oh-my-customcode 1.1.106 → 1.1.107

package/templates/README.md

@@ -48,11 +48,11 @@ templates/
 ├── manifest.json                    # 배포 컴포넌트 카운트 및 메타데이터
 ├── .claude/
 │   ├── agents/                      # 에이전트 정의 파일 (*.md, 50개)
-│   ├── skills/                      # 스킬 모듈 (각 디렉토리에 SKILL.md, 115개)
+│   ├── skills/                      # 스킬 모듈 (각 디렉토리에 SKILL.md, 114개)
 │   ├── rules/                       # 전역 규칙 (R000–R023, 23개)
 │   ├── hooks/
 │   │   ├── hooks.json               # 훅 이벤트 설정 (PreToolUse/PostToolUse 등)
-│   │   └── scripts/                 # 훅 셸 스크립트 (34개)
+│   │   └── scripts/                 # 훅 셸 스크립트 (41개)
 │   ├── contexts/                    # 컨텍스트 설정 파일 (ecomode 등)
 │   └── ontology/                    # Ontology-RAG 지식 그래프
 └── guides/                          # 레퍼런스 문서 디렉토리 (56개)
@@ -87,7 +87,7 @@ CI의 `verify-template-sync.sh`가 소스와 templates/ 간 일치를 검증합
 | System | 4 |
 | Agora | 1 |
 
-### Skills (115)
+### Skills (114)
 
 `.claude/skills/*/SKILL.md` — 재사용 가능한 스킬 모듈.
 
@@ -116,7 +116,7 @@ CI의 `verify-template-sync.sh`가 소스와 templates/ 간 일치를 검증합
 
 각 디렉토리는 단일 토픽에 대한 best practices, 튜토리얼, 또는 설계 가이드를 담습니다. 에이전트가 작업 중 참조합니다 (R006 관심사 분리).
 
-### Hooks (42)
+### Hooks (41)
 
 `.claude/hooks/scripts/*.sh` — 라이프사이클 훅 스크립트.
 

package/templates/guides/external-tools/ecc-absorption-decisions.md

@@ -183,6 +183,8 @@ v1.1.29(#1484)에서 제거되었습니다.
 
 DEFER 기간 동안의 cross-tool integration 우회 경로:
 
+아래 대안과 use case 범위는 당시 결정 이력으로 보존합니다. RTK 프로젝트 통합은 v1.1.107에서 퇴역하므로 RTK proxy skill을 현재 실행 경로로 사용하지 마십시오. 이 기록의 효과 범위를 현재 버전에서 새로 실측했다는 뜻은 아닙니다.
+
 - **RTK proxy skill**: 기존 infra 활용, Cursor 등에서 oh-my-customcode skill 호출
 - **Codex/Gemini exec skill**: 외부 LLM executor를 skill로 래핑, harness 종속성 없음
 

package/templates/guides/multi-provider-exec/README.md

@@ -8,18 +8,13 @@ Inspired by OpenHarness's provider profile switching pattern, adapted for oh-my-
 
 ## Provider Matrix
 
-| Provider | Skill | CLI Dependency | Model | Strengths |
-|----------|-------|---------------|-------|-----------|
-| RTK (proxy) | `rtk-exec` | `rtk` CLI | Configurable | Token-optimized output, cost reduction |
+v1.1.107에서는 사용자 결정에 따라 프로젝트 RTK 통합과 공개 `rtk-exec` 스킬을 퇴역합니다. 이 가이드의 RTK 실행 예시·추천을 사용하지 마십시오. 머신에 별도로 설치한 RTK 바이너리는 이 변경으로 제거하지 않습니다.
 
 ## Availability Detection
 
 The `session-env-check.sh` hook (SessionStart) auto-detects available providers:
 
-```
-[SessionStart] Checking external CLI availability...
-  rtk: ✓ available
-```
+RTK availability 점검과 상태 출력은 퇴역합니다. Codex·Gemini 등 나머지 CLI availability 점검은 기존 session hook 계약을 유지합니다.
 
 Providers are opt-in — missing CLIs are silently skipped.
 
@@ -27,15 +22,11 @@ Providers are opt-in — missing CLIs are silently skipped.
 
 ### Direct Invocation
 
-```
-/rtk-exec "List files matching pattern X"
-```
+공개 `/rtk-exec` 명령은 제거됩니다. 이 문서에서 다른 provider의 실행 스킬이나 자동 대체 명령을 새로 지정하지 않습니다.
 
