selfish-pipeline 1.1.0 → 1.2.0

package/.claude-plugin/marketplace.json

@@ -5,15 +5,15 @@
     "email": "relee6203@gmail.com"
   },
   "metadata": {
-    "description": "Claude Code 전용 자동화 파이프라인 — spec → plan → tasks → implement → review → clean",
-    "version": "1.1.0"
+    "description": "Automated pipeline for Claude Code — spec → plan → tasks → implement → review → clean",
+    "version": "1.2.0"
   },
   "plugins": [
     {
       "name": "selfish",
       "source": "./",
-      "description": "Claude Code 전용 자동화 파이프라인. spec → plan → tasks → implement → review → clean 전체 개발 사이클을 자동화합니다.",
-      "version": "1.1.0",
+      "description": "Automated pipeline for Claude Code. Automates the full development cycle: spec → plan → tasks → implement → review → clean.",
+      "version": "1.2.0",
       "category": "automation",
       "tags": ["pipeline", "automation", "spec", "plan", "implement", "review", "critic-loop"]
     }

package/.claude-plugin/plugin.json

@@ -1,13 +1,11 @@
 {
   "name": "selfish",
-  "version": "1.1.0",
-  "description": "Claude Code 전용 자동화 파이프라인. spec → plan → tasks → implement → review → clean 전체 개발 사이클을 자동화합니다.",
+  "version": "1.2.0",
+  "description": "Automated pipeline for Claude Code. Automates the full development cycle: spec → plan → tasks → implement → review → clean.",
   "author": { "name": "jhlee0409", "email": "relee6203@gmail.com" },
   "homepage": "https://github.com/jhlee0409/selfish-pipeline",
   "repository": "https://github.com/jhlee0409/selfish-pipeline",
   "license": "MIT",
   "keywords": ["pipeline", "automation", "spec", "plan", "implement", "review", "critic-loop"],
-  "commands": "./commands/",
-  "hooks": "./hooks/hooks.json",
-  "agents": "./agents/"
+  "commands": "./commands/"
 }

package/MIGRATION.md

@@ -1,27 +1,27 @@
 # Migration Guide: install.sh → Plugin
 
-> 기존 `git clone` + `install.sh` 방식에서 Claude Code 플러그인 방식으로 마이그레이션하는 가이드입니다.
+> A guide for migrating from the `git clone` + `install.sh` approach to the Claude Code plugin system.
 
-## 변경 요약
+## Summary of Changes
 
-| 항목 | 이전 | 이후 |
-|------|------|------|
-| 설치 | `git clone` + `./install.sh` | `/plugin install <url>` |
-| 커맨드 구분자 | `.` (`/selfish.spec`) | `:` (`/selfish:spec`) |
-| 커맨드 위치 | `~/.claude/commands/selfish.*.md` | 플러그인 내 `commands/*.md` |
-| Hook 스크립트 | `<project>/.claude/hooks/*.sh` | 플러그인 내 `scripts/*.sh` |
-| Hook 설정 | `<project>/.claude/settings.json` | 플러그인 내 `hooks/hooks.json` |
-| 설정 파일 | `.claude/selfish.config.md` (변경 없음) | `.claude/selfish.config.md` (변경 없음) |
+| Item | Before | After |
+|------|--------|-------|
+| Installation | `git clone` + `./install.sh` | `/plugin install <url>` |
+| Command separator | `.` (`/selfish.spec`) | `:` (`/selfish:spec`) |
+| Command location | `~/.claude/commands/selfish.*.md` | `commands/*.md` inside the plugin |
+| Hook scripts | `<project>/.claude/hooks/*.sh` | `scripts/*.sh` inside the plugin |
+| Hook config | `<project>/.claude/settings.json` | `hooks/hooks.json` inside the plugin |
+| Config file | `.claude/selfish.config.md` (unchanged) | `.claude/selfish.config.md` (unchanged) |
 
