agent Invocation Count by Mode
+## Sub-agent Spawn Count by Mode
+
+| Mode | Spec+Plan | Scheduler | Builder | Veri+Commit | Total |
+|------|:---------:|:---------:|:-------:|:-----------:|:-----:|
+| direct | 1 (assumed) | — | 1 | 1 | **3** |
+| pipeline | 1 (combined) | — | 1 | 1 | **3** |
+| full (N TASKs) | 1 (combined) | 1 | N | N | **2 + 2N** |
 
-| Mode | Specifier | Planner | Scheduler | Builder | Verifier | Committer | Total |
-|------|:---------:|:-------:|:---------:|:-------:|:--------:|:---------:|:-----:|
-| direct | O (assumed) | X | X | O | X | O | **3** |
-| pipeline | O | O | X | O | O | O | **5** |
-| full | O | O | O | O | O | O | **6** |
+**Before vs After (6 TASKs):**
+
+| | Before | After | Reduction |
+|---|:---:|:---:|:---:|
+| Spawns | 2 + 3×6 = 20 | 2 + 2×6 = 14 | **-30%** |
 
 ---
 
@@ -113,13 +158,15 @@ Resume pipeline for a WORK that already has PLAN.md + TASKs:
 | Mode | Approvals | Timing | What to show user |
 |------|:---------:|--------|-------------------|
 | direct | 1 | After Specifier completes | Requirement.md + PLAN.md + TASK-00.md summary |
-| pipeline/full | 2 | After Specifier → After Planner | 1st: Requirement.md summary, 2nd: PLAN.md + TASK list |
+| pipeline/full | 1 | After Specifier+Planner completes | Requirement.md + PLAN.md + TASK list |
 | auto-approve | 0 | — | Skip all approval gates |
 
+> Note: pipeline/full now has **1 approval** (not 2), since specifier and planner run in one spawn.
+
 **How to request approval:**
-1. Present a summary of what the specifier/planner created (files, scope, execution-mode)
+1. Present a summary of what the specifier+planner created (files, scope, execution-mode)
 2. Ask: "Proceed?" or equivalent
-3. **WAIT for user response** — do NOT invoke builder/planner until approved
+3. **WAIT for user response** — do NOT invoke builder until approved
 
 ---
 
@@ -204,13 +251,11 @@ If REFERENCES_DIR is not available (e.g., npm installation without plugin), sub-
 ### Flow Example
 
 ```
-specifier (no ref-cache in) → reads files → returns task-result with <ref-cache>
-  ↓ Main Claude copies <ref-cache> into dispatch
-planner (ref-cache in) → skips file reads → returns task-result with <ref-cache>
+specifier+planner (no ref-cache in) → reads files → returns task-result with <ref-cache>
   ↓ Main Claude copies <ref-cache> into dispatch
 builder (ref-cache in) → skips file reads → returns task-result with <ref-cache>
   ↓ Main Claude copies <ref-cache> into dispatch
-verifier → committer → ...
+verifier+committer (ref-cache in) → skips file reads → commit
 ```
 
 ### Phase 2: Selective Section Delivery
@@ -221,12 +266,10 @@ Instead of passing full reference files, Main Claude extracts only the sections
 
 | Agent | shared-prompt-sections | file-content-schema | xml-schema | context-policy | work-activity-log |
 |-------|:---:|:---:|:---:|:---:|:---:|
-| **specifier** | §1,§7,§8,§9,§11 | §0,§1,§2,§3 | §1,§3 | — | full |
-| **planner** | §1,§2,§11 | §1,§2,§3 | — | — | full |
+| **specifier+planner** | §1,§2,§7,§8,§9,§11 | §0,§1,§2,§3 | §1,§3 | — | full |
 | **scheduler** | §4,§8,§10 | §1,§6 | §1,§3,§4,§5 | full | full |
 | **builder** | §1,§2,§10,§12 | §2,§3 | §1,§2,§4 | Builder section | full |
-| **verifier** | §1,§2,§12 | — | §1,§2,§4 | Verifier section | full |
-| **committer** | §1,§2,§8,§10 | §3,§4,§5,§6,§7 | §1,§2,§4 | Committer+Retry | full |
+| **verifier+committer** | §1,§2,§8,§10,§12 | §3,§4,§5,§6,§7 | §1,§2,§4 | Verifier+Committer | full |
 
