oh-my-customcode 0.105.1 → 0.106.1

package/README.md

@@ -13,7 +13,7 @@
 
 **[한국어 문서 (Korean)](./README_ko.md)**
 
-48 agents. 113 skills. 22 rules. One command.
+49 agents. 113 skills. 22 rules. One command.
 
 ```bash
 npm install -g oh-my-customcode && cd your-project && omcustom init
@@ -111,7 +111,7 @@ Agent(arch-documenter):haiku      ┘
 
 ---
 
-### Agents (48)
+### Agents (49)
 
 | Category | Count | Agents |
 |----------|-------|--------|
@@ -126,7 +126,7 @@ Agent(arch-documenter):haiku      ┘
 | QA | 3 | qa-planner, qa-writer, qa-engineer |
 | Security | 1 | sec-codeql |
 | Managers | 6 | mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sauron, mgr-claude-code-bible |
-| System | 2 | sys-memory-keeper, sys-naggy |
+| System | 3 | sys-memory-keeper, sys-naggy, tracker-checkpoint |
 
 Each agent declares its tools, model, memory scope, and limitations in YAML frontmatter. Tool budgets are enforced per agent type for accuracy.
 
@@ -222,7 +222,7 @@ Key rules: R010 (orchestrator never writes files), R009 (parallel execution mand
 
 ---
 
-### Guides (42)
+### Guides (43)
 
 Reference documentation covering best practices, architecture decisions, and integration patterns. Located in `guides/` at project root, covering topics from agent design to CI/CD to observability.
 
@@ -271,7 +271,7 @@ omcustom serve-stop            # Stop Web UI
 your-project/
 ├── CLAUDE.md                   # Entry point
 ├── .claude/
-│   ├── agents/                 # 48 agent definitions
+│   ├── agents/                 # 49 agent definitions
 │   ├── skills/                 # 113 skill modules
 │   ├── rules/                  # 22 governance rules (R000-R021)
 │   ├── hooks/                  # 15 lifecycle hook scripts
@@ -279,7 +279,7 @@ your-project/
 │   ├── specs/                  # Extracted canonical specs
 │   ├── contexts/               # 4 shared context files
 │   └── ontology/               # Knowledge graph for RAG
-└── guides/                     # 42 reference documents
+└── guides/                     # 43 reference documents
 ```
 
 ---

package/dist/cli/index.js

@@ -2334,7 +2334,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "0.105.1",
+    version: "0.106.1",
     description: "Batteries-included agent harness for Claude Code",
     type: "module",
     bin: {

package/dist/index.js

@@ -2014,7 +2014,7 @@ var package_default = {
   workspaces: [
     "packages/*"
   ],
-  version: "0.105.1",
+  version: "0.106.1",
   description: "Batteries-included agent harness for Claude Code",
   type: "module",
   bin: {

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "0.105.1",
+  "version": "0.106.1",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/agents/tracker-checkpoint.md

