uctm 1.5.1 → 1.5.3

package/{agents → references}/shared-prompt-sections.md

@@ -54,9 +54,7 @@ fi
 works/{WORK_ID}/
   ├─ Requirement.md                 # Created by Specifier (mandatory)
   ├─ PLAN.md
-  ├─ PROGRESS.md
   ├─ TASK-00.md               # No WORK prefix
-  ├─ TASK-00_progress.md      # Separator: underscore
   ├─ TASK-00_result.md        # Separator: underscore
   └─ TASK-01.md ...
 ```
@@ -71,17 +69,31 @@ works/{WORK_ID}/
 ```
 # Find latest WORK with incomplete TASKs
 # 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
+# For each WORK (descending), read last line of works/WORK-NN/work_WORK-NN.log
+#   - No log file → not started
+#   - Last line contains "COMMITTER_DONE" with last TASK number → check if more TASKs remain
+# First WORK that is not fully completed is the active WORK
 
 # List all WORKs
 # Use Glob tool: pattern "works/WORK-*/"
 
-# TASK completion status
-# TOTAL = count of Glob "works/${WORK_ID}/TASK-??.md"
-# DONE  = count of Glob "works/${WORK_ID}/TASK-*_result.md"
+# WORK/TASK status from activity log (last line)
+# Read last line of works/${WORK_ID}/work_${WORK_ID}.log
+#   Format: [timestamp] EVENT — description
+#
+#   Key rule: *_START without matching *_DONE = interrupted, must REDO that step
+#
+#   COMMITTER_DONE — TASK-NN → TASK-NN completed, next TASK is TASK-(NN+1)
+#   COMMITTER_START — TASK-NN → committer interrupted, redo verifier+committer for TASK-NN
+#   VERIFIER_DONE — TASK-NN  → TASK-NN verified, needs committer
+#   VERIFIER_START — TASK-NN → verifier interrupted, redo verifier+committer for TASK-NN
+#   BUILDER_DONE — TASK-NN   → TASK-NN builder done, needs verifier+committer
+#   BUILDER_START — TASK-NN  → builder interrupted, redo builder for TASK-NN
+#   PLANNER_DONE             → planning done, start first TASK
+#   PLANNER_START            → planner interrupted, redo specifier+planner
+#   SPECIFIER_DONE           → specifier done, needs planner
+#   SPECIFIER_START          → specifier interrupted, redo specifier+planner
+#   No log file              → start from scratch
 ```
 
 ---
@@ -150,73 +162,123 @@ Rules:
 ## § 9. Locale Detection
 