 **Delivery format**: Condense each `<ref key="">` to contain only the needed sections, not the full file. Use one-line summaries for simple rules, keep full content only for templates and code blocks.
 

package/agents/ko/agent-flow.md

@@ -30,39 +30,35 @@
 1. specifier 호출 → Requirement.md + PLAN.md + TASK-00 생성 + builder dispatch XML 반환
 2. ⛔ STOP — 산출물 요약을 사용자에게 제시하고 승인을 기다린다 (builder 호출 금지)
 3. builder 호출 (dispatch XML을 prompt로) — self-check 포함
-4. committer 호출 (builder 결과를 prompt로)
+4. verifier+committer 호출 (builder 결과를 prompt로) — 단일 spawn에서 검증 후 커밋
 ```
 
-> Verifier 생략: Builder가 self-check(build/lint)를 수행하므로 단일 TASK에서 별도 검증 불필요.
+> Verifier+Committer 통합: 단일 spawn에서 검증 수행 후 result.md 생성 + git commit.
 
 ---
 
 ## pipeline 모드 (Planner 별도 호출)
 
 ```
-1. specifier 호출 → Requirement.md 생성 + planner dispatch XML 반환
-2. ⛔ STOP — Requirement.md 요약을 제시하고 기획 승인을 기다린다
-3. planner 호출 (dispatch XML을 prompt로) → PLAN.md + TASK-NN 생성 + execution-mode 결정
-4. ⛔ STOP — PLAN.md + TASK 목록을 제시하고 개발 승인을 기다린다
-5. builder 호출 (TASK별 dispatch XML을 prompt로)
-6. verifier 호출 (builder 결과를 prompt로)
-7. committer 호출 (verifier 결과를 prompt로)
+1. specifier+planner 호출 (단일 spawn) → Requirement.md + PLAN.md + TASK-NN 생성 + execution-mode 결정
+2. ⛔ STOP — Requirement.md + PLAN.md + TASK 목록을 제시하고 승인을 기다린다
+3. builder 호출 (TASK별 dispatch XML을 prompt로)
+4. verifier+committer 호출 (builder 결과를 prompt로) — 단일 spawn에서 검증 후 커밋
 ```
 
+> Specifier+Planner 통합: specifier.md 역할 (Requirement.md) 수행 후 planner.md 역할 (PLAN.md + TASKs) 순차 수행.
+
 ---
 
 ## full 모드 (Scheduler 포함)
 
 ```
-1. specifier 호출 → Requirement.md 생성 + planner dispatch XML 반환
-2. ⛔ STOP — Requirement.md 요약을 제시하고 기획 승인을 기다린다
-3. planner 호출 → PLAN.md + TASK 분해 + execution-mode: full 결정
-4. ⛔ STOP — PLAN.md + TASK 목록을 제시하고 개발 승인을 기다린다
-5. scheduler 호출 → DAG 분석 + READY TASK + builder dispatch XML 반환
-6. builder 호출 (dispatch XML을 prompt로) → 구현
-7. verifier 호출 (builder 결과를 prompt로) → 검증
-8. committer 호출 (verifier 결과를 prompt로) → commit
-9. 미완료 TASK 있으면 5번으로 돌아감
+1. specifier+planner 호출 (단일 spawn) → Requirement.md + PLAN.md + TASK 분해 + execution-mode: full
+2. ⛔ STOP — Requirement.md + PLAN.md + TASK 목록을 제시하고 승인을 기다린다
+3. scheduler 호출 → DAG 분석 + READY TASK + builder dispatch XML 반환
+4. builder 호출 (dispatch XML을 prompt로) → 구현
+5. verifier+committer 호출 (builder 결과를 prompt로) → 단일 spawn에서 검증 후 커밋
+6. 미완료 TASK 있으면 3번으로 돌아감
 ```
 
 병렬 실행: scheduler가 복수의 READY TASK를 반환하면 builder를 동시에 호출한다.
@@ -75,32 +71,81 @@
 
