@ai-dev-methodologies/rlp-desk 0.9.0 → 0.9.1

package/docs/plans/validated-snacking-crayon.md

@@ -1,399 +1,188 @@
-# Plan: Worker Planning, Preset Sync, Brainstorm Exploration, Memory Bridge & Coding Principles
+# Plan: Flywheel Phase 1 — SV Report Generation + Brainstorm Feedback Loop
 
 ## Context
 
-rlp-desk의 Worker/Verifier 프롬프트와 brainstorm/init 흐름에 5가지 개선을 적용한다.
-기존 iron law 정책 체계의 후속 업데이트로, 검증된 패턴을 Worker/Verifier fresh context에 내장한다.
+rlp-desk의 flywheel 아키텍처(governance §8½ + brainstorm step 0)가 설계되어 있지만 구현이 끊겨 있다.
+`--with-self-verification` 플래그가 파싱되지만 실제 SV 리포트 생성 코드가 없고, brainstorm step 0도 SV 리포트를 읽는 로직이 없다.
 
-**문제:**
-1. `print_run_presets()`가 rlp-desk.md 옵션 인터페이스와 desync (stale 플래그, 틀린 기본값)
-2. Worker가 파일 읽자마자 바로 TDD로 넘어감 (계획 단계 없음)
-3. Brainstorm이 코드 안 보고 US 제안
-4. Brainstorm 결과가 campaign memory에 안 남음 (첫 Worker가 재발견)
-5. Worker/Verifier가 코딩 원칙 가이드라인 없이 작동 (글로벌 CLAUDE.md 의존 불가)
+**목표:** 캠페인 A → SV 리포트 생성 → 캠페인 B brainstorm이 A의 패턴 참조 — 최소한의 피드백 루프 완성.
 
-**브랜치:** `improve/worker-planning-and-preset-sync`
+**브랜치:** `feature/flywheel-sv-report`
 
 ---
 
-## Changes
-
-### Change 1: Fix Run Preset Desync
-**File:** `src/scripts/init_ralph_desk.zsh` lines 197-238
-
-Rewrite `print_run_presets()` to match `src/commands/rlp-desk.md` lines 142-200.
-
-**Desync table:**
-
-| current (init_ralph_desk.zsh) | canonical (rlp-desk.md) |
-|---|---|
-| `--final-consensus` (line 207) | `--consensus final-only` |
-| `gpt-5.3-codex-spark:high` (line 210) | `spark:high` |
-| `--verify-consensus` (line 232) | `--consensus off\|all\|final-only` |
-| worker default `sonnet` (line 230) | `haiku` |
-| verifier default `opus` (line 231) | per-US `sonnet`, final `opus` |
-| Missing `--mode tmux` in recommended | Present |
-| Missing 6 options | `--lock-worker-model`, `--consensus-model`, `--final-consensus-model`, `--cb-threshold`, `--iter-timeout`, `--final-verifier-model` |
+## Current State (Gap Analysis)
 
-**Action:** Replace lines 197-238 with function that mirrors rlp-desk.md lines 142-200.
+| 구성요소 | 상태 | 위치 |
+|----------|------|------|
+| `--with-self-verification` 플래그 파싱 | ✅ | run.mjs:142-144 |
+| 10섹션 SV 리포트 템플릿 정의 | ✅ | rlp-desk.md:522-573 |
+| §8½ 피드백 루프 정의 | ✅ | governance.md:629-635 |
+| Brainstorm step 0 정의 | ✅ | rlp-desk.md:115 |
+| `generateSVReport()` 함수 | ❌ | 존재하지 않음 |
+| campaign-main-loop.mjs에서 SV 호출 | ❌ | svSummary 파라미터 안 전달 (465, 568, 590) |
+| analytics 디렉토리 생성 | ❌ | 코드 없음 |
+| SV 리포트 테스트 | ❌ | us007에 없음 |
 