-## 마이그레이션 절차
+## Migration Steps
 
-### 1. 기존 파일 정리
+### 1. Clean Up Existing Files
 
 ```bash
-# 기존 커맨드 파일 삭제 (유저 레벨)
+# Remove existing command files (user level)
 rm -f ~/.claude/commands/selfish.*.md
 
-# 기존 hook 스크립트 삭제 (프로젝트 레벨)
+# Remove existing hook scripts (project level)
 rm -f .claude/hooks/session-start-context.sh
 rm -f .claude/hooks/pre-compact-checkpoint.sh
 rm -f .claude/hooks/track-selfish-changes.sh
@@ -29,72 +29,72 @@ rm -f .claude/hooks/selfish-stop-gate.sh
 rm -f .claude/hooks/selfish-pipeline-manage.sh
 ```
 
-### 2. settings.json에서 selfish hook 제거
+### 2. Remove selfish hooks from settings.json
 
-`.claude/settings.json`에서 selfish 관련 hook 항목을 제거합니다.
-플러그인이 자체 `hooks.json`으로 hook을 등록하므로 settings.json에서의 수동 설정이 불필요합니다.
+Remove selfish-related hook entries from `.claude/settings.json`.
+Since the plugin registers hooks via its own `hooks.json`, manual configuration in settings.json is no longer needed.
 
-제거 대상 (settings.json 내):
+Items to remove (from settings.json):
 - `SessionStart` → `session-start-context.sh`
 - `PreCompact` → `pre-compact-checkpoint.sh`
 - `PostToolUse` → `track-selfish-changes.sh`
 - `Stop` → `selfish-stop-gate.sh`
 
-> 다른 프로젝트 고유 hook이 settings.json에 있다면 그것은 유지하세요.
+> If you have other project-specific hooks in settings.json, keep those as they are.
 
-### 3. 플러그인 설치
+### 3. Install the Plugin
 
 ```bash
 npx selfish-pipeline
 ```
 
-또는 수동으로:
+Or manually:
 
 ```bash
 claude plugin marketplace add jhlee0409/selfish-pipeline
 claude plugin install selfish@selfish-pipeline --scope user
 ```
 
-기존 `install.sh`의 `--commands-only`에 해당하는 것은 **User** 스코프, 팀 공유는 **Project** 스코프입니다.
+The equivalent of `install.sh --commands-only` is the **User** scope; for team sharing, use the **Project** scope.
 
-### 4. 커맨드명 변경
+### 4. Command Name Changes
 
-모든 커맨드의 구분자가 `.`에서 `:`로 변경되었습니다:
+The separator for all commands has changed from `.` to `:`:
 
 ```text
-# 이전
-/selfish.auto "기능 설명"
-/selfish.spec "기능 설명"
+# Before
+/selfish.auto "feature description"
+/selfish.spec "feature description"
 /selfish.plan
 
-# 이후
-/selfish:auto "기능 설명"
-/selfish:spec "기능 설명"
+# After
+/selfish:auto "feature description"
+/selfish:spec "feature description"
 /selfish:plan
 ```
 
-### 5. 설정 파일 확인
+### 5. Verify Config File
 
-`.claude/selfish.config.md`는 **변경 없이 그대로 사용 가능**합니다.
+`.claude/selfish.config.md` can be **used as-is without any changes**.
 
-신규 프로젝트라면 `/selfish:init`으로 자동 생성할 수 있습니다.
+For new projects, you can auto-generate it with `/selfish:init`.
 
-## 변경되지 않는 것
+## What Stays the Same
 
-- `.claude/selfish.config.md` 파일 형식 및 경로
-- `specs/{feature}/` 아티팩트 경로
-- `memory/` 참조 (checkpoint, principles, research, decisions)
-- `.selfish-*` 상태 파일 경로
-- `git tag selfish/pre-*` 안전 태그
-- hook 스크립트 내부 로직
+- `.claude/selfish.config.md` file format and path
+- `specs/{feature}/` artifact paths
+- `memory/` references (checkpoint, principles, research, decisions)
+- `.selfish-*` state file paths
+- `git tag selfish/pre-*` safety tags
+- Internal logic of hook scripts
 
 ## FAQ
 
-**Q: 기존 프로젝트의 `.claude/selfish.config.md`를 다시 만들어야 하나요?**
-A: 아니요. 설정 파일 형식은 동일합니다. 그대로 사용하세요.
+**Q: Do I need to recreate `.claude/selfish.config.md` for existing projects?**
+A: No. The config file format is the same. Use it as-is.
 