@@ -0,0 +1,72 @@
+---
+name: tracker-checkpoint
+description: Pipeline execution state tracker with checkpoint persistence. Reads/writes /tmp/.claude-pipeline-*-{PPID}.json state files and validates state transitions. Used by dag-orchestration for resume-after-failure and pipeline-guards for quality gate state.
+model: sonnet
+effort: medium
+tools: [Read, Write, Edit, Bash, Glob, Grep]
+memory: project
+skills: [dag-orchestration, pipeline-guards]
+domain: universal
+permissionMode: bypassPermissions
+---
+
+# Tracker Checkpoint Agent
+
+## Purpose
+
+Pipeline 실행 상태를 persistent checkpoint 파일로 관리. `/pipeline resume`, `dag-orchestration`, `pipeline-guards`와 협력하여 실패 후 재개를 가능하게 합니다.
+
+## Capabilities
+
+- Read/write `/tmp/.claude-pipeline-{name}-{PPID}.json` state files
+- Validate state transitions (pending → running → completed | failed)
+- Coordinate with dag-orchestration for step-level checkpointing
+- Coordinate with pipeline-guards for gate-level state snapshots
+- Support `/pipeline resume` by loading last known state
+
+## Workflow
+
+### 1. Pipeline Start (Bootstrap)
+- Create `/tmp/.claude-pipeline-{name}-{PPID}.json` with initial state
+- Record: pipeline name, started timestamp, total steps, current_step=0
+
+### 2. Per-Step Checkpoint
+- After each step: update state file atomically
+- Record: step name, status, duration_ms, output artifacts paths
+- Status transitions: pending → running → completed | failed
+
+### 3. Failure Freeze
+- On step failure: mark status=halted, preserve state for resume
+- Capture: error message, stack trace (if any), partial artifacts
+
+### 4. Resume Coordination
+- On `/pipeline resume`: scan `/tmp/.claude-pipeline-*-{PPID}.json`
+- Return state to orchestrator: name, failed step, error, options (retry/skip/abort)
+- On retry: reset failed step to pending, resume execution
+
+## State File Schema
+
+```json
+{
+  "pipeline": "{name}",
+  "started": "ISO-8601",
+  "status": "running|completed|halted",
+  "current_step": 0,
+  "steps": [
+    {"name": "triage", "status": "completed", "duration_ms": 5000, "artifacts": []},
+    {"name": "plan", "status": "running"}
+  ]
+}
+```
+
+## Integration Points
+
+- `dag-orchestration` skill — step dependency resolution + tracker coordination
+- `pipeline-guards` skill — guard gate state preservation
+- `pipeline` skill — `/pipeline resume` state loader
+
+## Rules Compliance
+
+- R006: Agent artifact; skills (dag-orchestration, pipeline-guards) are source
+- R010: File modifications via Write/Edit (prefer over Bash for .claude/ paths)
+- R017: Structural changes require sauron verification

package/templates/.claude/skills/dag-orchestration/SKILL.md

@@ -57,7 +57,7 @@ nodes:
     depends_on: [test, review, docs]
 