 ```
 1. scheduler 호출 → READY TASK 확인 + builder dispatch XML 반환
-2. builder → verifier → committer 순서대로 실행
-3. 미완료 TASK 있으면 1번으로 돌아감
+2. builder 호출 → 구현
+3. verifier+committer 호출 → 단일 spawn에서 검증 후 커밋
+4. 미완료 TASK 있으면 1번으로 돌아감
 ```
 
 ---
 
+## 통합 에이전트 호출
+
+### Specifier+Planner (단일 spawn)
+
+pipeline/full 모드에서 specifier 호출 시 양쪽 에이전트 정의를 포함:
+
+```
+에이전트에 전달할 프롬프트:
+  "두 가지 역할을 순서대로 수행하라.
+
+   역할 1 — Specifier: specifier.md를 읽고 Requirement.md를 생성하라.
+   역할 2 — Planner: planner.md를 읽고 PLAN.md + TASK 파일을 생성하라.
+
+   역할 1을 먼저 수행한 후 역할 2를 수행하라. 통합 결과를 반환하라."
+```
+
+- specifier의 모델(opus)로 spawn
+- REFERENCES_DIR에서 specifier.md와 planner.md 양쪽 참조
+- 반환: Requirement.md + PLAN.md + TASK 파일 + execution-mode
+
+### Verifier+Committer (단일 spawn)
+
+builder 완료 후 검증 호출 시:
+
+```
+에이전트에 전달할 프롬프트:
+  "두 가지 역할을 순서대로 수행하라.
+
+   역할 1 — Verifier: verifier.md를 읽고 build/lint/test를 검증하라.
+   역할 2 — Committer: committer.md를 읽고 result.md를 생성하고 git commit하라.
+
+   역할 1을 먼저 수행하라. 검증 통과 시 역할 2를 수행하라.
+   검증 실패 시 역할 2를 건너뛰고 FAIL 결과만 반환하라."
+```
+
+- verifier의 모델(haiku)로 spawn
+- REFERENCES_DIR에서 verifier.md와 committer.md 양쪽 참조
+- 통과 시: 검증 결과 + commit hash 반환
+- 실패 시: 검증 실패만 반환 (커밋 없음)
+
+---
+
 ## 에이전트 역할 요약
 
-| 에이전트 | 반환값 | 호출 주체 |
-|---------|-------|---------|
-| specifier | Requirement.md + (겸임 시) PLAN.md/TASK + dispatch XML | Main Claude |
-| planner | PLAN.md/TASK 파일 생성 완료 + execution-mode | Main Claude |
-| scheduler | READY TASK + dispatch XML | Main Claude |
-| builder | task-result XML (context-handoff 포함) | Main Claude |
-| verifier | task-result XML | Main Claude |
-| committer | task-result XML + commit hash | Main Claude |
+| 에이전트 | 역할 | 모델 | 통합 대상 |
+|---------|------|------|----------|
+| specifier | 요구사항 분석 | opus | + planner (pipeline/full) |
+| planner | PLAN + TASK 분해 | opus | specifier spawn에 통합 |
+| scheduler | DAG 관리 + dispatch | haiku | 단독 |
+| builder | 코드 구현 | sonnet | 단독 |
+| verifier | build/lint/test 검증 | haiku | + committer |
+| committer | 결과 보고 + git commit | haiku | verifier spawn에 통합 |
 
 ---
 
-## 모드별 서브에이전트 호출 횟수
+## 모드별 서브에이전트 Spawn 횟수
+
+| 모드 | Spec+Plan | Scheduler | Builder | Veri+Commit | 합계 |
+|------|:---------:|:---------:|:-------:|:-----------:|:----:|
+| direct | 1 (겸임) | — | 1 | 1 | **3** |
+| pipeline | 1 (통합) | — | 1 | 1 | **3** |
+| full (N TASK) | 1 (통합) | 1 | N | N | **2 + 2N** |
 
-| 모드 | Specifier | Planner | Scheduler | Builder | Verifier | Committer | 합계 |
-|------|:---------:|:-------:|:---------:|:-------:|:--------:|:---------:|:----:|
-| direct | O (겸임) | X | X | O | X | O | **3회** |
-| pipeline | O | O | X | O | O | O | **5회** |
-| full | O | O | O | O | O | O | **6회** |
+**Before vs After (6 TASK 기준):**
+
+| | Before | After | 감소율 |
+|---|:---:|:---:|:---:|
+| Spawn 횟수 | 2 + 3×6 = 20 | 2 + 2×6 = 14 | **-30%** |
 
 ---
 
@@ -113,13 +158,15 @@
 | 모드 | 승인 횟수 | 시점 | 사용자에게 보여줄 내용 |
 |------|:---------:|------|----------------------|
 | direct | 1회 | Specifier 완료 후 | Requirement.md + PLAN.md + TASK-00.md 요약 |
-| pipeline/full | 2회 | Specifier 후 → Planner 후 | 1차: Requirement.md 요약, 2차: PLAN.md + TASK 목록 |
+| pipeline/full | 1회 | Specifier+Planner 완료 후 | Requirement.md + PLAN.md + TASK 목록 |
 | 자동 승인 | 0회 | — | 모든 승인 게이트 생략 |
 
+> 참고: pipeline/full 승인이 **2회에서 1회**로 줄었다 (specifier+planner가 단일 spawn이므로).
+
 **승인 요청 방법:**
-1. specifier/planner가 생성한 산출물 요약을 제시 (파일, 범위, execution-mode)
+1. specifier+planner가 생성한 산출물 요약을 제시 (파일, 범위, execution-mode)
 2. "진행할까요?" 또는 동등한 질문
-3. **사용자 응답을 기다린다** — 승인 전까지 builder/planner를 호출하지 마라
+3. **사용자 응답을 기다린다** — 승인 전까지 builder를 호출하지 마라
 
 ---
 

package/agents/ko/planner.md

@@ -57,9 +57,10 @@ WORK (일)          — 사용자 요청의 목표 단위
 
 ### 3-2. 프로젝트 탐색 (Discovery Process)
 
-```bash
-# 1. 기존 WORK 확인
-ls -d works/WORK-* 2>/dev/null | sort -V | tail -1
+```
+# 1. 기존 WORK 확인 — Glob 도구 사용
+Glob pattern: "works/WORK-*/"
+→ 마지막 항목이 최신 WORK 번호
 ```
 