-**Q: 여러 프로젝트에서 사용 중인데, 각 프로젝트마다 마이그레이션해야 하나요?**
-A: 플러그인은 한 번만 설치하면 됩니다. 각 프로젝트에서는 기존 `.claude/hooks/*.sh`와 settings.json의 selfish hook 항목만 정리하면 됩니다.
+**Q: I'm using this across multiple projects. Do I need to migrate each one?**
+A: You only need to install the plugin once. For each project, just clean up the existing `.claude/hooks/*.sh` files and selfish hook entries in settings.json.
 
-**Q: 이전 버전과 플러그인을 동시에 사용할 수 있나요?**
-A: 권장하지 않습니다. 커맨드명이 다르므로 (`/selfish.spec` vs `/selfish:spec`) 충돌은 없지만, hook이 중복 등록될 수 있습니다.
+**Q: Can I use the old version and the plugin at the same time?**
+A: This is not recommended. Since the command names differ (`/selfish.spec` vs `/selfish:spec`), there are no conflicts, but hooks may get registered twice.

package/README.md

@@ -4,9 +4,9 @@
 
 [![npm version](https://img.shields.io/npm/v/selfish-pipeline)](https://www.npmjs.com/package/selfish-pipeline)
 [![license](https://img.shields.io/github/license/jhlee0409/selfish-pipeline)](./LICENSE)
-[![test](https://img.shields.io/badge/tests-101%20passed-brightgreen)]()
-[![hooks](https://img.shields.io/badge/hooks-15%20events-blue)]()
-[![commands](https://img.shields.io/badge/commands-16-orange)]()
+[![test](https://img.shields.io/badge/tests-161%20passed-brightgreen)](#how-it-works)
+[![hooks](https://img.shields.io/badge/hooks-15%20events-blue)](#15-hook-events)
+[![commands](https://img.shields.io/badge/commands-18-orange)](#18-slash-commands)
 
 > Zero-dependency automation pipeline for Claude Code. One command (`/selfish:auto`) runs the entire cycle: write specs, design plans, break into tasks, implement code, review quality, and clean up — all with built-in CI gates and critic loops.
 
@@ -14,7 +14,7 @@
 
 Selfish Pipeline is a **Claude Code plugin** that transforms your development workflow into a fully automated pipeline. Instead of manually prompting Claude through each development phase, you run a single command and the pipeline handles everything — from writing feature specifications to final code review.
 