 ### Provider Selection Guide
 
-| Task | Recommended Provider | Rationale |
-|------|---------------------|-----------|
-| Token-heavy batch operations | rtk-exec | Compressed output reduces context cost |
+기존 RTK 추천 항목은 제거됩니다. provider를 선택할 때는 사용 가능한 스킬의 실제 계약과 CLI 설정을 확인하십시오.
 
 ### Integration with Existing Skills
 
@@ -49,18 +40,16 @@ Providers are opt-in — missing CLIs are silently skipped.
 | Aspect | Multi-Model Routing | Multi-Provider Exec |
 |--------|--------------------|--------------------|
 | Scope | Claude model selection | Cross-provider execution |
-| Models | haiku / sonnet / opus | RTK proxy |
+| Models | haiku / sonnet / opus | 명시적으로 선택한 외부 provider의 모델 |
 | Mechanism | `model` frontmatter field | Exec skill invocation |
-| Use case | Cost/quality optimization within Claude | Token-optimized output via RTK proxy |
+| Use case | Cost/quality optimization within Claude | 명시적으로 선택한 외부 provider 실행 |
 | Guide | `guides/multi-model-routing/` | `guides/multi-provider-exec/` |
 
 ## Configuration
 
 No global configuration required. Each exec skill reads its own CLI configuration:
 
-| Skill | Config Source |
-|-------|-------------|
-| rtk-exec | RTK proxy running on localhost |
+RTK 전용 설정 연결은 제거됩니다. 이 변경은 다른 CLI의 사용자 설정을 삭제하지 않습니다.
 
 ## Limitations
 

package/templates/manifest.json

@@ -1,6 +1,6 @@
 {
-  "version": "1.1.106",
-  "lastUpdated": "2026-09-03",
+  "version": "1.1.107",
+  "lastUpdated": "2026-10-06",
   "omcustomMinClaudeCode": "2.1.121",
   "omcustomMinClaudeCodeReason": "Sensitive-path direct Write/Edit on .claude/** under bypassPermissions (R010 deprecation, #1101)",
   "components": [
@@ -20,7 +20,7 @@
       "name": "skills",
       "path": ".claude/skills",
       "description": "Reusable skill modules (includes slash commands)",
-      "files": 115
+      "files": 114
     },
     {
       "name": "guides",

package/templates/workflows/auto-dev.yaml

@@ -1446,9 +1446,11 @@ steps:
               re-running step d then step e, re-staging, and re-running this assertion.
 
          Version decision (semver) — PATCH-PREFERRED policy (post-1.0.0):
+         - The user's explicit version or bump-level judgment takes precedence. Approval to remove a feature or change hooks is not approval for a major or minor version.
          - No existing tags → v0.1.0
          - Previous tag exists → DEFAULT to patch. When in doubt, patch — do NOT reflexively bump minor for rule/doc/skill edits.
            - patch (DEFAULT): rule/doc/skill/config/wiki/workflow changes, bugfixes, hardening, CC-compat notes — the vast majority of this project's changes
+           - Public skill/agent/integration additions and removals follow this repository's PATCH-PREFERRED lifecycle policy, including RTK integration and /rtk-exec retirement. Names, files, or counts appearing or disappearing alone do not justify a major or minor bump.
            - minor: ONLY a new user-facing capability that changes HOW the harness is used — a new
              workflow axis, a new command surface users must learn, or a contract other components
              depend on. NOT "a file was added under .claude/skills/ or .claude/agents/".
@@ -1460,7 +1462,7 @@ steps:
              baseline rate of change, NOT a minor signal. If a version bump would follow
              mechanically from "a new file exists", it is patch. Ask instead: does a user's
              workflow change because of this?
-           - major: breaking changes to user-facing contracts (CLI flags, public skill/command names, public API), or a deliberate milestone declaration (e.g., v1.0.0)
+           - major: actual compatibility breaks in existing CLI flags or public APIs, or an explicit major milestone declaration (e.g., v1.0.0). Skill/agent/integration lifecycle changes alone are excluded; the user's explicit version or bump-level judgment takes precedence.
          - Previous tag is ahead of source version (e.g., tag v0.136.1, package.json 0.136.0): use next available skip-version (0.136.2)
 
