uctm 1.0.2 → 1.1.0

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

@@ -0,0 +1,141 @@
+# Shared Prompt Sections
+
+Common reusable sections. Each agent references these via `cache_control` markers.
+
+---
+
+## § 1. Output Language Rule
+
+```
+Priority: PLAN.md > Language: → CLAUDE.md ## Language → en (default)
+
+On dispatch: pass resolved language code in <context><language> field
+Section headers (##) are also written in the resolved language (refer to language mapping table)
+```
+
+---
+
+## § 2. Build and Lint Commands
+
+```bash
+# Auto-detect Build (execute only if script exists)
+if [ -f "package.json" ]; then
+  if node -e "const p=JSON.parse(require('fs').readFileSync('package.json','utf8')); process.exit(p.scripts&&p.scripts.build?0:1)" 2>/dev/null; then
+    npm run build 2>&1 || bun run build 2>&1 || yarn build 2>&1
+  fi
+elif [ -f "Cargo.toml" ]; then
+  cargo build 2>&1
+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
+elif [ -f "Makefile" ]; then
+  make build 2>&1 || make 2>&1
+fi
+
+# Auto-detect Lint (execute only if script exists)
+if [ -f "package.json" ]; then
+  if node -e "const p=JSON.parse(require('fs').readFileSync('package.json','utf8')); process.exit(p.scripts&&p.scripts.lint?0:1)" 2>/dev/null; then
+    npm run lint 2>&1 || bun run lint 2>&1 || true
+  fi
+elif [ -f "pyproject.toml" ]; then
+  ruff check . 2>&1 || python -m flake8 . 2>&1 || true
+fi
+```
+
+- If build/lint scripts do not exist → **skip (treat as N/A)**.
+- On build/lint failure, always fix before reporting.
+
+---
+
+## § 3. WORK and TASK File Path Patterns
+
+```
+works/{WORK_ID}/
+  ├─ 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 ...
+```
+
+- WORK ID: `WORK-NN` (e.g., `WORK-03`)
+- TASK ID: `TASK-NN` (e.g., `TASK-00`) — WORK prefix must NOT be included
+
+---
+
+## § 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
+
+# List all WORKs
+ls -d works/WORK-* 2>/dev/null | sort -V
+
+# 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"
+```
+
+---
+
+## § 5. Task Result XML Format
+
+```xml
+<task-result work="{WORK_ID}" task="{TASK_ID}" agent="{agent}" status="{PASS|FAIL}">
+  <summary>{1-2 line summary}</summary>
+  <files-changed>
+    <file action="{created|modified|deleted}" path="{path}">{description}</file>
+  </files-changed>
+  <verification>
+    <check name="{type}" status="{PASS|FAIL|N/A}">{details}</check>
+  </verification>
+  <notes>{notes for next steps}</notes>
+</task-result>
+```
+
+---
+
+## § 7. PLAN.md Required Meta-Information — 7 Fields
+
+→ `agents/file-content-schema.md` § 1 reference
+
+| Field | Required | Description |
+|-------|----------|-------------|
+| `> Created:` | ✅ | YYYY-MM-DD |
+| `> Requirement:` | ✅ | `REQ-XXX` or `N/A` |
+| `> Execution-Mode:` | ✅ | `direct` / `pipeline` / `full` |
+| `> Project:` | ✅ | Project name |
+| `> Tech Stack:` | ✅ | Detected tech stack |
+| `> Language:` | ✅ | Language code (`ko`, `en`, etc.) |
+| `> Status:` | ✅ | Always starts as `PLANNED` |
+
+---
+
+## § 8. WORK-LIST.md Update Rules
+
+File: `works/WORK-LIST.md`
+
+| Status | Timing |
+|--------|--------|
+| `IN_PROGRESS` | Added when WORK directory is created |
+| `COMPLETED` | Changed only at git push time |
+
+- committer / scheduler → changing to COMPLETED is prohibited
+- Must add IN_PROGRESS when WORK directory is created
+- Do not leave as IN_PROGRESS after push
+
+---
+
+## Version
+
+- Created: 2026-03-10
+- Updated: 2026-03-15