 config:
-  max_parallel: 4          # R009 limit
+  max_parallel: 4          # R009 soft default (hard cap: 5)
   failure_strategy: stop   # stop | skip | retry
   retry_count: 2           # Max retries per node (if strategy=retry)
   timeout_per_node: 300    # Seconds per node (0 = no limit)
@@ -76,7 +76,11 @@ config:
    c. On completion:
       - Success → decrement in-degree of dependents
       - Failure → apply failure_strategy
-   d. Enqueue newly-ready nodes (in-degree = 0)
+   d. Stall check:
+      - If running node duration > 2x average completed duration
+      - AND pending nodes exist with in-degree = 0 (ignoring stalled node's edges)
+      - THEN enqueue those independent nodes immediately (adaptive split)
+   e. Enqueue newly-ready nodes (in-degree = 0)
 6. Verify all nodes executed (detect unreachable nodes)
 ```
 
@@ -84,11 +88,12 @@ config:
 
 | Rule | Detail |
 |------|--------|
-| Max parallel | 4 concurrent nodes (R009) |
+| Max parallel | 5 concurrent nodes max, 4 default (R009) |
 | Agent Teams gate | 3+ parallel nodes → check R018 eligibility |
 | Orchestrator only | DAG scheduling runs in main conversation (R010) |
 | Node execution | Each node = one Task tool call to specified agent |
 | State tracking | `/tmp/.claude-dag-$PPID.json` |
+| Stall detection | Running node > 2x avg completed duration → enqueue independent pending nodes early |
 
 ## Failure Strategies
 
@@ -193,9 +198,47 @@ Execute? [Y/n]
 
 The orchestrator builds the DAG from this inline format and executes using the same algorithm.
 
+## State Management via tracker-checkpoint
+
+Pipeline 상태는 `tracker-checkpoint` 에이전트로 위임됩니다.
+
+### Flow
+
+1. Pipeline 시작 → orchestrator가 tracker-checkpoint 호출 → 초기 state 파일 생성 (`/tmp/.claude-pipeline-{name}-{PPID}.json`)
+2. 각 step 후 → tracker-checkpoint가 state 업데이트 (atomic write)
+3. step 실패 → tracker-checkpoint가 halted 상태로 freeze
+4. `/pipeline resume` → tracker-checkpoint가 state 로드 → orchestrator에 복원 옵션 제공
+
+### Integration
+
+- PPID-scoped state file 경로: `/tmp/.claude-pipeline-{name}-{PPID}.json`
+- step 실행 전후로 tracker-checkpoint delegation
+- resume 시 checkpoint → dag 재빌드 → 미완료 step부터 재개
+
+See `.claude/agents/tracker-checkpoint.md` for agent spec.
+
 ## Limitations
 
 - No cycles allowed (DAG = acyclic)
 - Max 20 nodes per workflow (complexity guard)
 - Nested DAGs not supported (flatten instead)
 - Cross-workflow dependencies not supported
+
+## External References
+
+### Multica — Managed Agent Platform
+
+> Reference: [Multica](https://github.com/multica-ai/multica) — managed agent platform for Claude Code/Codex.
+> Verdict: INTEGRATE (external reference, not internalize)
+
+Multica's task lifecycle pattern (enqueue → claim → start → complete/fail) is a useful reference for DAG node state management:
+
+| Multica State | DAG Equivalent | Notes |
+|---------------|---------------|-------|
+| enqueue | pending | Node waiting for dependencies |
+| claim | ready | Dependencies resolved, ready to execute |
+| start | running | Agent spawned and executing |
+| complete | completed | Node finished successfully |
+| fail | failed | Node execution failed |
+
+Consider this pattern when extending DAG node state tracking or implementing retry logic.

package/templates/.claude/skills/pipeline-guards/SKILL.md

@@ -19,11 +19,13 @@ Defines mandatory safety constraints for all pipeline, workflow, and iterative e
 | Max iterations | 3 | 5 | worker-reviewer-pipeline |
 | Max DAG nodes | 20 | 30 | dag-orchestration |
 | Max parallel agents | 4 | 5 | R009 (all pipelines) |
+| Max parallel steps   | 4        | 4        | pipeline parallel blocks |
 | Timeout per node | 300s | 600s | dag-orchestration nodes |
 | Timeout per pipeline | 900s | 1800s | worker-reviewer-pipeline |
 | Max retry count | 2 | 3 | Failure retry strategies |
 | Max PR improvement items | 20 | 50 | pr-auto-improve |
 | Max auto-improve items | 20 | 50 | omcustom-auto-improve |
+| Max files per agent | 10 | 15 | All agent spawns (advisory) |
 
 ## Enforcement
 
@@ -82,6 +84,23 @@ When guards are triggered, they integrate with existing advisory systems:
 | Timeout approaching (80%) | → warn user, suggest early termination |
 | Hard cap hit | → force stop, report to user |
 
+## Task Granularity Guard
+
+Advisory guard for agent task scope. When a single agent is assigned too many files, it becomes a bottleneck in parallel execution.
+
+| Signal | Default | Action |
+|--------|---------|--------|
+| Files per agent > 10 | Advisory warning | Suggest splitting by layer/domain |
+| Files per agent > 15 | Hard warning | Require explicit user override |
+
+Display:
+```
+[Guard] ⚠ Agent assigned {n} files (> 10) — consider splitting by layer
+[Guard] 🛑 Agent assigned {n} files (> 15) — requires explicit override
+```
+
+This integrates with R009 Adaptive Parallel Splitting: if a stalled agent is detected AND it was assigned > 10 files, the splitting recommendation is stronger.
+
 ## Guard Configuration
 
 Pipelines can override defaults (within hard caps):
@@ -157,6 +176,26 @@ Guard warnings appear inline:
 | omcustom-auto-improve | Auto-improve item count limits |
 | stuck-recovery | Guard triggers feed into stuck detection |
 | model-escalation | Repeated failures trigger escalation advisory |
+| task-decomposition | Subtask file counts validated against granularity guard thresholds |
+
+## Checkpoint Gate Integration
+
+각 guard 통과/실패 시 `tracker-checkpoint` 에이전트로 gate state 기록.
+
+### Flow
+
+1. Guard 진입 → tracker-checkpoint에 gate state: running 기록
+2. Guard 통과 → tracker-checkpoint에 gate state: passed + metrics 기록
+3. Guard 실패 → tracker-checkpoint에 gate state: failed + failure reason freeze
+4. 다음 단계는 checkpoint state 참조하여 재개/중단 판단
+
+### Benefits
+
+- 긴 파이프라인에서 guard 지점마다 복원점 확보
+- 부분 실패 시 직전 guard 지점부터 재시도 가능 (비용 절감)
+- guard metrics 축적으로 품질 추이 관찰 가능
+
+See `.claude/agents/tracker-checkpoint.md` for the tracker spec.
 
 ## Override Policy
 

package/templates/.claude/skills/sdd-dev/SKILL.md

@@ -2,7 +2,7 @@
 name: sdd-dev
 description: Spec-Driven Development workflow — enforces sdd/ folder hierarchy with planning-first gates, current-state artifacts, and completion verification
 scope: core
-version: 1.0.0
+version: 1.1.0
 user-invocable: true
 argument-hint: "[task description or leave empty for guided workflow]"
 ---
@@ -27,7 +27,8 @@ sdd/
 ├── 03_build/        # Current build state, implementation notes
 ├── 04_verify/       # Verification evidence, test results, residual risks
 ├── 05_operate/      # Deployment notes, runbooks (conditional)
-└── 99_toolchain/    # Tool configs, scripts, environment setup
+├── 99_toolchain/    # Tool configs, scripts, environment setup
+└── decisions/       # Decision records for major design choices
 ```
 
