oh-my-customcodex 0.1.5 → 0.1.7

package/README.md

@@ -13,7 +13,7 @@
 
 **[한국어 문서 (Korean)](./README_ko.md)**
 
-48 agents. 107 skills. 22 rules. One command.
+48 agents. 108 skills. 22 rules. One command.
 
 ```bash
 npm install -g oh-my-customcodex && cd your-project && omcodex init
@@ -132,7 +132,7 @@ Each agent declares its tools, model, memory scope, and limitations in YAML fron
 
 ---
 
-### Skills (107)
+### Skills (108)
 
 | Category | Count | Includes |
 |----------|-------|----------|
@@ -140,7 +140,7 @@ Each agent declares its tools, model, memory scope, and limitations in YAML fron
 | Routing | 4 | secretary, dev-lead, de-lead, qa-lead |
 | Workflow | 13 | structured-dev-cycle, deep-plan, research, evaluator-optimizer, dag-orchestration, worker-reviewer-pipeline, reasoning-sandwich, pipeline, and more |
 | Development | 9 | dev-review, dev-refactor, analysis, create-agent, intent-detection, web-design-guidelines, omcodex:takeover, skill-extractor, idea |
-| Operations | 9 | update-docs, audit-agents, sauron-watch, monitoring-setup, fix-refs, release-notes, and more |
+| Operations | 10 | update-docs, audit-agents, sauron-watch, monitoring-setup, token-efficiency-audit, fix-refs, release-notes, and more |
 | Memory | 3 | memory-save, memory-recall, memory-management |
 | Package | 3 | npm-publish, npm-version, npm-audit |
 | Optimization | 3 | optimize-analyze, optimize-bundle, optimize-report |
@@ -205,6 +205,7 @@ All commands are invoked inside the oh-my-customcodex GPT Codex + OMX session.
 | `/memory-save` | Save session context |
 | `/memory-recall` | Search and recall memories |
 | `/omcodex:monitoring-setup` | OTel monitoring toggle |
+| `/token-efficiency-audit` | Audit and tune token-efficiency settings |
 | `/omcodex:loop` | Auto-continue background agent workflows (3-continue safety limit) |
 | `/omcodex:lists` | Show all commands |
 | `/omcodex:status` | System health check |
@@ -273,7 +274,7 @@ your-project/
 ├── AGENTS.md                   # Entry point
 ├── .codex/
 │   ├── agents/                 # 48 agent definitions
-│   ├── skills/                 # 107 skill modules
+│   ├── skills/                 # 108 skill modules
 │   ├── rules/                  # 22 governance rules (R000-R021)
 │   ├── hooks/                  # 15 lifecycle hook scripts
 │   ├── schemas/                # Tool input validation schemas

package/dist/cli/index.js

@@ -3087,7 +3087,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "0.1.5",
+    version: "0.1.7",
     description: "Batteries-included agent harness on top of GPT Codex + OMX",
     type: "module",
     bin: {

package/dist/index.js

@@ -2173,7 +2173,7 @@ var package_default = {
   workspaces: [
     "packages/*"
   ],
-  version: "0.1.5",
+  version: "0.1.7",
   description: "Batteries-included agent harness on top of GPT Codex + OMX",
   type: "module",
   bin: {

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "0.1.5",
+  "version": "0.1.7",
   "description": "Batteries-included agent harness on top of GPT Codex + OMX",
   "type": "module",
   "bin": {

package/templates/.claude/skills/token-efficiency-audit/SKILL.md

@@ -0,0 +1,147 @@
+---
+name: token-efficiency-audit
+description: Audit and tune Claude/Codex settings for lower token usage without changing code
+scope: package
+argument-hint: "[audit|apply-interactive|apply-ci|status]"
+user-invocable: true
+---
+
+# Token Efficiency Audit
+
+Audit and tune Claude Code / Codex configuration for better token efficiency.
+
+This skill is for configuration-level optimization, not runtime behavior shaping. It complements:
+
+- `guides/cc-token-saver/README.md` for plugin-level token protection
+- R013 ecomode for runtime compression
+- `omcodex:monitoring-setup` for telemetry and usage visibility
+
+## Modes
+
+### `audit` (default)
+
+Inspect the current token-efficiency posture without changing files.