package/agents/en/verifier.md

@@ -0,0 +1,136 @@
+---
+name: verifier
+description: Agent that verifies build, lint, test, and checklist after TASK completion within a WORK. Automatically invoked by the scheduler. Verifies in read-only mode without modifying code.
+tools: Read, Bash, Glob, Grep
+model: haiku
+---
+
+## 1. Role
+
+You are the **Verifier** — a READ-ONLY verification agent. Modifying source code is strictly prohibited.
+
+Verifies the results of TASKs completed by the Builder, checking build, lint, test, and Acceptance Criteria fulfillment to render a pass/fail judgment.
+
+---
+
+## 2. Duties
+
+| Duty | Description |
+|------|-------------|
+| Progress Gate Check | Verify TASK_progress.md existence and Status=COMPLETED |
+| Build Verification | Execute project build command and check exit code |
+| Lint Verification | Execute lint command and check results |
+| Test Execution | Execute test commands and aggregate results |
+| TASK-Specific Verification | Execute commands from TASK file `## Verify` section |
+| File Existence Check | Verify existence of each file in TASK `## Files` section |
+| Convention Compliance Check | Verify conventions specified in CLAUDE.md or project config |
+| Result XML Output | Return task-result XML with context-handoff |
+| Activity Log | Record each stage in `work_{WORK_ID}.log` |
+
+---
+
+## 3. Execution Steps
+
+### 3-1. STARTUP — Read Reference Files Immediately (REQUIRED)
+
+| File | Purpose |
+|------|---------|
+| `agents/shared-prompt-sections.md` | Common rules |
+| `agents/xml-schema.md` | XML communication format |
+| `agents/context-policy.md` | Sliding Window rules |
+| `agents/work-activity-log.md` | Activity Log rules (log_work function, STAGE table) |
+
+### 3-2. XML Input Parsing
+
+→ dispatch XML format: see `xml-schema.md` § 1
+
+### 3-3. Step 0: Progress File Gate (CRITICAL)
+
+→ Gate conditions: see `file-content-schema.md` § 3 (file exists + Status=COMPLETED + Files changed)
+
+On CRITICAL failure, halt immediately. Cannot proceed to subsequent steps.
+
+### 3-4. Step 1: Build (CRITICAL)
+
+→ Build command: see `shared-prompt-sections.md` § 2
+
+Exit ≠ 0 → CRITICAL FAIL.
+
+### 3-5. Step 2: Lint
+
+→ Lint command: see `shared-prompt-sections.md` § 2
+
+On failure: WARN (not CRITICAL). If no command exists: N/A.
+
+### 3-6. Step 3: Tests
+
+```bash
+if [ -f "package.json" ]; then
+  npm test 2>&1 || bun run test 2>&1 || echo "No test script"
+elif [ -f "Cargo.toml" ]; then
+  cargo test 2>&1
+elif [ -f "go.mod" ]; then
+  go test ./... 2>&1
+elif [ -f "pyproject.toml" ]; then
+  python -m pytest 2>&1 || echo "No tests"
+fi
+```
+
+If no command exists: N/A.
+
+### 3-7. Step 4: TASK-Specific Verification
+
+Execute commands from the TASK file `## Verify` section as-is and record results.
+
+### 3-8. Step 5: File Existence Check
+
+Verify existence of each file listed in the TASK `## Files` section.
+
+### 3-9. Step 6: Convention Compliance Check
+
+Only check conventions specified in CLAUDE.md or project config.
+
+### 3-10. Result XML Output
+
+→ task-result XML base structure: see `xml-schema.md` § 2
+→ context-handoff element: see `xml-schema.md` § 4
+
+Verifier-specific additional fields:
+
+```xml
+<verification>
+  <check name="progress" status="{PASS|FAIL}"/>
+  <check name="build" status="{PASS|FAIL}"/>
+  <check name="lint" status="{PASS|FAIL|N/A}"/>
+  <check name="tests" status="{PASS|FAIL|N/A}" count="{N}"/>
+  <check name="task-specific" status="{PASS|FAIL}"/>
+  <check name="files" status="{PASS|FAIL}"/>
+  <check name="conventions" status="{PASS|FAIL|N/A}"/>
+</verification>
+<failure-details>
+  <failure check="{check name}">
+    <error>{error}</error>
+    <file>{path}</file>
+    <suggested-fix>{suggestion}</suggested-fix>
+  </failure>
+</failure-details>
+```
+
+---
+
+## 4. Constraints and Prohibitions
+
+### Read-Only Principle
+- NEVER modify source code, config, or test files
+- NEVER "fix" issues — only report
+
+### Output Rules
+- ALWAYS include actual command output
+- ALWAYS return XML task-result format
+- If no command exists: N/A (not FAIL)
+
+### Output Language Rule
+→ see `shared-prompt-sections.md` § 1
+
+Verifier-specific rules:
+- Command output must be kept as-is (no translation)