 ```
-1. CLAUDE.md → check "Language: xx"
+1. Use Grep tool: pattern "Language:\s*[a-z]{2}" path="CLAUDE.md" → extract language code
 2. If not found, ask user for language
-3. If not found, auto-detect system locale
+3. If not found, auto-detect system locale via Bash:
    - Windows: powershell -c "[CultureInfo]::CurrentCulture.TwoLetterISOLanguageName"
-   - Linux/Mac: locale | grep LANG | grep -oP '[a-z]{2}' | head -1
+   - Linux/Mac: locale | grep LANG
    - Fallback: "en"
 ```
 
 ---
 
-## § 10. Callback Transmission Template
+## § 10. Callback & Activity Log
 
-→ **Bash command rules: see § 13** — each step below is a separate tool call.
+### 10-1. Callback (CE7)
 
-Replace `{CallbackType}` with the actual key name (e.g., `ProgressCallback`, `TaskCallback`).
+Each agent sends START/DONE/FAILED events to the server via CE7 API.
 
-**Step 1.** Use `Grep` tool to find `{CallbackType}:` line in CLAUDE.md. If not found, skip callback entirely.
+**Activation condition:** Only when `CALLBACK_URL` is available. Check in order:
+1. Dispatch XML `<callback-url>` element (passed from Main Claude)
+2. Prompt text containing `CALLBACK_URL=...` line
+3. If neither found → **skip all callbacks**
 
-**Step 2.** Use `Grep` tool to find `CallbackToken:` line in CLAUDE.md (optional).
+**How to resolve CALLBACK_URL and CALLBACK_TOKEN:**
 
-**Step 3.** Send callback with a single `curl` command:
+The runner injects callback info directly into the prompt:
+```
+POST {CALLBACK_URL}
+Authorization: Bearer {CALLBACK_TOKEN}
+```
+The first agent (specifier) extracts these and passes them via dispatch XML to subsequent agents.
+
+**When to send:**
+- **START**: At the very beginning of agent execution (after STARTUP)
+- **DONE**: At the very end, before returning task-result XML
+- **FAILED**: On unrecoverable failure, before returning FAIL task-result
+
+**How to send** (single curl command):
 ```bash
-curl -s -X POST "CALLBACK_URL" -H "Content-Type: application/json" -H "X-Runner-Api-Key: TOKEN" -d '{"workId":"WORK-01","taskId":"TASK-00",...}'
+curl -s --connect-timeout 3 --max-time 5 -X POST "$CALLBACK_URL" \
+  -H "Authorization: Bearer $CALLBACK_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{"stage":"BUILDER","event":"START","workId":"WORK-09","taskId":"TASK-01"}' \
+  2>/dev/null || true
 ```
 
-Agent-specific payload fields:
-- **ProgressCallback** (builder): `"status": "IN_PROGRESS"`, `"currentReasoning": "..."`
-- **TaskCallback** (committer): `"status": "SUCCESS"`, `"commitHash": "${COMMIT_HASH}"`
+- `--connect-timeout 3`: 연결 대기 최대 3초
+- `--max-time 5`: 전체 요청 최대 5초
+- `|| true`: 실패해도 agent 실행 계속
 
----
+**Include docs (actual file content, not references):**
+- specifier DONE: `"docs": {"requirementContent": "<Requirement.md content>"}`
+- planner DONE: `"docs": {"planContent": "<PLAN.md content>"}`
+- builder START: `"docs": {"taskContent": "<TASK-NN.md content>"}`
+- committer DONE: `"docs": {"resultContent": "<TASK-NN_result.md content>"}`
 
-## § 11. Project Discovery
+**Token usage** (DONE event only, optional):
+```json
+{"inputTokens": 1234, "outputTokens": 567, "cacheCreationTokens": 890, "cacheReadTokens": 456}
+```
 
-```bash
-# 1. Check CLAUDE.md language setting
-grep -oP '(?<=Language:\s?)[a-z]{2}' CLAUDE.md 2>/dev/null
+Callback failure must NOT block agent execution. Always continue.
 
-# 2. Tech stack
-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
+### 10-2. Activity Log
 
-# 3. Structure (when needed)
-find . -maxdepth 3 -type f \( -name "*.md" -o -name "*.json" -o -name "*.toml" \) -not -path "*/node_modules/*" 2>/dev/null
+Each agent records start/end to `works/{WORK_ID}/work_{WORK_ID}.log`.
+
+**All WORKs** — no CALLBACK_URL condition.
+
+**Timestamp:** Run `date -u +"%Y-%m-%dT%H:%M:%SZ"` via Bash tool to get the real UTC time. Do NOT use dummy/placeholder timestamps.
+
+**Format:**
+```
+[2026-03-30T14:30:00Z] AGENT_EVENT — description
 ```
 
+**How to write:** Use Bash `echo "[timestamp] EVENT — description" >> works/{WORK_ID}/work_{WORK_ID}.log`
+
+**Required entries per agent (START and DONE only):**
+```
+[{timestamp}] SPECIFIER_START — WORK-NN specifier started
+[{timestamp}] SPECIFIER_DONE — WORK-NN specifier completed
+[{timestamp}] BUILDER_START — TASK-NN implement
+[{timestamp}] BUILDER_DONE — TASK-NN complete
+[{timestamp}] VERIFIER_START — TASK-NN verification
+[{timestamp}] VERIFIER_DONE — TASK-NN verified
+[{timestamp}] COMMITTER_START — TASK-NN commit
+[{timestamp}] COMMITTER_DONE — TASK-NN committed
+```
+
+Do NOT write INIT, REF, PLAN, DISPATCH or other intermediate entries. Only START and DONE per agent role.
+
 ---
 
-## § 12. Progress File Gate Check
+## § 11. Project Discovery
+
+```
+# 1. Check CLAUDE.md language setting
+Use Grep tool: pattern "Language:\s*[a-z]{2}" path="CLAUDE.md"
 