       2. Release notes via omcustom-release-notes skill

package/templates/.claude/hooks/scripts/rtk-intercept.sh

@@ -1,77 +0,0 @@
-#!/bin/bash
-# RTK Auto-Intercept Hook
-# Trigger: PreToolUse (Bash matcher)
-# Purpose: Transparently rewrite CLI commands through RTK proxy
-# Protocol: stdin JSON → stdout modified JSON, exit 0 always
-
-set -euo pipefail
-
-input=$(cat)
-
-# Only intercept Bash tool calls
-tool_name=$(printf '%s\n' "$input" | jq -r '.tool // empty' 2>/dev/null || echo "")
-if [ "$tool_name" != "Bash" ]; then
-  printf '%s\n' "$input"
-  exit 0
-fi
-
-# Check RTK availability
-RTK_AVAILABLE=false
-STATUS_FILE="/tmp/.claude-env-status-${PPID}"
-if [ -f "$STATUS_FILE" ] && grep -q "rtk=available" "$STATUS_FILE" 2>/dev/null; then
-  RTK_AVAILABLE=true
-elif command -v rtk >/dev/null 2>&1; then
-  RTK_AVAILABLE=true
-fi
-
-if [ "$RTK_AVAILABLE" != "true" ]; then
-  printf '%s\n' "$input"
-  exit 0
-fi
-
-# Extract command
-cmd=$(printf '%s\n' "$input" | jq -r '.tool_input.command // empty' 2>/dev/null || echo "")
-if [ -z "$cmd" ]; then
-  printf '%s\n' "$input"
-  exit 0
-fi
-
-# Skip if already using rtk
-if echo "$cmd" | grep -qE '^rtk\b'; then
-  printf '%s\n' "$input"
-  exit 0
-fi
-
-# Skip complex commands (pipes, redirections, background, subshells, semicolons with multiple commands)
-if echo "$cmd" | grep -qE '[|><&]|;\s*\w'; then
-  printf '%s\n' "$input"
-  exit 0
-fi
-
-# RTK-supported command prefixes
-RTK_CMDS="ls find tree du cat head tail wc grep rg git cargo npm pnpm bun pip pytest vitest jest rspec eslint tsc ruff docker kubectl"
-
-# Extract first word of command (skip env var assignments like FOO=bar)
-first_word=$(echo "$cmd" | sed 's/^[A-Z_]*=[^ ]* //' | awk '{print $1}')
-
-# Check if command is RTK-supported
-SUPPORTED=false
-for rtk_cmd in $RTK_CMDS; do
-  if [ "$first_word" = "$rtk_cmd" ]; then
-    SUPPORTED=true
-    break
-  fi
-done
-
-if [ "$SUPPORTED" != "true" ]; then
-  printf '%s\n' "$input"
-  exit 0
-fi
-
-# Rewrite command with rtk prefix
-new_cmd="rtk $cmd"
-echo "[RTK] Intercepted: $cmd → $new_cmd" >&2
-
-# Output modified JSON
-printf '%s\n' "$input" | jq --arg new_cmd "$new_cmd" '.tool_input.command = $new_cmd'
-exit 0