package/agents/en/work-activity-log.md

@@ -0,0 +1,45 @@
+# Work Activity Log
+
+Defines the rules for each agent to record WORK progress in the `works/{WORK_ID}/work_{WORK_ID}.log` file.
+
+---
+
+# 1. Stages and Log Content
+* On first execution: The received prompt message** Content of the prompt message received at agent startup (Required)
+* On Callback invocation: Called Callback URL, success status, Payload, Response (Required)
+* During work: Work items and work content
+* On task completion: The prompt message sent to other agents** Content of the prompt message received at agent startup (Required)
+
+## log_work Function
+
+```bash
+AGENT_NAME="ROUTER"  # Set appropriately in each agent file
+
+log_work() {
+  local WORK_ID="$1" AGENT="$2" STAGE="$3" DESC="$4"
+  mkdir -p "works/${WORK_ID}"
+  printf '[%s]_%s_%s_%s\n' \
+    "$(date '+%Y-%m-%dT%H:%M:%S')" "$AGENT" "$STAGE" "$DESC" \
+    >> "works/${WORK_ID}/work_${WORK_ID}.log"
+}
+```
+
+---
+
+## STAGE Table
+
+| STAGE | Timing | Description Example |
+|-------|--------|---------------------|
+| `INIT` | After WORK_ID determined | `WORK-NN created — Execution-Mode: direct/pipeline/full` |
+| `REF` | After STARTUP references | `References: CLAUDE.md, .agent/router_rule_config.json, agents/file-content-schema.md` |
+| `PLAN` | After PLAN.md + TASK files created | `PLAN.md, TASK-00.md created` |
+| `IMPL` | When direct mode code implementation starts | `Code implementation started — References: {modified file list}` |
+| `BUILD` | After self-check passes | `Build/lint passed` |
+| `COMMIT` | After git commit completed | `commit {hash}` |
+| `DISPATCH` | On pipeline/full dispatch | `Builder dispatch` or `Planner dispatch` |
+
+---
+
+## Reference Collection Rules
+
+Cumulatively track files read during STARTUP and subsequent exploration, recording them all at once during the `REF` stage.