-### Change 2: Add Worker Planning Step
-**Files:**
-- `src/scripts/init_ralph_desk.zsh` Worker prompt — insert between line 316 and line 318
-- `src/governance.md` line 217 — add `plan` to step types
-- `src/scripts/init_ralph_desk.zsh` Verifier prompt — add audit after line 478
-
-**Insert after line 316 ("Execute the plan for $SLUG."), before line 318 ("## Before you start"):**
-
-```
-## Planning (before writing any code)
-After reading all files, BEFORE writing any test or code:
-1. List the specific files you will create or modify
-2. For each AC in the contract, state your approach in 1 sentence
-3. Identify ordering constraints (which AC depends on which)
-4. Record as first execution_step: {"step": "plan", "ac_id": "all", "command": null, "exit_code": null, "summary": "Plan: [files], [approach], [order]"}
-Keep planning lightweight — 1-2 sentences per AC, not a detailed analysis.
-If the plan reveals the contract is unclear or infeasible, signal "blocked" immediately.
-```
-
-**governance.md line 217:** Change from:
-```
-- Step types: `write_test`, `verify_red`, `implement`, `verify_green`, `refactor`, `commit`, `verify`, `verify_existing`
-```
-to:
-```
-- Step types: `plan`, `write_test`, `verify_red`, `implement`, `verify_green`, `refactor`, `commit`, `verify`, `verify_existing`
-```
-
-**Verifier prompt after line 478 (Worker Process Audit):** Add:
-```
-   - Planning step presence: done-claim execution_steps should include a `plan` step as the first entry. If missing, record in reasoning as {"check": "Planning Step", "decision": "info", "basis": "plan step present/absent"} — informational only (does not affect pass/fail verdict)
-```
-
-### Change 3: Brainstorm Exploration Phase
-**File:** `src/commands/rlp-desk.md` — insert between line 25 and line 26
-
-**Insert after line 25 ("2. **Objective**") and before line 26 ("3. **User Stories**"):**
-
-```
-2.5. **Codebase Exploration** — Before proposing user stories, examine the project:
-   - Read the project's entry points, key modules, and test structure
-   - Identify architectural patterns in use (frameworks, conventions, test setup)
-   - Note constraints the Worker will encounter (dependencies, build system, existing code style)
-   - Present findings: "I explored the codebase and found: [patterns], [constraints], [existing tests]. This informs the US breakdown below."
-   - If the project is new/empty, skip this step and note "greenfield project."
-```
-
-### Change 4: Memory Bridge
-**Files:**
-- `src/commands/rlp-desk.md` line 131
-- `src/scripts/init_ralph_desk.zsh` lines 578-580 (campaign memory template)
-- `src/scripts/init_ralph_desk.zsh` line 355 area (Worker prompt iteration rules)
+---
 
-**rlp-desk.md line 131:** Change from:
-```
-If brainstorm was done, auto-fill PRD and test-spec with the results.
-```
-to:
-```
-If brainstorm was done, auto-fill:
-- PRD and test-spec with the brainstorm results
-- Campaign memory "Key Decisions" with architectural decisions from brainstorm
-- Campaign memory "Patterns Discovered" with codebase exploration findings (from step 2.5)
-```
+## Changes
 