 **Key Principle**: These folders are **current-state artifacts**, not history archives. Each file reflects the current state of the work — update in place rather than appending new versions.
@@ -44,7 +45,7 @@ ls sdd/ 2>/dev/null || echo "sdd/ folder not found"
 
 If `sdd/` does not exist:
 1. Inform the user that SDD workflow requires a `sdd/` folder
-2. Offer to create the folder structure: `mkdir -p sdd/{01_planning,02_plan,03_build,04_verify,05_operate,99_toolchain}`
+2. Offer to create the folder structure: `mkdir -p sdd/{01_planning,02_plan,03_build,04_verify,05_operate,99_toolchain,decisions}`
 3. Ask user to confirm before proceeding
 
 If `sdd/` exists, continue to Step 1.
@@ -121,6 +122,7 @@ Artifact to produce or update: `sdd/03_build/current.md`
 
 ## Decisions Made
 - {decision}: {rationale}
+- Write DR for major decisions: sdd/decisions/{YYYY-MM-DD}-{topic}.md (template: templates/decision-record.md)
 
 ## Known Issues
 - {issue}: {planned resolution}
@@ -235,6 +237,18 @@ Final display:
 3. **Checkboxes reflect reality**: Do NOT pre-check criteria. Update checkboxes as work is verified.
 4. **Residual risks are honest**: List known risks even after passing. Hiding risks defeats the purpose.
 