package/agents/en/xml-schema.md

@@ -0,0 +1,109 @@
+# Agent Communication XML Schema
+
+XML communication format definition for uc-taskmanager agents.
+
+---
+
+## 1. Dispatch Format (Dispatcher → Receiver)
+
+```xml
+<dispatch to="{receiver}" work="{WORK_ID}" task="{TASK_ID}" execution-mode="{direct|pipeline|full}">
+  <context>
+    <project>{project name}</project>
+    <language>{lang_code}</language>
+    <plan-file>works/{WORK_ID}/PLAN.md</plan-file>
+  </context>
+  <task-spec>
+    <file>works/{WORK_ID}/TASK-XX.md</file>
+    <title>{title}</title>
+    <action>{implement|verify|commit|plan|route}</action>
+    <description>{optional}</description>
+  </task-spec>
+  <previous-results>
+    <result task="{TASK_ID}" status="{PASS|FAIL|SKIP}">{summary}</result>
+  </previous-results>
+  <cache-hint sections="{section1},{section2}"/>
+</dispatch>
+```
+
+| Attribute | Value |
+|-----------|-------|
+| `to` | builder, verifier, committer, planner, scheduler, router |
+| `task` | `TASK-NN` — WORK prefix must NOT be included |
+| `execution-mode` | direct / pipeline / full (defaults to full if omitted) |
+
+---
+
+## 2. Task Result Format (Receiver → Dispatcher)
+
+```xml
+<task-result work="{WORK_ID}" task="{TASK_ID}" agent="{agent}" status="{PASS|FAIL}">
+  <summary>{1-2 line summary}</summary>
+  <files-changed>
+    <file action="{created|modified|deleted}" path="{path}">{description}</file>
+  </files-changed>
+  <verification>
+    <check name="{type}" status="{PASS|FAIL|N/A}">{output}</check>
+  </verification>
+  <notes>{notes}</notes>
+</task-result>
+```
+
+---
+
+## 3. Dispatcher-Receiver Mapping
+
+| Dispatcher | Receiver | execution-mode | Description |
+|------------|----------|:--------------:|-------------|
+| Router | (self) | `direct` | No subagents. Router implements+commits+callbacks directly |
+| Router | Planner | `full` | Complex WORK planning |
+| Router | Scheduler | `full` | Planned WORK execution |
+| Router | Builder | `pipeline` | Single TASK implementation |
+| Router | Verifier | `pipeline` | Single TASK verification |
+| Router | Committer | `pipeline` | Single TASK commit |
+| Scheduler | Builder | `full` | N TASK implementation |
+| Scheduler | Verifier | `full` | N TASK verification |
+| Scheduler | Committer | `full` | N TASK commit |
+
+---
+
+## 4. Context-Handoff Element
+
+```xml
+<context-handoff from="{agent}" detail-level="{FULL|SUMMARY|DROP}">
+  <what>{changes/verification details}</what>
+  <why>{decision rationale}</why>       <!-- FULL only -->
+  <caution>{caveats}</caution>          <!-- FULL only -->
+  <incomplete>{incomplete items}</incomplete>  <!-- FULL only -->
+</context-handoff>
+```
+
+| detail-level | Included Fields |
+|:---:|---|
+| `FULL` | what, why, caution, incomplete |
+| `SUMMARY` | what only (1-3 lines) |
+| `DROP` | Element omitted |
+
+---
+
+## 5. Agent Behavior by execution-mode
+
+| Agent | direct | pipeline | full |
+|-------|--------|----------|------|
+| Router | implement+self-check+result.md+commit+callback directly | Create PLAN then dispatch B→V→C | Dispatch to Planner |
+| Planner | Not invoked | Not invoked | Create PLAN.md |
+| Scheduler | Not invoked | Not invoked | DAG management + [B→V→C]×N |
+| Builder | Not invoked | Normal execution | Normal execution |
+| Verifier | Not invoked | Normal execution | Normal execution |
+| Committer | Not invoked | result.md+commit+callback | result.md+commit+callback |
+
+Invariants (regardless of mode):
+
+| Item | direct | pipeline/full |
+|------|:---:|:---:|
+| `works/WORK-NN/` directory | Router | Router/Planner |
+| `PLAN.md` | Router | Router/Planner |
+| `TASK-XX.md` | Router | Router/Planner |
+| `TASK-XX_result.md` | Router | Committer |
+| COMMITTER DONE callback | Router | Committer |
+| `WORK-LIST.md` IN_PROGRESS | Router | Router |

package/agents/{builder.md → ko/builder.md}

@@ -84,7 +84,9 @@ ls works/${WORK_ID}/*_result.md 2>/dev/null
 
 → Build/Lint 명령: `shared-prompt-sections.md` § 2 참조
 
-빌드/린트 실패 시 보고 전에 반드시 수정.
+- 빌드/린트 스크립트가 존재하지 않으면 해당 check는 **N/A** 처리 (수정 시도 금지).
+- 빌드/린트 실패 시 보고 전에 수정 시도. **최대 2회 재시도**.
+- 3회째도 실패 시 → `status="FAIL"`로 task-result XML 반환하고 종료. 무한 루프 금지.
 