-**init_ralph_desk.zsh lines 578-580:** Change from:
+### Change 1: `generateSVReport()` 함수 구현
+**File:** `src/node/reporting/campaign-reporting.mjs` (확장)
+
+기존 `generateCampaignReport()` (line 159) 옆에 `generateSVReport()` 추가.
+
+**Input:**
+- `slug` — campaign slug
+- `logsDir` — `.claude/ralph-desk/logs/<slug>/` (done-claim, verify-verdict 파일 위치)
+- `prdFile` — PRD 경로
+- `testSpecFile` — test-spec 경로
+- `analyticsFile` — campaign.jsonl 경로
+- `outputDir` — `~/.claude/ralph-desk/analytics/<slug>/` (SV 리포트 출력)
+
+**로직:**
+1. `logsDir`에서 `iter-*-done-claim.json`, `iter-*-verify-verdict.json` 파일 수집
+2. done-claim에서 execution_steps 파싱 → Worker Process Quality 집계
+3. verify-verdict에서 reasoning 파싱 → Verifier Judgment Quality 집계
+4. campaign.jsonl에서 per-iteration 요약 → Automated Validation Summary
+5. AC lifecycle 추적 (first claimed, first verified, reopen count)
+6. 10섹션 마크다운 생성
+7. `outputDir/self-verification-report-NNN.md`에 버전드 파일 쓰기
+8. `outputDir/self-verification-data.json`에 구조화 데이터 쓰기
+
+**10섹션 구현 우선순위:**
+- 필수 (핵심 피드백): §1 Automated Validation, §3 Worker Process Quality, §7 Patterns, §8 Recommendations
+- 중요 (진단): §2 Failure Deep Dive, §4 Verifier Quality, §5 AC Lifecycle
+- 보조 (참고): §6 Test-Spec Adherence, §9 Cost, §10 Blind Spots
+
+**Return:** `{ reportPath, version, summary }` — summary는 generateCampaignReport()의 svSummary 파라미터로 전달
+
+### Change 2: campaign-main-loop.mjs에 SV 생성 연결
+**File:** `src/node/runner/campaign-main-loop.mjs` lines 465, 568, 590
+
+현재 `generateCampaignReport()` 호출 3곳에서:
+1. `options.withSelfVerification` 체크
+2. true면 `generateSVReport()` 호출
+3. 결과의 summary를 `svSummary` 파라미터로 전달
+
+**Before (현재):**
+```javascript
+await generateCampaignReport({
+  slug, reportFile, prdFile, statusFile, analyticsFile, now
+});
+```
+
+**After:**
+```javascript
+let svSummary = 'N/A — --with-self-verification not enabled';
+if (options.withSelfVerification) {
+  const sv = await generateSVReport({
+    slug, logsDir: paths.logsDir, prdFile: paths.prdFile,
+    testSpecFile: paths.testSpecFile, analyticsFile: paths.analyticsFile,
+    outputDir: paths.analyticsDir,
+  });
+  svSummary = sv.summary;
+}
+await generateCampaignReport({
+  slug, reportFile, prdFile, statusFile, analyticsFile, now, svSummary
+});
 ```
-## Key Decisions
 
-## Patterns Discovered
-```
-to:
-```
-## Key Decisions
-(seeded from brainstorm — do not erase, only append)
+### Change 3: analytics 디렉토리 생성
+**File:** `src/node/runner/campaign-main-loop.mjs` (초기화 단계)
 
-## Patterns Discovered
-(seeded from brainstorm codebase exploration — do not erase, only append)
-```
+캠페인 시작 시 `~/.claude/ralph-desk/analytics/<slug>/` 디렉토리 생성.
+- slug에 `--<root_hash>` 접미사 추가 (cross-project 충돌 방지, rlp-desk.md:248 스펙)
+- metadata.json 초기 작성
 
-**init_ralph_desk.zsh Worker prompt, after line 355 ("- Rewrite campaign memory in full."):** Add:
-```
-- When rewriting campaign memory, PRESERVE the Key Decisions and Patterns Discovered sections from prior iterations — append new entries, do not erase existing ones.
+**paths 객체에 추가:**
+```javascript
+analyticsDir: join(homeDir, '.claude/ralph-desk/analytics', `${slug}--${rootHash}`),
 ```
 
-### Change 5: Coding Principles (Karpathy Guidelines)
-**Files:**
-- `src/scripts/init_ralph_desk.zsh` Worker prompt — insert after line 316, before Change 2's Planning section
-- `src/scripts/init_ralph_desk.zsh` Verifier prompt — insert after line 429
+### Change 4: Brainstorm Step 0 SV Report Feedback 구현
+**File:** `src/commands/rlp-desk.md` brainstorm section (line 115 area)
 