+
+Check these sources when they exist:
+
+- `.codex/settings.local.json`
+- `.codex/settings.json`
+- `~/.codex/config.toml`
+- shell startup files such as `~/.zshrc`, `~/.bashrc`, `~/.bash_profile`
+
+Audit for:
+
+- Claude-side knobs
+  - `includeGitInstructions`
+  - `autoConnectIde`
+  - output caps such as `BASH_MAX_OUTPUT_LENGTH`
+  - file-read / MCP output token caps
+- Codex-side knobs
+  - `features.apps`
+  - `web_search`
+  - `tool_output_token_limit`
+- worker-only flags that should not be silently enabled in normal interactive sessions
+
+Report:
+
+1. current settings found
+2. low-risk improvements
+3. high-risk / CI-only improvements
+4. expected tradeoffs
+
+### `status`
+
+Summarize the current posture in a compact status report:
+
+- configuration files found
+- safe interactive settings present / missing
+- CI-only settings present / missing
+- main token-risk hotspots
+
+### `apply-interactive`
+
+Apply only low-risk settings suitable for human interactive sessions.
+
+Preferred targets:
+
+- `.codex/settings.local.json` for session-local settings
+- user shell rc files only when environment variables are the right fit
+
+Safe defaults to consider:
+
+- disable unnecessary git instruction injection when not needed
+- disable unnecessary IDE auto-connect when not needed
+- set sane output ceilings to reduce runaway tool output without over-truncating
+- reduce Codex tool output limits to a practical level
+- disable unneeded app surfaces when they are not part of the user workflow
+
+Guardrails:
+
+- preserve existing user config
+- never overwrite unrelated settings
+- do not apply CI-only flags here
+- explain tradeoffs before writing
+
+### `apply-ci`
+
+Apply stronger settings for non-interactive worker / CI contexts.
+
+This mode is intentionally stricter and must call out risk clearly.
+
+Examples of CI-only candidates:
+
+- disable auto-memory features
+- disable built-in agent surfaces not needed for batch execution
+- disable nonessential MCP / app surfaces
+- tighten output limits more aggressively than interactive mode
+
+Required warning:
+
+- these settings can reduce convenience or disable important harness behaviors
+- they should be scoped to CI/worker environments, not broad local defaults
+
+## Output Contract
+
+### Audit / Status
+
+```text
+[Token Efficiency]
+
+Mode: audit|status
+Posture: good|mixed|wasteful
+
+Safe interactive wins:
+- ...
+
+CI-only wins:
+- ...
+
+Watchouts:
+- ...
+```
+
+### Apply Modes
+
+```text
+[Token Efficiency]
+
+Mode: apply-interactive|apply-ci
+Files updated:
+- ...
+
+Settings applied:
+- ...
+
+Tradeoffs:
+- ...
+
+Rollback:
+- restore prior values from git diff / file backup
+```
+
+## Heuristics
+
+- Prefer smaller, reversible config edits over broad environment mutation
+- Keep interactive and CI profiles separate
+- Do not set output limits so low that users trigger repeated re-runs and spend more tokens overall
+- When uncertain, recommend `audit` first and `apply-*` second

package/templates/CLAUDE.md

@@ -104,7 +104,7 @@ oh-my-customcodex로 구동됩니다.