 → 탐색 명령 (2~4단계): `shared-prompt-sections.md` § 11 참조

package/agents/ko/shared-prompt-sections.md

@@ -28,7 +28,7 @@ elif [ -f "Cargo.toml" ]; then
 elif [ -f "go.mod" ]; then
   go build ./... 2>&1
 elif [ -f "pyproject.toml" ] || [ -f "setup.py" ]; then
-  python -m py_compile $(find . -name "*.py" -not -path "*/venv/*" | head -20) 2>&1
+  python -m py_compile $(find . -maxdepth 3 -name "*.py" -not -path "*/venv/*" 2>/dev/null) 2>&1
 elif [ -f "Makefile" ]; then
   make build 2>&1 || make 2>&1
 fi
@@ -68,22 +68,20 @@ works/{WORK_ID}/
 
 ## § 4. File System Discovery Scripts
 
-```bash
+```
 # 미완료 TASK가 있는 최신 WORK 찾기
-for dir in $(ls -d works/WORK-* 2>/dev/null | sort -V -r); do
-  WORK_ID=$(basename $dir)
-  TOTAL=$(ls $dir/TASK-*.md 2>/dev/null | grep -v result | wc -l)
-  DONE=$(ls $dir/TASK-*_result.md 2>/dev/null | wc -l)
-  [ "$DONE" -lt "$TOTAL" ] && echo "$WORK_ID" && break
-done
+# Glob 도구 사용: pattern "works/WORK-*/" → 전체 WORK 디렉토리 목록 (정렬됨)
+# 각 WORK (역순)에 대해 비교:
+#   Glob "works/WORK-NN/TASK-*.md" (*_result.md, *_progress.md 제외) → TOTAL
+#   Glob "works/WORK-NN/TASK-*_result.md" → DONE
+# DONE < TOTAL인 첫 번째 WORK가 활성 WORK
 