-**Worker prompt — insert after line 316 ("Execute the plan for $SLUG."), as first section:**
+현재 step 0은 한 줄 설명만 있음. 구체적 실행 절차 추가:
 
-```
-## Coding Principles (applies to ALL work in this iteration)
-
-1. Think Before Coding
-   Don't assume. Don't hide confusion. Surface tradeoffs.
-   - State assumptions explicitly. If uncertain, signal blocked with your options
-     listed — do not guess.
-   - If multiple interpretations exist, present them in blocked signal — do not
-     pick silently.
-   - If a simpler approach exists, note it in your plan.
-   - If something important is unclear, stop and name what is confusing.
-
-2. Simplicity First
-   Minimum code that solves the problem. Nothing speculative.
-   - No features beyond what was asked.
-   - No abstractions for single-use code.
-   - No configurability that was not specified.
-   - No defensive handling for implausible scenarios unless the context requires it.
-   - If 200 lines could be 50, rewrite it.
-   Ask: "Would a strong senior engineer call this overcomplicated?" If yes, simplify.
-
-3. Surgical Changes
-   Touch only what you must. Clean up only your own mess.
-   - Do not improve adjacent code, comments, or formatting unless required by the task.
-   - Do not refactor unrelated code.
-   - Match the local style unless there is a compelling reason not to.
-   - If unrelated dead code is noticed, mention it in done-claim — do not delete it.
-   - Remove imports, variables, or functions that YOUR changes made unused.
-   - Do not remove pre-existing dead code.
-   Test: every changed line should trace directly to the contract.
-
-4. Goal-Driven Execution
-   Define success criteria. Loop until verified.
-   These principles are enforced by the TDD Mandate and Planning step below.
-   If success criteria for any AC are unclear, signal blocked.
-```
-
-**Verifier prompt — insert after line 429 ("Independent verifier for Ralph Desk: $SLUG"), before line 431 ("## Iron Law"):**
-
-```
-## Verification Principles
-
-1. Think Before Judging
-   Don't assume. Don't default to PASS or FAIL without evidence.
-   - State your assumptions about what PASS looks like for each AC before
-     checking evidence.
-   - If evidence is ambiguous or incomplete, say what is unclear and why —
-     do not default to either verdict.
-   - If multiple interpretations of an AC exist, flag it as a spec issue.
-
-2. Goal-Driven Verification
-   Define the specific evidence required for PASS before you start checking.
-   - For each AC, state: "PASS requires [specific evidence]."
-   - Verify against that criteria, not against a general impression of code quality.
-   - If success criteria are unclear, note it in reasoning — do not invent criteria.
+```markdown
+0. **SV Report Feedback** — If a prior campaign's self-verification report exists:
+   a. Scan `~/.claude/ralph-desk/analytics/` for directories matching this project root
+   b. Read the latest `self-verification-report-*.md` from each matching directory
+   c. Extract from §7 (Patterns) and §8 (Recommendations):