-- **16 slash commands** for every phase of development
+- **18 slash commands** for every phase of development
 - **15 hook events** with 3 handler types (shell scripts, LLM prompts, subagents)
 - **5 project presets** for popular stacks (Next.js, React SPA, Express API, Monorepo)
 - **Persistent memory agents** that learn across sessions
@@ -75,9 +75,9 @@ Runs all 6 phases automatically with **Critic Loop** quality checks at each gate
 Spec (1/6) → Plan (2/6) → Tasks (3/6) → Implement (4/6) → Review (5/6) → Clean (6/6)
 ```
 
-### 16 Slash Commands
+### 18 Slash Commands
 
-**User-invocable:**
+**User and model (unrestricted):**
 
 | Command | Description |
 |---|---|
@@ -85,24 +85,31 @@ Spec (1/6) → Plan (2/6) → Tasks (3/6) → Implement (4/6) → Review (5/6)
 | `/selfish:spec` | Write feature specification with acceptance criteria |
 | `/selfish:plan` | Design implementation plan with file change map |
 | `/selfish:implement` | Execute code implementation with CI gates |
+| `/selfish:test` | Test strategy planning and test writing |
 | `/selfish:review` | Code review with security scanning |
 | `/selfish:research` | Technical research with persistent storage |
-| `/selfish:init` | Project setup — detects stack and generates config |
+| `/selfish:debug` | Bug diagnosis and fix |
 
-**Model-callable (internal):**
+**User-only** (`disable-model-invocation: true`):
 
 | Command | Description |
 |---|---|
-| `/selfish:tasks` | Break plan into parallelizable tasks |
-| `/selfish:analyze` | Verify artifact consistency |
+| `/selfish:init` | Project setup — detects stack and generates config |
+| `/selfish:doctor` | Diagnose project health and plugin setup |
 | `/selfish:architect` | Architecture analysis (persistent memory) |
 | `/selfish:security` | Security scan (persistent memory, isolated worktree) |
-| `/selfish:clarify` | Resolve spec ambiguities |
-| `/selfish:debug` | Bug diagnosis and fix |
 | `/selfish:principles` | Project principles management |
 | `/selfish:checkpoint` | Save session state |
 | `/selfish:resume` | Restore session state |
 
+**Model-only** (`user-invocable: false`):
+
+| Command | Description |
+|---|---|
+| `/selfish:tasks` | Break plan into parallelizable tasks |
+| `/selfish:analyze` | Verify artifact consistency |
+| `/selfish:clarify` | Resolve spec ambiguities |
+
 ### 15 Hook Events
 
 Every hook fires automatically — no configuration needed after install.
@@ -187,7 +194,7 @@ This detects your tech stack and generates `.claude/selfish.config.md` with:
 ## FAQ
 
 ### What is selfish-pipeline?
-A Claude Code plugin that automates the entire development cycle (spec → plan → tasks → implement → review → clean) through 16 slash commands and 15 hook events.
+A Claude Code plugin that automates the entire development cycle (spec → plan → tasks → implement → review → clean) through 18 slash commands and 15 hook events.
 
 ### How does it compare to manual Claude Code workflows?
 Instead of manually prompting each step, selfish-pipeline orchestrates the full cycle with built-in quality gates that physically prevent skipping CI or security checks.

package/agents/selfish-architect.md

@@ -1,6 +1,6 @@
 ---
 name: selfish-architect
-description: "아키텍처 분석 에이전트 — ADR 결정과 아키텍처 패턴을 세션 간 기억하여 일관된 설계 조언을 제공한다."
+description: "Architecture analysis agent — remembers ADR decisions and architecture patterns across sessions to provide consistent design guidance."
 tools:
   - Read
   - Grep
@@ -15,7 +15,13 @@ skills:
   - docs/phase-gate-protocol.md
 ---
 
-You are an architecture analysis agent for the selfish-pipeline project.
+You are an architecture analysis agent for the current project.
+
+## Reference Documents
+
+Before performing analysis, read these shared reference documents:
+- `docs/critic-loop-rules.md` — Critic Loop execution rules
+- `docs/phase-gate-protocol.md` — Phase gate validation protocol
 
 ## Memory Usage
 

package/agents/selfish-security.md

@@ -1,12 +1,13 @@
 ---
 name: selfish-security
-description: "보안 스캔 에이전트 — 취약점 패턴과 프로젝트별 보안 특성을 세션 간 기억하여 스캔 정밀도를 향상시킨다."
+description: "Security scanning agent — remembers vulnerability patterns and project-specific security characteristics across sessions to improve scan precision."
 tools:
   - Read
   - Grep
   - Glob
   - Bash
   - Task
+  - WebSearch
 model: sonnet
 memory: project
 isolation: worktree
@@ -15,7 +16,13 @@ skills:
   - docs/phase-gate-protocol.md
 ---
 
-You are a security scanning agent for the selfish-pipeline project.
+You are a security scanning agent for the current project.
+
+## Reference Documents
+
+Before performing scans, read these shared reference documents:
+- `docs/critic-loop-rules.md` — Critic Loop execution rules
+- `docs/phase-gate-protocol.md` — Phase gate validation protocol
 