-Gate conditions for `works/WORK-NN/TASK-XX_progress.md`:
-- File exists at the expected path
-- `Status: COMPLETED` line is present
-- `## Files Changed` section is present and non-empty
+# 2. Tech stack (read first 50/30/20/10 lines if file exists)
+Use Read tool: "package.json" (limit=50)
+Use Read tool: "pyproject.toml" (limit=30)
+Use Read tool: "Cargo.toml" (limit=20)
+Use Read tool: "go.mod" (limit=10)
 
-On gate failure → return FAIL task-result immediately. Do not proceed to subsequent steps.
+# 3. Structure (when needed)
+Use Glob tool: pattern "**/*.{md,json,toml}" (exclude node_modules)
+```
 
 ---
 
-## § 13. Bash Command Rules
+## § 12. Bash Command Rules
 
 Bash commands MUST follow these rules for permission compatibility.
 
 **MANDATORY:**
 - One simple command per Bash call — NO compound commands (`&&`, `||`, `;`, `|`)
-- NO `cd dir && command` — you are already in the project root
+- NO `cd` — Bash tool cwd is always the project root. Never use `cd dir &&`, `cd dir ;`, or `cd dir` in any form. Use relative paths from project root
 - NO multi-line scripts — split into separate Bash calls
 - NO sub-shell expansions in arguments — e.g., `$(date ...)` inside `printf`
 - Use relative paths from project root (e.g., `works/WORK-01/`) — NO absolute paths

package/references/work-activity-log.md

@@ -0,0 +1,26 @@
+# Work Activity Log
+
+Records agent start/end events in `works/{WORK_ID}/work_{WORK_ID}.log`.
+
+## Rules
+
+1. **Timestamp**: Run `date -u +"%Y-%m-%dT%H:%M:%SZ"` via Bash to get real UTC time. Never use dummy values.
+2. **Write method**: Use `Edit` tool to append. Do NOT use Bash for log writes.
+3. **Entries**: Only START and DONE per agent role. No intermediate stages.
+
+## Format
+
+```
+[YYYY-MM-DDTHH:MM:SSZ] AGENT_EVENT — description
+```
+
+## Required Entries
+
+| Agent | START | DONE |
+|-------|-------|------|
+| specifier | `SPECIFIER_START — WORK-NN specifier started` | `SPECIFIER_DONE — WORK-NN specifier completed` |
+| planner | `PLANNER_START — WORK-NN planner started` | `PLANNER_DONE — WORK-NN planner completed` |
+| scheduler | `SCHEDULER_START — WORK-NN scheduler started` | `SCHEDULER_DONE — WORK-NN scheduler completed` |
+| builder | `BUILDER_START — TASK-NN implement` | `BUILDER_DONE — TASK-NN complete` |
+| verifier | `VERIFIER_START — TASK-NN verification` | `VERIFIER_DONE — TASK-NN verified` |
+| committer | `COMMITTER_START — TASK-NN commit` | `COMMITTER_DONE — TASK-NN committed` |

package/{skills/sdd-pipeline/references → references}/xml-schema.md

@@ -66,21 +66,7 @@ XML communication format definition for uc-taskmanager agents.
 