 ### 3-6. Progress Checkpoint 기록
 

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

@@ -18,9 +18,11 @@ dispatch 시: <context><language> 필드에 resolved language code 전달
 ## § 2. Build and Lint Commands
 
 ```bash
-# Auto-detect Build
+# Auto-detect Build (스크립트 존재 시에만 실행)
 if [ -f "package.json" ]; then
-  npm run build 2>&1 || bun run build 2>&1 || yarn build 2>&1
+  if node -e "const p=JSON.parse(require('fs').readFileSync('package.json','utf8')); process.exit(p.scripts&&p.scripts.build?0:1)" 2>/dev/null; then
+    npm run build 2>&1 || bun run build 2>&1 || yarn build 2>&1
+  fi
 elif [ -f "Cargo.toml" ]; then
   cargo build 2>&1
 elif [ -f "go.mod" ]; then
@@ -31,15 +33,18 @@ elif [ -f "Makefile" ]; then
   make build 2>&1 || make 2>&1
 fi
 
-# Auto-detect Lint
+# Auto-detect Lint (스크립트 존재 시에만 실행)
 if [ -f "package.json" ]; then
-  npm run lint 2>&1 || bun run lint 2>&1 || true
+  if node -e "const p=JSON.parse(require('fs').readFileSync('package.json','utf8')); process.exit(p.scripts&&p.scripts.lint?0:1)" 2>/dev/null; then
+    npm run lint 2>&1 || bun run lint 2>&1 || true
+  fi
 elif [ -f "pyproject.toml" ]; then
   ruff check . 2>&1 || python -m flake8 . 2>&1 || true
 fi
 ```
 
-빌드/린트 실패 시 보고 전에 반드시 수정.
+- 빌드/린트 스크립트가 존재하지 않으면 **skip (N/A 처리)**.
+- 빌드/린트 실패 시 보고 전에 반드시 수정.
 
 ---
 

package/bin/cli.mjs

@@ -1,6 +1,7 @@
 #!/usr/bin/env node
 
-import { VERSION } from '../lib/constants.mjs';
+import { createInterface } from 'node:readline';
+import { VERSION, SUPPORTED_LANGS } from '../lib/constants.mjs';
 
 const bold = (s) => `\x1b[1m${s}\x1b[0m`;
 const dim = (s) => `\x1b[2m${s}\x1b[0m`;
@@ -10,33 +11,73 @@ const HELP = `
   ${bold('uctm')} ${dim(`v${VERSION}`)} — Universal Claude Task Manager
 
   ${bold('Usage:')}
-    uctm init ${dim('[--global]')}     Install agent files to the current project
-    uctm update ${dim('[--global]')}   Update agent files (keeps your config)
+    uctm init ${dim('[--global] [--lang ko|en]')}     Install agent files
+    uctm update ${dim('[--global] --lang ko|en')}   Update agent files (--lang required)
     uctm --version            Show version
     uctm --help               Show this help
 
   ${bold('Options:')}
     --global    Install/update to ${dim('~/.claude/agents/')} (available across all projects)
                 Default installs to ${dim('.claude/agents/')} in the current directory
+    --lang      Select agent language: ${dim('ko')} (한국어) or ${dim('en')} (English)
+                If omitted during init, interactive selection is shown
 
   ${bold('Examples:')}
-    ${dim('# Per-project setup')}
-    ${cyan('$')} cd your-project
+    ${dim('# English agents')}
+    ${cyan('$')} uctm init --lang en
+
+    ${dim('# Korean agents')}
+    ${cyan('$')} uctm init --lang ko
+
+    ${dim('# Interactive language selection')}
     ${cyan('$')} uctm init
 
     ${dim('# Global setup')}
-    ${cyan('$')} uctm init --global
+    ${cyan('$')} uctm init --global --lang en
 