 ## Memory Usage
 

package/bin/cli.mjs

@@ -12,19 +12,19 @@ const SCOPES = [
   {
     key: "1",
     name: "user",
-    label: "User (개인 전체 프로젝트)",
+    label: "User (all projects for this user)",
     desc: "~/.claude/settings.json",
   },
   {
     key: "2",
     name: "project",
-    label: "Project (팀 공유, git 커밋 가능)",
+    label: "Project (shared with team, committable)",
     desc: ".claude/settings.json",
   },
   {
     key: "3",
     name: "local",
-    label: "Local (이 프로젝트만, gitignore)",
+    label: "Local (this project only, gitignored)",
     desc: ".claude/settings.local.json",
   },
 ];
@@ -44,48 +44,48 @@ async function main() {
   console.log("  ================================================");
   console.log();
 
-  // claude CLI 존재 확인
+  // Check claude CLI exists
   try {
     execSync("claude --version", { stdio: "pipe" });
   } catch {
-    console.error("  ✗ Claude Code CLI가 설치되어 있지 않습니다.");
-    console.error("    https://claude.ai/code 에서 설치하세요.");
+    console.error("  ✗ Claude Code CLI is not installed.");
+    console.error("    Install it from https://claude.ai/code");
     exit(1);
   }
 
   const rl = createInterface({ input: stdin, output: stdout });
 
   try {
-    console.log("  설치 범위를 선택하세요:\n");
+    console.log("  Select install scope:\n");
     for (const s of SCOPES) {
       console.log(`    ${s.key}) ${s.label}`);
       console.log(`       → ${s.desc}`);
     }
     console.log();
 
-    const answer = await rl.question("  선택 [1/2/3] (기본: 1): ");
+    const answer = await rl.question("  Choose [1/2/3] (default: 1): ");
     const choice = answer.trim() || "1";
     const scope = SCOPES.find((s) => s.key === choice);
 
     if (!scope) {
-      console.error("\n  ✗ 잘못된 선택입니다.");
+      console.error("\n  ✗ Invalid selection.");
       exit(1);
     }
 
-    console.log(`\n  → ${scope.label} 스코프로 설치합니다...\n`);
+    console.log(`\n  → Installing with ${scope.label} scope...\n`);
 
-    // Step 1: 마켓플레이스 등록
-    console.log("  [1/2] 마켓플레이스 등록...");
+    // Step 1: Register marketplace
+    console.log("  [1/2] Registering marketplace...");
     run(`claude plugin marketplace add ${GITHUB_REPO}`);
 
-    // Step 2: 플러그인 설치
-    console.log(`  [2/2] 플러그인 설치 (--scope ${scope.name})...`);
+    // Step 2: Install plugin
+    console.log(`  [2/2] Installing plugin (--scope ${scope.name})...`);
     const installed = run(
       `claude plugin install ${PLUGIN_NAME}@${MARKETPLACE_NAME} --scope ${scope.name}`
     );
 
     if (!installed) {
-      console.error("\n  ✗ 설치에 실패했습니다. 수동으로 시도하세요:");
+      console.error("\n  ✗ Installation failed. Try manually:");
       console.error(`    claude plugin marketplace add ${GITHUB_REPO}`);
       console.error(
         `    claude plugin install ${PLUGIN_NAME}@${MARKETPLACE_NAME} --scope ${scope.name}`
@@ -94,11 +94,11 @@ async function main() {
     }
 
     console.log();
-    console.log("  ✓ 설치 완료!");
+    console.log("  ✓ Installation complete!");
     console.log();
-    console.log("  다음 단계:");
-    console.log("    /selfish:init              프로젝트 설정 생성");
-    console.log('    /selfish:auto "기능 설명"   파이프라인 실행');
+    console.log("  Next steps:");
+    console.log("    /selfish:init                    Create project config");
+    console.log('    /selfish:auto "feature desc"      Run the pipeline');
     console.log();
   } finally {
     rl.close();
@@ -106,6 +106,6 @@ async function main() {
 }
 
 main().catch((err) => {
-  console.error(`\n  ✗ 설치 실패: ${err.message}`);
+  console.error(`\n  ✗ Installation failed: ${err.message}`);
   exit(1);
 });

package/commands/analyze.md

@@ -1,10 +1,9 @@
 ---
 name: selfish:analyze
-description: "아티팩트 정합성 검증 (읽기 전용)"
-argument-hint: "[검증 범위: spec-plan, tasks-only]"
+description: "Artifact consistency validation (read-only)"
+argument-hint: "[validation scope: spec-plan, tasks-only]"
 user-invocable: false
 context: fork
-agent: Explore
 allowed-tools:
   - Read
   - Grep
@@ -12,116 +11,116 @@ allowed-tools:
 model: haiku
 ---
 
-# /selfish:analyze — 아티팩트 정합성 검증
+# /selfish:analyze — Artifact Consistency Validation
 
-> spec.md, plan.md, tasks.md 간의 일관성과 품질을 검증한다.
-> **읽기 전용** — 파일을 수정하지 않는다.
+> Validates consistency and quality across spec.md, plan.md, and tasks.md.
+> **Read-only** — does not modify any files.
 
-## 인자
+## Arguments
 
-- `$ARGUMENTS` — (선택) 검증 범위 한정 (예: "spec-plan", "tasks-only")
+- `$ARGUMENTS` — (optional) limit validation scope (e.g., "spec-plan", "tasks-only")
 
-## 설정 로드
+## Config Load
 
-프로젝트 루트의 `CLAUDE.md` 또는 `.claude/CLAUDE.md`에서 다음 설정을 읽어 `config` 변수에 할당:
+Read the following settings from `CLAUDE.md` or `.claude/CLAUDE.md` at the project root and assign to the `config` variable:
 