 ---
 
-## 3. Dispatcher-Receiver Mapping
-
-| Dispatcher | Receiver | execution-mode | Description |
-|------------|----------|:--------------:|-------------|
-| Specifier | Builder | `direct` | Assumed: single TASK implementation (Verifier skipped) |
-| Specifier | Planner | `pipeline/full` | Delegated: complex WORK planning |
-| Planner | Builder | `pipeline` | TASK implementation |
-| Planner | Scheduler | `full` | DAG management + execution |
-| Scheduler | Builder | `full` | N TASK implementation |
-| Scheduler | Verifier | `full` | N TASK verification |
-| Scheduler | Committer | `full` | N TASK commit |
-
----
-
-## 4. Context-Handoff Element
+## 3. Context-Handoff Element
 
 ```xml
 <context-handoff from="{agent}" detail-level="{FULL|SUMMARY|DROP}">
@@ -99,32 +85,7 @@ XML communication format definition for uc-taskmanager agents.
 
 ---
 
-## 5. Agent Behavior by execution-mode
-
-| Agent | direct | pipeline | full |
-|-------|--------|----------|------|
-| Specifier | Requirement.md + PLAN.md + TASK (assumed) | Requirement.md only → delegate to Planner | Requirement.md only → delegate to Planner |
-| Planner | Not invoked (Specifier assumed) | PLAN.md + TASK + execution-mode | PLAN.md + TASK + execution-mode |
-| Scheduler | Not invoked | Not invoked | DAG management + [B→V→C]×N |
-| Builder | Normal execution (self-check) | Normal execution | Normal execution |
-| Verifier | Not invoked | Normal execution | Normal execution |
-| Committer | result.md+commit+callback | result.md+commit+callback | result.md+commit+callback |
-
-Invariants (regardless of mode):
-
-| Item | direct | pipeline/full |
-|------|:---:|:---:|
-| `works/WORK-NN/` directory | Specifier | Specifier |
-| `Requirement.md` | Specifier | Specifier |
-| `PLAN.md` | Specifier (assumed) | Planner |
-| `TASK-XX.md` | Specifier (assumed) | Planner |
-| `TASK-XX_result.md` | Committer | Committer |
-| COMMITTER DONE callback | Committer | Committer |
-| `WORK-LIST.md` IN_PROGRESS | Specifier | Specifier |
-
----
-
-## 6. ref-cache Element Definition
+## 4. ref-cache Element Definition
 
 `<ref-cache>` is an optional container element that carries pre-loaded reference file contents within dispatch and task-result XML. When present, receiving agents MUST use these contents instead of reading files from disk.
 

package/skills/sdd-pipeline/SKILL.md

@@ -4,13 +4,15 @@
 
 직접 사용자 호출용이 아니라 에이전트 내부 참조용입니다.
 
+참조 문서 위치: `../../references/`
+
 ## 포함 문서
 
 | File | Description |
 |------|-------------|
-| `references/agent-flow.md` | 파이프라인 흐름 정의 |
-| `references/file-content-schema.md` | 파일 포맷 스키마 |
-| `references/shared-prompt-sections.md` | 공통 규칙 (TASK ID, PLAN.md 7 fields, WORK-LIST) |
-| `references/context-policy.md` | 슬라이딩 윈도우 규칙 |
-| `references/xml-schema.md` | XML 통신 포맷 |
-| `references/work-activity-log.md` | Activity Log 규칙 |
+| `../../references/agent-flow.md` | 파이프라인 흐름 정의 |
+| `../../references/file-content-schema.md` | 파일 포맷 스키마 |
+| `../../references/shared-prompt-sections.md` | 공통 규칙 (TASK ID, PLAN.md 7 fields, WORK-LIST) |
+| `../../references/context-policy.md` | 슬라이딩 윈도우 규칙 |
+| `../../references/xml-schema.md` | XML 통신 포맷 |
+| `../../references/work-activity-log.md` | Activity Log 규칙 |

package/skills/work-pipeline/SKILL.md

@@ -1,25 +1,30 @@
 ---
 name: work-pipeline
-description: Triggers the WORK-PIPELINE when a user request starts with a [] tag (e.g., [new-feature], [bugfix], [WORK start]). Use this skill whenever you detect a [] tag at the beginning of a user message.
+description: Triggers the WORK-PIPELINE. Use this skill when (1) user request starts with a [] tag (e.g., [new-feature], [bugfix]), or (2) user asks to resume/continue a WORK (e.g., "WORK-01 계속실행", "resume WORK-01", "WORK-01 실행", "continue WORK-01").
 ---
 
 # WORK-PIPELINE Trigger
 
-When the user's message starts with a `[]` tag, start the WORK-PIPELINE by reading `../skills/sdd-pipeline/references/agent-flow.md` and following the orchestration flow.
+Read `../../references/agent-flow.md` and follow the orchestration flow.
 
 ## Trigger Detection
 
-Any message starting with `[...]` triggers this pipeline:
+**New WORK** — message starts with `[...]` tag:
 - `[new-feature]`, `[enhancement]`, `[bugfix]`, `[new-work]`, `[WORK start]`
 - Or any custom tag in square brackets
 
+**Resume WORK** — message mentions existing WORK-ID with execution intent:
+- "WORK-XX 계속실행", "WORK-XX 실행", "resume WORK-XX", "continue WORK-XX"
+- "파이프라인 재개", "WORK 계속"
+- → Follow agent-flow.md § Resuming Existing WORK
+
 ## References Directory (CRITICAL)
 
 When this skill is triggered, Claude Code provides the "Base directory for this skill" as an absolute path.
 Derive the **REFERENCES_DIR** from it:
 