+      - Which US types/sizes failed most frequently
+      - Which AC quality dimensions scored lowest
+      - Which model tiers underperformed for this project's complexity
+      - Specific brainstorm/PRD/test-spec recommendations from prior campaigns
+   d. Present findings to user: "Prior campaign analysis found: [patterns]. Recommendations: [suggestions]."
+   e. If no prior reports exist, skip and note "No prior campaign data available."
 ```
 
 ---
 
 ## Implementation Sequence
 
-| Wave | Changes | Files | Risk |
-|------|---------|-------|------|
-| 1 | Change 1 (run preset desync) | init_ralph_desk.zsh | LOW |
-| 2 | Change 5 (coding principles) | init_ralph_desk.zsh | LOW |
-| 2 | Change 2 (planning step) | init_ralph_desk.zsh + governance.md | LOW-MED |
-| 3 | Change 3 (brainstorm exploration) | rlp-desk.md | LOW |
-| 3 | Change 4 (memory bridge) | rlp-desk.md + init_ralph_desk.zsh | MEDIUM |
+| Wave | Changes | Files | Dependency |
+|------|---------|-------|------------|
+| 1 | Change 1 (generateSVReport) | campaign-reporting.mjs | None |
+| 1 | Change 3 (analytics dir) | campaign-main-loop.mjs + paths.mjs | None |
+| 2 | Change 2 (SV 호출 연결) | campaign-main-loop.mjs | Change 1, 3 |
+| 3 | Change 4 (brainstorm step 0) | rlp-desk.md | Change 1 (reports exist) |
 
-**Order rationale:**
-- Wave 1: Standalone bugfix, no dependencies
-- Wave 2: Coding Principles first (top of prompt), then Planning step (uses principles). Both in init_ralph_desk.zsh Worker prompt.
-- Wave 3: rlp-desk.md changes. Change 4 depends on Change 3 (exploration produces findings that get seeded).
+Wave 1은 병렬 가능 (서로 독립).
+Wave 2는 Wave 1 완료 후.
+Wave 3는 별도 — rlp-desk.md만 수정.
 
 ---
 
-## TDD Verification Plan
-
-Each change has tests written FIRST, verified to fail, then implementation, then re-verify.
-
-### Test Script: `tests/test_template_generation.sh`
-
-```bash
-#!/bin/bash
-# TDD tests for template generation changes
-# Run: bash tests/test_template_generation.sh
-set -euo pipefail
-
-SCRIPT="src/scripts/init_ralph_desk.zsh"
-CMD="src/commands/rlp-desk.md"
-GOV="src/governance.md"
-PASS=0; FAIL=0; TOTAL=0
-
-assert_contains() {
-  local file="$1" pattern="$2" label="$3"
-  TOTAL=$((TOTAL+1))
-  if grep -q "$pattern" "$file" 2>/dev/null; then
-    echo "  PASS: $label"; PASS=$((PASS+1))
-  else
-    echo "  FAIL: $label (pattern not found: $pattern)"; FAIL=$((FAIL+1))
-  fi
-}
-
-assert_not_contains() {
-  local file="$1" pattern="$2" label="$3"
-  TOTAL=$((TOTAL+1))
-  if grep -q "$pattern" "$file" 2>/dev/null; then
-    echo "  FAIL: $label (stale pattern still present: $pattern)"; FAIL=$((FAIL+1))
-  else
-    echo "  PASS: $label"; PASS=$((PASS+1))
-  fi
-}
-
-echo "=== Change 1: Run Preset Desync ==="
-assert_not_contains "$SCRIPT" "\-\-final-consensus" "C1: no --final-consensus"
-assert_not_contains "$SCRIPT" "gpt-5.3-codex-spark" "C1: no gpt-5.3-codex-spark"
-assert_not_contains "$SCRIPT" "\-\-verify-consensus" "C1: no --verify-consensus"
-assert_contains "$SCRIPT" "\-\-consensus final-only" "C1: --consensus final-only present"