+## Decision Record Template
+
+Major design decisions during Step 3 are recorded in `sdd/decisions/{YYYY-MM-DD}-{topic}.md` using the template at `templates/decision-record.md` (relative to this skill directory).
+
+When to create a Decision Record:
+- Architectural choice between 2+ viable options
+- Trade-off accepted (e.g., complexity for performance)
+- Deferred decision (waiting for data/approval)
+- Superseding a previous decision
+
+See `guides/harness-engineering/` for harness-level decision context that DRs may reference.
+
 ## Integration with Other Skills
 
 | Skill | When to Use Together |

package/templates/.claude/skills/sdd-dev/templates/decision-record.md

@@ -0,0 +1,45 @@
+---
+title: {Decision title}
+date: YYYY-MM-DD
+status: proposed | accepted | superseded | deprecated
+context: guides/harness-engineering/README.md
+decision_makers: [{agent or role}]
+---
+
+# {Decision title}
+
+## Context
+
+{What is the problem and why is a decision needed? Include relevant constraints, goals, and the situation that makes this decision necessary.}
+
+## Options Considered
+
+1. **Option A**: {Description}
+   - Pros: {benefits}
+   - Cons: {drawbacks, trade-offs}
+
+2. **Option B**: {Description}
+   - Pros: {benefits}
+   - Cons: {drawbacks, trade-offs}
+
+3. **Option C** *(if applicable)*: {Description}
+   - Pros: {benefits}
+   - Cons: {drawbacks, trade-offs}
+
+## Decision
+
+**Chosen**: Option {A|B|C}
+
+{Explain the rationale for the choice. Why does this option best satisfy the constraints and goals from the Context section?}
+
+## Consequences
+
+- **Positive**: {What improves as a result of this decision}
+- **Negative**: {Trade-offs and costs accepted}
+- **Risks**: {Future considerations, potential issues to monitor}
+
+## References
+
+- guides/harness-engineering/README.md
+- {related skill or agent, e.g. .claude/skills/action-validator/SKILL.md}
+- {link to issue or PR if applicable}

package/templates/CLAUDE.md

@@ -103,7 +103,7 @@ oh-my-customcode로 구동됩니다.
 | 릴리즈 | `/pipeline auto-dev`, `/omcustom-release-notes`, `/release-plan` | 자동 개발, 릴리즈 노트 |
 | 리서치 | `/research`, `/scout`, `/deep-plan`, `/omcustom:agora` | 병렬 분석, URL 평가, 연구 계획 |
 | 메모리 | `/memory-save`, `/memory-recall` | 세션 메모리 관리 |
-| 최적화 | `/token-efficiency-audit` | 토큰 효율 감사 (3계층 방어 스택) |
+| 최적화 | `/token-efficiency-audit` | 토큰 효율 감사 (5계층 방어 스택) |
 | 시스템 | `/omcustom:lists`, `/omcustom:status`, `/omcustom:help` | 전체 목록, 상태, 도움말 |
 