 ```
-config.architecture = 프로젝트에서 사용하는 아키텍처 패턴
-                      (예: "FSD", "Clean Architecture", "Layered", "Modular Monolith")
-                      → CLAUDE.md에 명시된 아키텍처 기준. 없으면 "레이어드 아키텍처"로 가정.
+config.architecture = the architecture pattern used in the project
+                      (e.g., "FSD", "Clean Architecture", "Layered", "Modular Monolith")
+                      → Architecture standard specified in CLAUDE.md. Assume "Layered Architecture" if not present.
 ```
 
-## 실행 절차
+## Execution Steps
 
-### 1. 아티팩트 로드
+### 1. Load Artifacts
 
-`specs/{feature}/`에서:
-- **spec.md** (필수)
-- **plan.md** (필수)
-- **tasks.md** (있으면)
-- **research.md** (있으면)
+From `specs/{feature}/`:
+- **spec.md** (required)
+- **plan.md** (required)
+- **tasks.md** (if present)
+- **research.md** (if present)
 
-누락 파일이 있으면 경고하되 있는 것으로 진행.
+Warn about missing files but proceed with what is available.
 
-### 2. 검증 수행
+### 2. Run Validation
 
-6가지 카테고리를 검증:
+Validate across 6 categories:
 
-#### A. 중복 감지 (DUPLICATION)
-- spec.md 내 유사한 요구사항
-- tasks.md 내 겹치는 태스크
+#### A. Duplication Detection (DUPLICATION)
+- Similar requirements within spec.md
+- Overlapping tasks within tasks.md
 
-#### B. 모호성 감지 (AMBIGUITY)
-- 측정 불가능한 형용사 ("적절한", "빠른", "좋은")
-- TODO/TBD/FIXME 잔류
-- 불완전한 문장
+#### B. Ambiguity Detection (AMBIGUITY)
+- Unmeasurable adjectives ("appropriate", "fast", "good")
+- Residual TODO/TBD/FIXME markers
+- Incomplete sentences
 
-#### C. 커버리지 갭 (COVERAGE)
-- spec → plan: 모든 FR-*/NFR-*가 plan에 반영되었는가?
-- plan → tasks: plan의 File Change Map 모든 항목이 tasks에 있는가?
-- spec → tasks: 모든 요구사항이 태스크에 매핑되는가?
+#### C. Coverage Gaps (COVERAGE)
+- spec → plan: Are all FR-*/NFR-* reflected in the plan?
+- plan → tasks: Are all items in the plan's File Change Map present in tasks?
+- spec → tasks: Are all requirements mapped to tasks?
 
-#### D. 불일치 (INCONSISTENCY)
-- 용어 드리프트 (같은 개념에 다른 이름)
-- 충돌하는 요구사항
-- plan의 기술 결정과 tasks의 실행이 불일치
+#### D. Inconsistencies (INCONSISTENCY)
+- Terminology drift (different names for the same concept)
+- Conflicting requirements
+- Mismatches between technical decisions in plan and execution in tasks
 
-#### E. 원칙 준수 (PRINCIPLES)
-- memory/principles.md가 있으면 MUST 원칙 대비 검증
-- {config.architecture} 규칙 위반 가능성
+#### E. Principles Compliance (PRINCIPLES)
+- Validate against MUST principles in memory/principles.md if present
+- Potential violations of {config.architecture} rules
 
-#### F. 리스크 미식별 (RISK)
-- plan.md에 식별되지 않은 리스크가 있는가?
-- 외부 의존성 리스크
-- 성능 병목 가능성
+#### F. Unidentified Risks (RISK)
+- Are there risks not identified in plan.md?
+- External dependency risks
+- Potential performance bottlenecks
 
-### 3. 심각도 분류
+### 3. Severity Classification
 
-| 심각도 | 기준 |
-|--------|------|
-| **CRITICAL** | 원칙 위반, 핵심 기능 차단, 보안 문제 |
-| **HIGH** | 중복/충돌, 테스트 불가능, 커버리지 갭 |
-| **MEDIUM** | 용어 드리프트, 모호한 요구사항 |
-| **LOW** | 스타일 개선, 사소한 중복 |
+| Severity | Criteria |
+|----------|----------|
+| **CRITICAL** | Principles violation, core feature blocker, security issue |
+| **HIGH** | Duplication/conflict, untestable, coverage gap |
+| **MEDIUM** | Terminology drift, ambiguous requirements |
+| **LOW** | Style improvements, minor duplication |
 
-### 4. 결과 출력 (콘솔)
+### 4. Output Results (console)
 