 # 전체 WORK 목록
-ls -d works/WORK-* 2>/dev/null | sort -V
+# Glob 도구 사용: pattern "works/WORK-*/"
 
 # TASK 완료 현황
-TOTAL=$(ls works/${WORK_ID}/TASK-*.md 2>/dev/null | grep -v result | wc -l)
-DONE=$(ls works/${WORK_ID}/TASK-*_result.md 2>/dev/null | wc -l)
-echo "$DONE / $TOTAL"
+# TOTAL = Glob "works/${WORK_ID}/TASK-??.md" 개수
+# DONE  = Glob "works/${WORK_ID}/TASK-*_result.md" 개수
 ```
 
 ---
@@ -190,13 +188,13 @@ curl -s -X POST "CALLBACK_URL" -H "Content-Type: application/json" -H "X-Runner-
 grep -oP '(?<=Language:\s?)[a-z]{2}' CLAUDE.md 2>/dev/null
 
 # 2. 기술 스택
-cat package.json 2>/dev/null | head -50
-cat pyproject.toml 2>/dev/null | head -30
-cat Cargo.toml 2>/dev/null | head -20
-cat go.mod 2>/dev/null | head -10
+head -50 package.json 2>/dev/null
+head -30 pyproject.toml 2>/dev/null
+head -20 Cargo.toml 2>/dev/null
+head -10 go.mod 2>/dev/null
 
 # 3. 구조 (필요 시)
-find . -maxdepth 3 -type f \( -name "*.md" -o -name "*.json" -o -name "*.toml" \) | grep -v node_modules | head -30
+find . -maxdepth 3 -type f \( -name "*.md" -o -name "*.json" -o -name "*.toml" \) -not -path "*/node_modules/*" 2>/dev/null
 ```
 
 ---

package/agents/planner.md

@@ -57,9 +57,10 @@ Required reference files for this agent:
 
 ### 3-2. Project Exploration (Discovery Process)
 
-```bash
-# 1. Check existing WORKs
-ls -d works/WORK-* 2>/dev/null | sort -V | tail -1
+```
+# 1. Check existing WORKs — use Glob tool
+Glob pattern: "works/WORK-*/"
+→ Take the last entry (latest WORK number)
 ```
 
 → Discovery commands (steps 2–4): see `shared-prompt-sections.md` § 11

package/agents/shared-prompt-sections.md

@@ -28,7 +28,7 @@ elif [ -f "Cargo.toml" ]; then
 elif [ -f "go.mod" ]; then
   go build ./... 2>&1
 elif [ -f "pyproject.toml" ] || [ -f "setup.py" ]; then
-  python -m py_compile $(find . -name "*.py" -not -path "*/venv/*" | head -20) 2>&1
+  python -m py_compile $(find . -maxdepth 3 -name "*.py" -not -path "*/venv/*" 2>/dev/null) 2>&1
 elif [ -f "Makefile" ]; then
   make build 2>&1 || make 2>&1
 fi
@@ -68,22 +68,20 @@ works/{WORK_ID}/
 
 ## § 4. File System Discovery Scripts
 
-```bash
+```
 # Find latest WORK with incomplete TASKs
-for dir in $(ls -d works/WORK-* 2>/dev/null | sort -V -r); do
-  WORK_ID=$(basename $dir)
-  TOTAL=$(ls $dir/TASK-*.md 2>/dev/null | grep -v result | wc -l)
-  DONE=$(ls $dir/TASK-*_result.md 2>/dev/null | wc -l)
-  [ "$DONE" -lt "$TOTAL" ] && echo "$WORK_ID" && break
-done
+# Use Glob tool: pattern "works/WORK-*/" → list all WORK directories (sorted)
+# For each WORK (descending), compare:
+#   Glob "works/WORK-NN/TASK-*.md" (exclude *_result.md, *_progress.md) → TOTAL
+#   Glob "works/WORK-NN/TASK-*_result.md" → DONE
+# First WORK where DONE < TOTAL is the active WORK
 
 # List all WORKs
-ls -d works/WORK-* 2>/dev/null | sort -V
+# Use Glob tool: pattern "works/WORK-*/"
 
 # TASK completion status
-TOTAL=$(ls works/${WORK_ID}/TASK-*.md 2>/dev/null | grep -v result | wc -l)
-DONE=$(ls works/${WORK_ID}/TASK-*_result.md 2>/dev/null | wc -l)
-echo "$DONE / $TOTAL"
+# TOTAL = count of Glob "works/${WORK_ID}/TASK-??.md"
+# DONE  = count of Glob "works/${WORK_ID}/TASK-*_result.md"
 ```
 