-assert_contains "$SCRIPT" "spark:high" "C1: spark:high present"
-assert_contains "$SCRIPT" "default: haiku" "C1: worker default haiku"
-assert_contains "$SCRIPT" "\-\-lock-worker-model" "C1: --lock-worker-model in options"
-assert_contains "$SCRIPT" "\-\-cb-threshold" "C1: --cb-threshold in options"
-assert_contains "$SCRIPT" "\-\-iter-timeout" "C1: --iter-timeout in options"
-assert_contains "$SCRIPT" "\-\-consensus-model" "C1: --consensus-model in options"
-assert_contains "$SCRIPT" "\-\-mode tmux" "C1: --mode tmux in recommended"
-
-echo ""
-echo "=== Change 2: Worker Planning Step ==="
-assert_contains "$SCRIPT" "## Planning" "C2: Planning section in Worker prompt"
-assert_contains "$SCRIPT" "step.*plan.*ac_id.*all" "C2: plan execution_step format"
-assert_contains "$SCRIPT" "Keep planning lightweight" "C2: lightweight constraint"
-assert_contains "$GOV" "plan.*write_test.*verify_red" "C2: plan in §1f step types"
-assert_contains "$SCRIPT" "Planning Step.*decision.*info" "C2: Verifier plan audit"
-
-echo ""
-echo "=== Change 3: Brainstorm Exploration ==="
-assert_contains "$CMD" "Codebase Exploration" "C3: exploration step present"
-assert_contains "$CMD" "greenfield project" "C3: greenfield skip path"
-assert_contains "$CMD" "entry points.*key modules" "C3: exploration instructions"
-
-echo ""
-echo "=== Change 4: Memory Bridge ==="
-assert_contains "$CMD" "Campaign memory.*Key Decisions" "C4: init seeds memory instruction"
-assert_contains "$SCRIPT" "seeded from brainstorm" "C4: seed markers in template"
-assert_contains "$SCRIPT" "PRESERVE the Key Decisions" "C4: Worker preservation instruction"
-
-echo ""
-echo "=== Change 5: Coding Principles ==="
-assert_contains "$SCRIPT" "## Coding Principles" "C5: Worker coding principles section"
-assert_contains "$SCRIPT" "Think Before Coding" "C5: principle 1 in Worker"
-assert_contains "$SCRIPT" "Simplicity First" "C5: principle 2 in Worker"
-assert_contains "$SCRIPT" "Surgical Changes" "C5: principle 3 in Worker"
-assert_contains "$SCRIPT" "Goal-Driven Execution" "C5: principle 4 in Worker"
-assert_contains "$SCRIPT" "## Verification Principles" "C5: Verifier principles section"
-assert_contains "$SCRIPT" "Think Before Judging" "C5: Verifier principle 1"
-assert_contains "$SCRIPT" "Goal-Driven Verification" "C5: Verifier principle 2"
-
-echo ""
-echo "=== RESULTS ==="
-echo "PASS: $PASS / $TOTAL"
-echo "FAIL: $FAIL / $TOTAL"
-[ $FAIL -eq 0 ] && echo "ALL TESTS PASSED" || echo "SOME TESTS FAILED"
-exit $FAIL
-```
-
-### TDD Flow Per Wave
+## TDD Plan
 
-**Wave 1 (Change 1):**
-1. Write test → run → expect 11 FAIL (stale patterns present, new patterns absent)
-2. Implement Change 1
-3. Run test → expect 11 PASS
-4. `bash -n src/scripts/init_ralph_desk.zsh` (syntax check)
+### 테스트 파일: `tests/node/test-sv-report.mjs` (새로 생성)
 
-**Wave 2 (Changes 5, 2):**
-1. Run test → expect Change 5 (7 tests) + Change 2 (5 tests) = 12 FAIL
-2. Implement Change 5 (Worker + Verifier principles)
-3. Run test → expect Change 5 PASS, Change 2 still FAIL
-4. Implement Change 2 (Planning step + governance + Verifier audit)