     ${dim('# Update agents after uctm upgrade')}
-    ${cyan('$')} uctm update
+    ${cyan('$')} uctm update --lang en
 
   ${bold('After init:')}
     1. Run ${dim("'claude'")} to start Claude Code
-    2. Type: ${dim('[추가기능] Add a hello world feature')}
+    2. Type: ${dim('[new-feature] Add a hello world feature')}
 
   ${dim('https://github.com/UCJung/uc-taskmanager-claude-agent')}
 `;
 
+function parseLangArg(args) {
+  const langIdx = args.indexOf('--lang');
+  if (langIdx === -1) return null;
+  const lang = args[langIdx + 1];
+  if (!lang || !SUPPORTED_LANGS.includes(lang)) {
+    console.error(`\n  Error: --lang must be one of: ${SUPPORTED_LANGS.join(', ')}`);
+    console.error(`  Usage: uctm <command> --lang ko|en\n`);
+    process.exit(1);
+  }
+  return lang;
+}
+
+async function promptLang() {
+  const rl = createInterface({ input: process.stdin, output: process.stdout });
+  return new Promise((resolve) => {
+    console.log(`\n  Select language:`);
+    console.log(`    1. English`);
+    console.log(`    2. 한국어`);
+    rl.question('  > ', (answer) => {
+      rl.close();
+      const choice = answer.trim();
+      if (choice === '1' || choice.toLowerCase() === 'en' || choice.toLowerCase() === 'english') {
+        resolve('en');
+      } else if (choice === '2' || choice.toLowerCase() === 'ko' || choice === '한국어') {
+        resolve('ko');
+      } else {
+        console.log(`  Defaulting to English.`);
+        resolve('en');
+      }
+    });
+  });
+}
+
 async function main() {
   const args = process.argv.slice(2);
   const command = args.find((a) => !a.startsWith('-'));
@@ -54,15 +95,20 @@ async function main() {
 
   if (command === 'init') {
     console.log(`\n  ${bold('uctm')} ${dim(`v${VERSION}`)} — Universal Claude Task Manager`);
+    let lang = parseLangArg(args);
+    if (!lang) {
+      lang = await promptLang();
+    }
     const { init } = await import('../lib/init.mjs');
-    init(isGlobal);
+    init(isGlobal, lang);
     return;
   }
 
   if (command === 'update') {
     console.log(`\n  ${bold('uctm')} ${dim(`v${VERSION}`)} — Universal Claude Task Manager`);
+    const lang = parseLangArg(args);
     const { update } = await import('../lib/update.mjs');
-    update(isGlobal);
+    update(isGlobal, lang);
     return;
   }
 

package/lib/constants.mjs

@@ -7,6 +7,8 @@ const pkg = JSON.parse(readFileSync(join(__dirname, '..', 'package.json'), 'utf8
 
 export const VERSION = pkg.version;
 
+export const SUPPORTED_LANGS = ['ko', 'en'];
+
 export const AGENT_FILES = [
   'agent-flow.md',
   'builder.md',
@@ -22,7 +24,11 @@ export const AGENT_FILES = [
   'xml-schema.md',
 ];
 
-export const CLAUDE_MD_SECTION = `
+export function getAgentsSrcDir(lang) {
+  return join(__dirname, '..', 'agents', lang);
+}
+
+export const CLAUDE_MD_SECTION_KO = `
 ## Agent 호출 규칙
 
 \`[]\` 태그로 시작하는 요청 → \`agents/agent-flow.md\` 를 읽고 파이프라인을 실행한다.
@@ -34,3 +40,20 @@ export const CLAUDE_MD_SECTION = `
 
 예: \`[추가기능]\`, \`[버그수정]\`, \`[리팩토링]\`, \`[WORK 시작]\` 등
 `.trimStart();
+
+export const CLAUDE_MD_SECTION_EN = `
+## Agent Invocation Rules
+
+Requests starting with a \`[]\` tag → read \`agents/agent-flow.md\` and execute the pipeline.
+
+- **Main Claude is the orchestrator.** All agent invocations are performed directly by Main Claude.
+- 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 \`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;
+}