package/templates/.claude/skills/rtk-exec/SKILL.md

@@ -1,199 +0,0 @@
----
-name: rtk-exec
-description: Execute CLI commands through RTK proxy for token-optimized output
-scope: core
-argument-hint: "<command> [args...] [--gain] [--version] [--init]"
-user-invocable: true
----
-
-# RTK Exec Skill
-
-Execute CLI commands through the RTK (Rust Token Killer) proxy to reduce LLM token consumption by 60-90%. RTK is a CLI command proxy — it wraps existing shell commands and compresses their output using smart filtering, grouping, truncation, and deduplication.
-
-> **Important**: RTK is NOT an AI prompt tool. It is a CLI output compressor. You pass it a regular shell command and it returns compressed output.
-
-## Options
-
-```
-<command> [args...]   Required. CLI command to proxy through RTK (e.g., "ls .", "git status", "cargo test")
---gain               Show token savings statistics (rtk gain)
---version            Show RTK version (rtk --version)
---init               Initialize RTK for current project (rtk init -g)
---timeout <ms>       Execution timeout (default: 120000, max: 600000)
---working-dir <dir>  Working directory for command execution
-```
-
-## Workflow
-
-```
-1. Pre-checks
-   - Verify `rtk` binary is installed (which rtk)
-   - No authentication required
-2. Build command
-   - Special: rtk gain | rtk --version | rtk init -g
-   - Proxy: rtk <command> [args...]
-3. Execute
-   - Run via Bash tool with timeout (default 2min, max 10min)
-   - Or use helper script: node .claude/skills/rtk-exec/scripts/rtk-wrapper.cjs
-4. Parse output
-   - RTK always returns plain text compressed output (no JSON modes)
-   - Capture stdout and stderr
-5. Report results
-   - Format output with execution metadata and token savings info
-```
-
-## Supported Commands
-
-RTK supports 100+ CLI commands across categories:
-
-| Category | Commands |
-|----------|----------|
-| File ops | `ls`, `find`, `grep`, `cat`, `tree`, `du`, `diff` |
-| Git | `git status`, `git log`, `git diff`, `git push`, `git pull`, `git branch` |
-| Test runners | `cargo test`, `pytest`, `vitest`, `jest`, `go test`, `bun test` |
-| Linters | `eslint`, `tsc`, `ruff`, `clippy`, `golangci-lint`, `rubocop` |
-| Package managers | `pnpm install`, `pip install`, `cargo build`, `npm install` |
-| Containers | `docker build`, `docker ps`, `kubectl get`, `kubectl logs` |
-| Build tools | `make`, `cmake`, `gradle`, `mvn` |
-| System | `ps`, `top`, `df`, `netstat`, `env` |
-
-## Output Format
-
-### Success
-```
-[RTK Exec] Completed
-
-Command: rtk git status
-Duration: 0.3s
-Working Dir: /path/to/project
-
---- Output ---
-{rtk compressed output}
-```
-
-### Success (--gain)
-```
-[RTK Exec] Token Savings
-
---- Gain Report ---
-{rtk gain statistics showing tokens saved per command}
-```
-
-### Failure
-```
-[RTK Exec] Failed
-
-Command: rtk cargo test
-Error: {error_message}
-Exit Code: {code}
-Stderr: {stderr}
-Suggested Fix: {suggestion}
-```
-
-## Helper Script
-
-For complex executions or programmatic use:
-```bash
-node .claude/skills/rtk-exec/scripts/rtk-wrapper.cjs --command "cargo test" [options]
-```
-
-The wrapper provides:
-- Binary availability check
-- Safe command construction
-- Timeout handling with graceful SIGTERM → SIGKILL escalation
-- Structured JSON output for programmatic consumption
-
-## Examples
-
-```bash
-# List files with compression
-/rtk-exec "ls -la src/"
-
-# Git status (often 70%+ token reduction)
-/rtk-exec "git status"
-
-# Run Rust tests
-/rtk-exec "cargo test"
-
-# Run Python tests
-/rtk-exec "pytest tests/ -v"
-
-# TypeScript type check
-/rtk-exec "tsc --noEmit"
-
-# Show token savings stats
-/rtk-exec --gain
-
-# Initialize RTK for project
-/rtk-exec --init
-
-# With timeout override
-/rtk-exec "cargo build --release" --timeout 300000
-
-# Specify working directory
-/rtk-exec "git log --oneline -20" --working-dir /path/to/repo
-```
-
-## Integration
-
-Works with the orchestrator pattern:
-- Main conversation delegates CLI execution via this skill
-- Results are returned to the main conversation for further processing
-- Particularly effective for test runs, lint checks, and git operations where output is verbose
-- Can be chained: rtk-exec for output collection → Claude expert for analysis
-
-## Availability Check
-
-rtk-exec requires the RTK binary to be installed. The skill is only usable when:
-
-1. `rtk` binary is found in PATH (`which rtk` succeeds)
-2. No authentication or API keys required
-
-If the binary check fails, this skill cannot be used. Fall back to direct Bash tool execution.
-
-> **Note**: This skill is invoked via `/rtk-exec` command or delegated by the orchestrator. It is most useful for any task that produces verbose CLI output that would otherwise consume large amounts of context tokens.
-
-## Agent Teams Integration
-
-When used within Agent Teams:
-
-1. **As delegated task**: orchestrator explicitly delegates CLI execution for token-efficient output
-2. **Hybrid workflow**: Claude team member plans → rtk-exec runs commands → Claude analyzes compressed output
-3. **Batch execution**: Multiple rtk-exec invocations in parallel for different commands
-
-```
-Orchestrator delegates CLI task
-  → /rtk-exec invoked with command
-  → Compressed output returned to orchestrator
-  → Analyst processes compressed result
-  → Iterate if needed
-```
-
-## Token Savings
-
-RTK uses four compression strategies:
-
-| Strategy | Description | Typical Savings |
-|----------|-------------|-----------------|
-| Smart Filtering | Removes redundant/noise lines based on command type | 30-50% |
-| Grouping | Collapses repeated patterns into summary counts | 20-40% |
-| Truncation | Clips excessively long lines with ellipsis | 10-20% |
-| Deduplication | Removes identical repeated output blocks | 15-30% |
-
-Combined effect: **60-90% token reduction** on typical CLI output (git log, test results, lint reports).
-
-## Installation
-
-```bash
-# macOS via Homebrew
-brew install rtk
-
-# Universal install script
-curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh
-
-# From source via Cargo
-cargo install --git https://github.com/rtk-ai/rtk
-
-# Verify installation
-rtk --version
-```