 ```markdown
-## 정합성 분석 결과: {기능명}
+## Consistency Analysis Results: {feature name}
 
-### 발견사항
-| ID | 카테고리 | 심각도 | 위치 | 요약 | 권장 조치 |
-|----|----------|--------|------|------|-----------|
-| A-001 | COVERAGE | HIGH | spec FR-003 | tasks에 매핑 없음 | 태스크 추가 |
-| A-002 | AMBIGUITY | MEDIUM | spec NFR-001 | "빠르게" 측정 불가 | 수치 기준 추가 |
+### Findings
+| ID | Category | Severity | Location | Summary | Recommended Action |
+|----|----------|----------|----------|---------|-------------------|
+| A-001 | COVERAGE | HIGH | spec FR-003 | No mapping in tasks | Add task |
+| A-002 | AMBIGUITY | MEDIUM | spec NFR-001 | "quickly" is unmeasurable | Add numeric threshold |
 
-### 커버리지 요약
-| 매핑 | 비율 |
-|------|------|
+### Coverage Summary
+| Mapping | Coverage |
+|---------|----------|
 | spec → plan | {N}% |
 | plan → tasks | {N}% |
 | spec → tasks | {N}% |
 
-### 메트릭스
-- 총 요구사항: {N}개
-- 총 태스크: {N}개
-- 이슈: CRITICAL {N} / HIGH {N} / MEDIUM {N} / LOW {N}
+### Metrics
+- Total requirements: {N}
+- Total tasks: {N}
+- Issues: CRITICAL {N} / HIGH {N} / MEDIUM {N} / LOW {N}
 
-### 다음 단계
-{CRITICAL/HIGH 이슈에 대한 구체적 조치 제안}
+### Next Steps
+{Concrete action proposals for CRITICAL/HIGH issues}
 ```
 
-### 5. 최종 출력
+### 5. Final Output
 
 ```
-🔎 분석 완료
-├─ 발견: CRITICAL {N} / HIGH {N} / MEDIUM {N} / LOW {N}
-├─ 커버리지: spec→plan {N}%, plan→tasks {N}%, spec→tasks {N}%
-└─ 권장: {다음 액션}
+Analysis complete
+├─ Found: CRITICAL {N} / HIGH {N} / MEDIUM {N} / LOW {N}
+├─ Coverage: spec→plan {N}%, plan→tasks {N}%, spec→tasks {N}%
+└─ Recommended: {next action}
 ```
 
-## 주의사항
+## Notes
 
-- **읽기 전용**: 어떤 파일도 수정하지 않는다. 보고만 한다.
-- **오탐 주의**: 모호성 감지가 과도하지 않도록. 컨텍스트를 고려.
-- **선택적**: 파이프라인에서 필수가 아님. plan → tasks → implement 직행 가능.
+- **Read-only**: Do not modify any files. Report only.
+- **Avoid false positives**: Do not over-flag ambiguity. Consider context.
+- **Optional**: Not required in the pipeline. Can proceed plan → tasks → implement directly.