-5. Run test → expect all PASS
-6. `bash -n src/scripts/init_ralph_desk.zsh` (syntax check)
+**Change 1 테스트:**
+- T1.1: done-claim + verify-verdict 파일에서 10섹션 리포트 생성
+- T1.2: 빈 logs 디렉토리 → graceful 처리 (빈 리포트)
+- T1.3: Worker Process Quality §3 — TDD compliance % 정확성
+- T1.4: Verifier Judgment Quality §4 — reasoning completeness % 정확성
+- T1.5: AC Lifecycle §5 — reopen count 추적
+- T1.6: Patterns §7 + Recommendations §8 — 패턴 추출
+- T1.7: 버전드 파일 쓰기 (NNN 증가)
+- T1.8: self-verification-data.json 구조 검증
 
-**Wave 3 (Changes 3, 4):**
-1. Run test → expect Change 3 (3 tests) + Change 4 (3 tests) = 6 FAIL
-2. Implement Change 3 (brainstorm exploration)
-3. Run test → expect Change 3 PASS, Change 4 still FAIL
-4. Implement Change 4 (memory bridge — rlp-desk.md + init)
-5. Run test → expect all PASS
+**Change 2 테스트:**
+- T2.1: withSelfVerification=false → svSummary 기본값
+- T2.2: withSelfVerification=true → generateSVReport 호출됨
 
-### Artifact-Based End-to-End Verification
+**Change 3 테스트:**
+- T3.1: analytics 디렉토리 생성 확인
+- T3.2: metadata.json 구조 검증
 
-After all waves, run init on a test slug and verify generated artifacts:
-
-```bash
-# E2E: generate artifacts and verify
-TEST_SLUG="test-karpathy-e2e"
-TEST_DIR=$(mktemp -d)
-cd "$TEST_DIR" && git init && mkdir -p .claude/ralph-desk
-
-bash /path/to/src/scripts/init_ralph_desk.zsh "$TEST_SLUG" "test objective"
-
-# Check Worker prompt
-grep -q "## Coding Principles" .claude/ralph-desk/prompts/$TEST_SLUG.worker.prompt.md
-grep -q "## Planning" .claude/ralph-desk/prompts/$TEST_SLUG.worker.prompt.md
-grep -q "Think Before Coding" .claude/ralph-desk/prompts/$TEST_SLUG.worker.prompt.md
-grep -q "PRESERVE the Key Decisions" .claude/ralph-desk/prompts/$TEST_SLUG.worker.prompt.md
-
-# Check Verifier prompt
-grep -q "## Verification Principles" .claude/ralph-desk/prompts/$TEST_SLUG.verifier.prompt.md
-grep -q "Think Before Judging" .claude/ralph-desk/prompts/$TEST_SLUG.verifier.prompt.md
-
-# Check campaign memory
-grep -q "seeded from brainstorm" .claude/ralph-desk/memos/$TEST_SLUG-memory.md
-
-# Check run presets (capture init output)
-# ... verify --consensus, spark:high, haiku defaults appear
-
-rm -rf "$TEST_DIR"
-```
+**Change 4 테스트:**
+- T4.1: rlp-desk.md에 step 0 실행 절차 존재 (grep)
 
 ---
 
-## Self-Verification Gate (CLAUDE.md mandatory)
+## Verification
 
-3 scenarios required because `governance.md`, `rlp-desk.md`, `init_ralph_desk.zsh` all change.
+### TDD Flow
+1. 테스트 작성 → RED (generateSVReport 없으므로)
+2. Change 1 구현 → 테스트 GREEN
+3. Change 3 구현 → analytics dir 테스트 GREEN
+4. Change 2 구현 → 연결 테스트 GREEN
+5. Change 4 구현 → grep 테스트 GREEN
 
-**Scenario 1: LOW risk — greenfield campaign, brainstorm skipped**
-- Init with test slug, no brainstorm
-- Verify: Worker prompt has Coding Principles + Planning section, run presets correct, campaign memory has default template (seed markers present but empty), Verifier has Verification Principles
-- Layers: L1 (grep tests) + L3 (E2E artifact check)
+### E2E Verification
+1. 테스트 프로젝트에서 campaign 실행 (with-self-verification 플래그)