 | 릴리즈 | `/pipeline auto-dev`, `/omcodex-release-notes`, `/release-plan` | 자동 개발, 릴리즈 노트 |
 | 리서치 | `/research`, `/scout`, `/deep-plan`, `/omcodex:agora` | 병렬 분석, URL 평가, 연구 계획 |
 | 메모리 | `/memory-save`, `/memory-recall` | 세션 메모리 관리 |
-| 시스템 | `/omcodex:lists`, `/omcodex:status`, `/omcodex:help` | 전체 목록, 상태, 도움말 |
+| 시스템 | `/token-efficiency-audit`, `/omcodex:lists`, `/omcodex:status`, `/omcodex:help` | 토큰 효율 감사, 전체 목록, 상태, 도움말 |
 
 > 전체 커맨드 목록 (60+ 커맨드): `/omcodex:lists` 실행
 
@@ -115,7 +115,7 @@ project/
 +-- AGENTS.md                    # 진입점
 +-- .codex/
 |   +-- agents/                  # 서브에이전트 정의 (48 파일)
-|   +-- skills/                  # 스킬 (106 디렉토리)
+|   +-- skills/                  # 스킬 (108 디렉토리)
 |   +-- rules/                   # 전역 규칙 (R000-R022)
 |   +-- hooks/                   # 훅 스크립트 (보안, 검증, HUD)
 |   +-- contexts/                # 컨텍스트 파일 (ecomode)

package/templates/CLAUDE.md.en

@@ -107,6 +107,7 @@ NO EXCEPTIONS. NO EXCUSES.
 | `/memory-save` | Save session context to omx-memory |
 | `/memory-recall` | Search and recall memories |
 | `/omcodex:monitoring-setup` | Enable/disable OTel console monitoring |
+| `/token-efficiency-audit` | Audit and tune token-efficiency settings |
 | `/omcodex:npm-publish` | Publish package to npm registry |
 | `/omcodex:npm-version` | Manage semantic versions |
 | `/omcodex:npm-audit` | Audit dependencies |
@@ -130,7 +131,7 @@ project/
 +-- AGENTS.md                    # Entry point
 +-- .codex/
 |   +-- agents/                  # Subagent definitions (48 files)
-|   +-- skills/                  # Skills (106 directories)
+|   +-- skills/                  # Skills (108 directories)
 |   +-- rules/                   # Global rules (22 files)
 |   +-- hooks/                   # Hook scripts (security, validation, HUD)
 |   +-- contexts/                # Context files (4 files)
@@ -174,7 +175,6 @@ This is the core oh-my-customcodex philosophy: **"No expert? CREATE one, connect
 | 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 |
-| Auxiliary | 1 | slack-cli-expert |
 | **Total** | **48** | |
 
 ## Agent Teams (MUST when enabled)

package/templates/CLAUDE.md.ko

@@ -107,6 +107,7 @@ oh-my-customcodex로 구동됩니다.
 | `/memory-save` | 세션 컨텍스트를 omx-memory에 저장 |
 | `/memory-recall` | 메모리 검색 및 리콜 |
 | `/omcodex:monitoring-setup` | OTel 콘솔 모니터링 활성화/비활성화 |
+| `/token-efficiency-audit` | 토큰 효율 설정 감사 및 조정 |
 | `/omcodex:npm-publish` | npm 레지스트리에 패키지 배포 |
 | `/omcodex:npm-version` | 시맨틱 버전 관리 |
 | `/omcodex:npm-audit` | 의존성 감사 |
@@ -130,7 +131,7 @@ project/
 +-- AGENTS.md                    # 진입점
 +-- .codex/
 |   +-- agents/                  # 서브에이전트 정의 (48 파일)
-|   +-- skills/                  # 스킬 (106 디렉토리)
+|   +-- skills/                  # 스킬 (108 디렉토리)
 |   +-- rules/                   # 전역 규칙 (22 파일)
 |   +-- hooks/                   # 훅 스크립트 (보안, 검증, HUD)
 |   +-- contexts/                # 컨텍스트 파일 (4 파일)
@@ -174,7 +175,6 @@ project/
 | 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 |
-| 보조 | 1 | slack-cli-expert |
 | **총계** | **48** | |
 
 ## Agent Teams (MUST when enabled)

package/templates/guides/cc-token-saver/README.md

@@ -61,6 +61,15 @@ These two components solve different problems and can run simultaneously:
 
 **No conflict** — Token Guardian fires on idle time, R013 fires on context percentage. Both warnings are useful.
 
+## Layer 3 Cross-Reference
+
+`cc-token-saver` is Layer 1 of the token-efficiency stack. For settings-level optimization before the session starts, use `/token-efficiency-audit`.