 > 전체 커맨드 목록 (60+ 커맨드): `/omcustom:lists` 실행
@@ -114,12 +114,12 @@ oh-my-customcode로 구동됩니다.
 project/
 +-- CLAUDE.md                    # 진입점
 +-- .claude/
-|   +-- agents/                  # 서브에이전트 정의 (48 파일)
+|   +-- agents/                  # 서브에이전트 정의 (49 파일)
 |   +-- skills/                  # 스킬 (113 디렉토리)
 |   +-- rules/                   # 전역 규칙 (R000-R022)
 |   +-- hooks/                   # 훅 스크립트 (보안, 검증, HUD)
 |   +-- contexts/                # 컨텍스트 파일 (ecomode)
-+-- guides/                      # 레퍼런스 문서 (42 토픽)
++-- guides/                      # 레퍼런스 문서 (43 토픽)
 ```
 
 ## 오케스트레이션
@@ -173,8 +173,8 @@ oh-my-customcode는 소프트웨어 컴파일과 동일한 구조를 따릅니
 | Infra Engineer | 2 | infra-docker-expert, infra-aws-expert |
 | QA Team | 3 | qa-planner, qa-writer, qa-engineer |
 | Manager | 6 | mgr-creator, mgr-updater, mgr-supplier, mgr-gitnerd, mgr-sauron, mgr-claude-code-bible |
-| System | 3 | sys-memory-keeper, sys-naggy, wiki-curator |
-| **총계** | **48** | |
+| System | 4 | sys-memory-keeper, sys-naggy, tracker-checkpoint, wiki-curator |
+| **총계** | **49** | |
 
 ## Agent Teams (MUST when enabled)
 
@@ -236,6 +236,7 @@ Claude Code의 Agent Teams 기능이 활성화되어 있으면 (`CLAUDE_CODE_EXP
 | 플러그인 | 소스 | 용도 |
 |----------|------|------|
 | cc-token-saver | ww-w-ai/cc-token-saver | 토큰/비용 최적화 (Token Guardian, /continue, /usage-view) |
+| caveman | JuliusBrussee/caveman | 영어 출력 토큰 압축 (코드 리뷰·커밋 메시지). R013 ecomode 미적용 구간 보완. 한국어 컨텍스트(R000)에는 ecomode 우선. `lite`/`full` 권장, `ultra`/`文言文` 가독성 저하 주의 |
 
 ### 권장 MCP 서버
 

package/templates/guides/agent-design/ralph-loop-pattern.md

@@ -0,0 +1,32 @@
+# Ralph Loop Pattern — 세션 경계 지속 진화
+
+> 출처: Q00/ouroboros Ralph Loop 패턴 (INTEGRATE #966)
+> 도입일: v0.106.0
+
+## Context
+
+LLM 에이전트는 세션 종료 시 누적된 맥락(tacit knowledge, 실패 교훈, 선호 패턴)을 잃는다. Ralph Loop는 세션 간 경계를 넘는 지속 진화 메커니즘으로, 각 세션의 실패/성공 sticky patterns를 다음 세션의 초기 컨텍스트로 주입한다.
+
+## Claude Code 통합
+
+- **claude-mem MCP**: feedback memories + session archives를 영속 저장소로
+- **sys-memory-keeper 에이전트**: 세션 종료 시 Ralph Loop 요약 수행
+- **R011 Memory Integration**: native auto-memory를 Ralph Loop의 primary writer로
+
+## Pattern
+
+1. **Bootstrap**: 세션 시작 시 MEMORY.md에서 이전 Ralph Loop 요약 로드
+2. **Evolve**: 세션 진행 중 발견한 새 패턴/실패를 feedback memory에 기록
+3. **Compact**: 세션 종료 시 sys-memory-keeper가 Ralph Loop 요약을 MEMORY.md 업데이트
+4. **Persist**: claude-mem MCP에 long-term save (cross-session search)
+
+## Anti-patterns
+
+- 세션마다 처음부터 다시 시작하는 sessionless 모드 (R011 native memory 사용)
+- 모든 세션 로그를 저장하는 brute-force persistence (selective feedback만)
+
+## References
+
+- R011 SHOULD-memory-integration.md
+- sys-memory-keeper 에이전트
+- Q00/ouroboros `ooo interview/run/ralph` CLI

package/templates/guides/claude-code/14-token-efficiency.md

@@ -1,4 +1,4 @@
-# Token Efficiency — Three-Layer Defense Stack
+# Token Efficiency — Five-Layer Defense Stack
 
 > **Source**: [Claude Code & Codex token efficiency by settings adjustment](https://www.stdy.blog/increasing-token-efficiency-by-setting-adjustment-in-claude-and-codex/)
 > **Reference baseline**: Claude Code v2.1.114+ / Codex v0.121.0+
@@ -7,7 +7,7 @@
 
 Token spend in Claude Code is not purely a function of task complexity. A significant portion of token consumption occurs through structural overhead: auto-injected git instructions, IDE file listings, tool output that exceeds what the model actually needs, and session state reloaded unnecessarily across turns.
 
-The three-layer defense stack addresses this overhead at three distinct points in the session lifecycle:
+The five-layer defense stack addresses this overhead at distinct points in the session lifecycle:
 