+2. `~/.claude/ralph-desk/analytics/<slug>/self-verification-report-001.md` 생성 확인
+3. 리포트에 10섹션 존재 확인
+4. 두 번째 campaign brainstorm에서 첫 캠페인 패턴 참조 확인
 
-**Scenario 2: MEDIUM risk — full brainstorm flow**
-- Brainstorm + init with codex installed
-- Verify: exploration step in brainstorm, init seeds memory, Worker preserves seeds, run presets show cross-engine commands, Verifier audits plan step
-- Layers: L1 + L2 (real integration) + L3
-
-**Scenario 3: CRITICAL risk — governance change verification**
-- Verify governance §1f has `plan` in step types
-- Simulate: Worker without plan step → Verifier records `info` (not fail)
-- Simulate: Worker erases Key Decisions → next Worker loses context
-- Layers: L1 + L2 + L3 + governance compliance
-
----
-
-## Post-Commit Checklist
-
-1. Local file sync (ALL distributable files):
-```bash
-cp src/commands/rlp-desk.md ~/.claude/commands/rlp-desk.md
-cp src/governance.md ~/.claude/ralph-desk/governance.md
-cp src/scripts/init_ralph_desk.zsh ~/.claude/ralph-desk/init_ralph_desk.zsh
-cp src/scripts/run_ralph_desk.zsh ~/.claude/ralph-desk/run_ralph_desk.zsh
-cp src/scripts/lib_ralph_desk.zsh ~/.claude/ralph-desk/lib_ralph_desk.zsh
-cp README.md ~/.claude/ralph-desk/README.md
-```
-
-2. Verify sync:
-```bash
-diff -q src/commands/rlp-desk.md ~/.claude/commands/rlp-desk.md
-diff -q src/governance.md ~/.claude/ralph-desk/governance.md
-diff -q src/scripts/init_ralph_desk.zsh ~/.claude/ralph-desk/init_ralph_desk.zsh
-diff -q src/scripts/run_ralph_desk.zsh ~/.claude/ralph-desk/run_ralph_desk.zsh
-diff -q src/scripts/lib_ralph_desk.zsh ~/.claude/ralph-desk/lib_ralph_desk.zsh
-diff -q README.md ~/.claude/ralph-desk/README.md
-```
-All must produce no output.
+### Self-Verification Gate
+governance.md 변경 없음 (§8½는 이미 정의됨). rlp-desk.md만 변경.
+init_ralph_desk.zsh 변경 없으면 2시나리오만 필요:
+- LOW: SV 리포트 없는 상태에서 brainstorm → "No prior data" 스킵
+- MEDIUM: SV 리포트 있는 상태에서 brainstorm → 패턴 참조
 
 ---
 
@@ -401,7 +190,15 @@ All must produce no output.
 
 | File | Changes |
 |------|---------|
-| `src/scripts/init_ralph_desk.zsh` | C1 (lines 197-238), C2 (lines 316-318, 478), C4 (lines 355, 578-580), C5 (lines 316, 429) |
-| `src/commands/rlp-desk.md` | C3 (lines 25-26), C4 (line 131) |
-| `src/governance.md` | C2 (line 217) |
-| `tests/test_template_generation.sh` | New — TDD test script |
+| `src/node/reporting/campaign-reporting.mjs` | Change 1: generateSVReport() 추가 |
+| `src/node/runner/campaign-main-loop.mjs` | Change 2: SV 호출 연결, Change 3: analytics dir |
+| `src/node/shared/paths.mjs` | Change 3: analyticsDir path 추가 |
+| `src/commands/rlp-desk.md` | Change 4: brainstorm step 0 절차 확장 |
+| `tests/node/test-sv-report.mjs` | 새로 생성 — SV 리포트 테스트 |
+
+### Reuse 가능한 기존 코드
+- `versionFile()` (campaign-reporting.mjs:47-60) — 버전드 파일 쓰기
+- `readAnalytics()` (campaign-reporting.mjs:70-80) — campaign.jsonl 파싱
+- `readJsonIfExists()` (campaign-reporting.mjs:62-68) — JSON 안전 읽기
+- `summarizeUsStatus()` (campaign-reporting.mjs:91-96) — US 상태 집계
+- `summarizeVerificationResults()` (campaign-reporting.mjs:98-102) — 검증 결과 집계