+
+See also:
+
+- `guides/claude-code/14-token-efficiency.md`
+- `/token-efficiency-audit audit`
+
 ## Usage Scenarios
 
 ### `/continue` — Zero-cost context restore

package/templates/guides/claude-code/13-cli-flags.md

@@ -149,3 +149,4 @@ claude auto-mode critique    # Review auto mode decisions
 - [Monitoring Guide](10-monitoring.md) — OTel metrics and events
 - [Sub-agents Guide](11-sub-agents.md) — Agent spawning and coordination
 - [Workflow Patterns](12-workflow-patterns.md) — Workflow automation
+- [Token Efficiency Layers](14-token-efficiency.md) — plugin/runtime/settings optimization stack

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

@@ -0,0 +1,73 @@
+# Token Efficiency Layers
+
+Token efficiency in oh-my-customcodex has three layers. They solve different problems and should not be mixed together blindly.
+
+## Layer 1: Plugin-Level Protection
+
+Use `cc-token-saver` when you want cache- and resume-oriented protection:
+
+- Token Guardian for prompt-cache expiry awareness
+- `/continue` for low-cost session resumption
+- usage dashboards and rate-limit reporting
+
+This layer is documented in `guides/cc-token-saver/README.md`.
+
+## Layer 2: Runtime Compression
+
+Use R013 ecomode and existing runtime guards when you want to compress active-session behavior:
+
+- shorter outputs
+- tighter budget awareness
+- safer handling of long-running, batch, or parallel tasks
+
+This layer changes how the session behaves while work is running.
+
+## Layer 3: Settings-Level Optimization
+
+Use `/token-efficiency-audit` when you want configuration-level changes before the session burns tokens.
+
+Typical settings-level levers:
+
+### Claude-side
+
+- `includeGitInstructions`
+- `autoConnectIde`
+- output ceilings such as `BASH_MAX_OUTPUT_LENGTH`
+- file-read / MCP output token caps
+
+### Codex-side
+
+- `features.apps`
+- `web_search`
+- `tool_output_token_limit`
+
+### CI / Worker-only
+
+- disable convenience features that are useful for humans but wasteful in headless runs
+- apply stronger output ceilings than interactive defaults
+
+## Recommended Usage
+
+| Goal | Best layer |
+|------|------------|
+| Protect cache value across pauses | Layer 1 |
+| Compress runtime behavior in large sessions | Layer 2 |
+| Reduce baseline token spend from configuration | Layer 3 |
+
+Use layers together, but keep responsibilities separate:
+
+- plugin layer for cache and resume
+- runtime layer for in-session behavior
+- settings layer for pre-session defaults
+
+## Tradeoffs
+
+| Lever | Benefit | Risk |
+|-------|---------|------|
+| lower output limits | prevents runaway logs | too low causes repeated reruns and extra token spend |
+| disable auto-connect / extra surfaces | less idle context and less noise | may remove convenience features users expect |
+| aggressive CI-only flags | efficient headless execution | can weaken local interactive ergonomics if applied too broadly |
+
+## Rule of Thumb
+
+Start with `audit`, then apply only the smallest reversible setting changes that address your dominant cost source.

package/templates/guides/claude-code/index.yaml

@@ -59,3 +59,8 @@ documents:
     title: CLI 플래그 및 모드
     description: CLI 플래그, 헤드리스 모드, 스케줄링, 환경변수 레퍼런스
     path: ./13-cli-flags.md
+
+  - name: token-efficiency
+    title: 토큰 효율 레이어
+    description: 플러그인, 런타임, 설정 레이어를 분리한 토큰 효율 최적화 가이드
+    path: ./14-token-efficiency.md

package/templates/manifest.json

@@ -1,6 +1,6 @@
 {
-  "version": "0.1.5",
-  "lastUpdated": "2026-04-19T07:00:00.000Z",
+  "version": "0.1.7",
+  "lastUpdated": "2026-04-19T08:21:30.000Z",
   "components": [
     {
       "name": "rules",
@@ -18,7 +18,7 @@
       "name": "skills",
       "path": ".codex/skills",
       "description": "Reusable skill modules (includes slash commands)",
-      "files": 107
+      "files": 108
     },
     {
       "name": "guides",