 ```
 ┌─────────────────────────────────────────────────────────────────┐
@@ -22,6 +22,10 @@ The three-layer defense stack addresses this overhead at three distinct points i
 ├─────────────────────────────────────────────────────────────────┤
 │  Layer 4: playwright-compress (MCP OUTPUT INTELLIGENCE)         │
 │  PostToolUse hook — Haiku summarization of browser MCP output   │
+├─────────────────────────────────────────────────────────────────┤
+│  Layer 5: caveman (OUTPUT STYLE COMPRESSION)                    │
+│  SessionStart hook — primitive-speech output reduces token spend│
+│  English scenarios only — R000 Korean-first contexts use Layer 2│
 └─────────────────────────────────────────────────────────────────┘
 ```
 
@@ -153,6 +157,7 @@ Disabling `includeGitInstructions` removes git workflow guidance from the contex
 | R001 Safety | `apply-ci` mode is Risk Level High — requires user confirmation before applying. |
 | R012 HUD Statusline | Statusline shows CTX% — effective measure of Layer 2+3 combined impact. |
 | playwright-compress | Layer 4 hook — complements Layer 3 MAX_MCP_OUTPUT_TOKENS with intelligent lossless compression. |
+| caveman | Layer 5 style compression — orthogonal to Layer 2 (volume) and Layer 4 (MCP). R000 Korean-first: use Layer 2 as primary. |
 
 ---
 
@@ -175,6 +180,43 @@ Hook trigger: `mcp__playwright__.*` and `mcp__claude-in-chrome__.*`
 
 ---
 
+## Layer 5: caveman (Output Style Compression)
+
+External plugin (JuliusBrussee/caveman, 41.6k stars, MIT) that rewrites Claude responses into compressed "primitive speech" via a SessionStart hook.
+
+**Measured savings:**
+- ~75% output token reduction
+- ~46% input token reduction (context accumulation effect)
+
+**Intensity levels:**
+
+| Level | Description | Recommendation |
+|-------|-------------|----------------|
+| `lite` | Light compression, high readability | Recommended |
+| `full` | Moderate compression | Recommended |
+| `ultra` | Heavy compression, reduced readability | Caution |
+| `文言文` | Classical Chinese style | Avoid for shared sessions |
+
+**Installation:** `/plugin install caveman` (requires marketplace access)
+
+**When to use:**
+
+| Scenario | Layer to apply |
+|----------|---------------|
+| English-only output sessions (code review, commit messages) | Layer 5 (caveman) |
+| Korean-first sessions (R000 contexts) | Layer 2 (R013 ecomode) — caveman articles/prepositions not present in Korean |
+| Mixed sessions | Layer 2 primary, Layer 5 optional |
+
+**Coexistence with other layers:**
+
+- Layer 5 compresses output style; Layer 2 (ecomode) compresses output volume. These are orthogonal — both can be active simultaneously.
+- Layer 5 applies globally to all responses; Layer 2 activates conditionally (4+ tasks threshold).
+- For Korean-first projects following R000, Layer 2 provides the primary compression benefit. Layer 5's article-removal compression is largely ineffective against Korean (article-free language).
+
+**R000 compatibility note:** caveman's compression relies on English grammatical structure (removing articles, prepositions). Korean lacks these structures, so compression rates are significantly lower in Korean-dominant sessions. Use `lite` or `full` mode only; avoid `ultra`/`文言文` in shared or multilingual sessions.
+
+---
+
 ## Cross-References
 
 - `guides/claude-code/13-cli-flags.md` — CLI flags for non-interactive/CI invocation
@@ -185,3 +227,4 @@ Hook trigger: `mcp__playwright__.*` and `mcp__claude-in-chrome__.*`
 - `.claude/skills/update-config/` — Generic settings.json manipulation (broader scope)
 - `.claude/skills/playwright-compress/SKILL.md` — Layer 4 MCP output compression hook
 - `.claude/hooks/scripts/playwright-compress.sh` — Layer 4 hook script
+- `https://github.com/JuliusBrussee/caveman` — Layer 5 caveman plugin (external)

package/templates/guides/harness-engineering/README.md

@@ -46,9 +46,9 @@ Deep Insight가 제안하는 4계층 구조는 oh-my-customcode에 이미 구현
 메인 대화 → Agent(mgr-creator, mode: "bypassPermissions") → Write(".claude/agents/new.md", content)
 ```
 