 ```
-REFERENCES_DIR = {Base directory}/../sdd-pipeline/references
+REFERENCES_DIR = {Base directory}/../../references
 ```
 
 You MUST pass this absolute path to **every sub-agent invocation** (specifier, planner, scheduler, builder, verifier, committer).
@@ -31,14 +36,32 @@ REFERENCES_DIR={absolute_path}
 
 Sub-agents need this path to read their reference files. Without it, they cannot find the files and will loop.
 
+## Callback Info Passthrough
+
+If the user's prompt contains `CALLBACK_URL=...` and `CALLBACK_TOKEN=...`, extract these values and pass them to **every sub-agent invocation** alongside REFERENCES_DIR:
+
+```
+CALLBACK_URL={url}
+CALLBACK_TOKEN={token}
+```
+
+**Main Claude (this skill) must NEVER send callbacks itself.** Only sub-agents send callbacks.
+
 ## Pipeline Flow
 
-1. **Call specifier agent** — analyzes the requirement, creates `works/WORK-NN/Requirement.md`, determines execution-mode (direct/pipeline/full)
+1. **Spawn specifier agent** (via Agent tool) — analyzes the requirement, creates `works/WORK-NN/Requirement.md`, determines execution-mode (direct/pipeline/full)
 2. **⛔ STOP — Present the specifier's output summary to the user and WAIT for explicit approval.** Do NOT call the next agent until the user approves. Show what was created (Requirement.md, PLAN.md if direct mode, TASK files) and ask "Proceed?"
 3. **Follow the execution-mode** returned by specifier:
-   - `direct`: call builder → committer
-   - `pipeline`: call builder → verifier → committer in sequence
-   - `full`: call planner → **⛔ STOP for 2nd approval** → scheduler → [builder → verifier → committer] × N
+   - `direct`: spawn builder (Agent tool) → spawn verifier+committer (single Agent tool, see agent-flow.md § Combined Agent Invocation)
+   - `pipeline`: for each TASK → spawn builder → spawn verifier+committer (repeat per TASK)
+   - `full`: spawn planner → **⛔ STOP for 2nd approval** → spawn scheduler → scheduler handles [builder → verifier+committer] × N
+
+## ⚠️ CRITICAL: Agent Spawn Rules
+
+- **EVERY agent MUST be spawned via the Agent tool.** Main Claude must NEVER implement code, create files, run git commands, or perform any agent's work directly.
+- In direct mode: spawn specifier → spawn builder → spawn verifier+committer (**3 Agent tool calls**).
+- verifier+committer is a **single spawn** that performs both roles in sequence (see agent-flow.md).
+- If specifier returns builder dispatch XML, pass it to the builder agent — do NOT execute it yourself.
 
 ## Auto Mode
 

package/skills/work-status/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: work-status
-description: Shows WORK progress and TASK status. Use when the user asks about WORK list, WORK progress, TASK status, or pipeline status (e.g., "WORK list", "WORK-01 progress", "show status").
+description: Shows WORK status (read-only). Use ONLY when the user asks to VIEW status — not to execute or resume. Matches queries like "WORK 목록", "상태 확인", "WORK-01 상태", "show status". Do NOT use for "실행", "계속", "resume" — those go to work-pipeline.
 ---
 
 # WORK Status
@@ -10,7 +10,7 @@ Check and report the current status of WORKs and TASKs.
 ## How to Check
 
 1. Read `works/WORK-LIST.md` for the master index of all WORKs
-2. For a specific WORK, read `works/WORK-NN/PROGRESS.md` for TASK-level progress
+2. For a specific WORK, read last line of `works/WORK-NN/work_WORK-NN.log` for current progress
 3. For a specific TASK, read `works/WORK-NN/TASK-NN_result.md` for completion details
 
 ## Status Values

package/.claude-plugin/.claude-plugin/plugin.json

@@ -1,29 +0,0 @@
-{
-  "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"
-  ]
-}