 ---
@@ -190,13 +188,13 @@ Agent-specific payload fields:
 grep -oP '(?<=Language:\s?)[a-z]{2}' CLAUDE.md 2>/dev/null
 
 # 2. Tech stack
-cat package.json 2>/dev/null | head -50
-cat pyproject.toml 2>/dev/null | head -30
-cat Cargo.toml 2>/dev/null | head -20
-cat go.mod 2>/dev/null | head -10
+head -50 package.json 2>/dev/null
+head -30 pyproject.toml 2>/dev/null
+head -20 Cargo.toml 2>/dev/null
+head -10 go.mod 2>/dev/null
 
 # 3. Structure (when needed)
-find . -maxdepth 3 -type f \( -name "*.md" -o -name "*.json" -o -name "*.toml" \) | grep -v node_modules | head -30
+find . -maxdepth 3 -type f \( -name "*.md" -o -name "*.json" -o -name "*.toml" \) -not -path "*/node_modules/*" 2>/dev/null
 ```
 
 ---

package/lib/constants.mjs

@@ -31,37 +31,6 @@ export function getAgentsSrcDir(lang) {
   return join(__dirname, '..', 'agents', lang);
 }
 
-export const CLAUDE_MD_SECTION_KO = `
-## Agent 호출 규칙
-
-\`[]\` 태그로 시작하는 요청 → \`.claude/agents/agent-flow.md\` 를 읽고 파이프라인을 실행한다.
-
-- **Main Claude가 오케스트레이터**다. 모든 에이전트 호출은 Main Claude가 직접 수행한다.
-- \`[]\` 태그 감지 시 → specifier 호출 (첫 번째 에이전트)
-- 각 에이전트는 작업 완료 후 결과(dispatch XML 또는 task-result XML)만 반환한다.
-- Main Claude가 반환값을 받아 다음 에이전트를 순서대로 호출한다.
-- 파이프라인 흐름은 \`.claude/agents/agent-flow.md\` 기준을 따른다.
-
-예: \`[추가기능]\`, \`[버그수정]\`, \`[리팩토링]\`, \`[WORK 시작]\` 등
-`.trimStart();
-
-export const CLAUDE_MD_SECTION_EN = `
-## Agent Invocation Rules
-
-Requests starting with a \`[]\` tag → read \`.claude/agents/agent-flow.md\` and execute the pipeline.
-
-- **Main Claude is the orchestrator.** All agent invocations are performed directly by Main Claude.
-- On \`[]\` tag detection → invoke specifier (first agent)
-- Each agent only returns results (dispatch XML or task-result XML) after completing its work.
-- Main Claude receives return values and invokes the next agent in sequence.
-- Pipeline flow follows \`.claude/agents/agent-flow.md\`.
-
-Examples: \`[new-feature]\`, \`[bugfix]\`, \`[enhancement]\`, \`[new-work]\`, etc.
-`.trimStart();
-
-export function getClaudeMdSection(lang) {
-  return lang === 'ko' ? CLAUDE_MD_SECTION_KO : CLAUDE_MD_SECTION_EN;
-}
 
 /**
  * Bash permissions required by uc-taskmanager agents.
@@ -117,10 +86,7 @@ export const REQUIRED_PERMISSIONS = [
   'Bash(make:*)',
 
   // Git operations (committer)
-  'Bash(git add:*)',
-  'Bash(git commit:*)',
-  'Bash(git log:*)',
-  'Bash(git rev-parse:*)',
+  'Bash(git:*)',
 
   // Network (callback transmission)
   'Bash(curl:*)',