-### Tracker 체크포인트 패턴 (v0.106.0+ 이관)
+### Tracker 체크포인트 패턴
 
-현재 파이프라인 상태 추적은 `/tmp/.claude-pipeline-{PID}.json` 파일과 `.claude/outputs/sessions/{YYYY-MM-DD}/` 아티팩트 규약으로 구현되어 있습니다. 전용 Tracker 에이전트(dag-orchestration / pipeline-guards 통합형)는 `context: fork` cap 확장 이후 후속 릴리즈로 이관합니다.
+현재 파이프라인 상태 추적은 `/tmp/.claude-pipeline-{PID}.json` 파일과 `.claude/outputs/sessions/{YYYY-MM-DD}/` 아티팩트 규약으로 구현되어 있습니다. ✅ 구현 완료 (v0.106.1 via #983 — `.claude/agents/tracker-checkpoint.md`): 전용 Tracker 에이전트(dag-orchestration / pipeline-guards 통합형)가 배포되어 checkpoint persistence, resume-after-failure, gate state 기록을 담당합니다.
 
 ---
 
@@ -185,7 +185,7 @@ opt-in: hard-enforce (filter 모드, --hard-enforce 플래그) — 명시적 사
 
 | 항목 | 이관 이유 | 예상 릴리즈 |
 |------|----------|-----------|
-| **Tracker 체크포인트 에이전트** — dag-orchestration / pipeline-guards 통합형 전용 Tracker | `context: fork` cap(현재 12/12) 확장 필요 | v0.106.0+ |
+| **Tracker 체크포인트 에이전트** — dag-orchestration / pipeline-guards 통합형 전용 Tracker | ✅ 구현 완료 (v0.106.1 via #983 — `.claude/agents/tracker-checkpoint.md`) | — |
 | **hierarchical-agent-topology 스킬** — 4계층 구조를 자동 검증하는 전용 스킬 | fork 스킬 cap 해소 후 추가 | v0.106.0+ |
 | **sdd-dev Harness Decision Record 템플릿** — 하네스 설계 결정을 ADR 형식으로 기록 | sdd-dev 스킬 업데이트와 병행 | v0.107.0+ |
 | **harness-synthesizer 2단계 격리 구현 예시** — Base64 인코딩 + subprocess 격리의 실제 YAML 예시 | 보안 리뷰 후 추가 | v0.107.0+ |

package/templates/manifest.json

@@ -1,6 +1,6 @@
 {
-  "version": "0.105.1",
-  "lastUpdated": "2026-04-18T00:00:00.000Z",
+  "version": "0.106.1",
+  "lastUpdated": "2026-04-24T07:30:00.000Z",
   "components": [
     {
       "name": "rules",
@@ -12,7 +12,7 @@
       "name": "agents",
       "path": ".claude/agents",
       "description": "AI agent definitions (flat .md files with prefixes)",
-      "files": 48
+      "files": 49
     },
     {
       "name": "skills",
@@ -24,7 +24,7 @@
       "name": "guides",
       "path": "guides",
       "description": "Reference documentation",
-      "files": 42
+      "files": 43
     },
     {
       "name": "hooks",