oh-my-customcode 1.1.14 → 1.1.16

package/dist/cli/index.js

@@ -241,7 +241,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "1.1.14",
+    version: "1.1.16",
     description: "Batteries-included agent harness for Claude Code",
     type: "module",
     bin: {

package/dist/index.js

@@ -2031,7 +2031,7 @@ var package_default = {
   workspaces: [
     "packages/*"
   ],
-  version: "1.1.14",
+  version: "1.1.16",
   description: "Batteries-included agent harness for Claude Code",
   type: "module",
   bin: {

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "1.1.14",
+  "version": "1.1.16",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/agents/mgr-sauron.md

@@ -1,6 +1,6 @@
 ---
 name: mgr-sauron
-description: Use when you need automated verification of R017 compliance, executing mandatory multi-round verification (5 manager rounds + 3 deep review rounds) before commits
+description: Use when you need automated verification of R017 compliance, executing mandatory multi-round verification (5 manager rounds + 3 deep review rounds, with rounds 3-4 conditionally skipped when rounds 1-2 return 0 issues) before commits
 model: sonnet
 domain: universal
 memory: local
@@ -33,6 +33,7 @@ You are an automated verification specialist that executes the mandatory R017 ve
 9. Structural linting: routing coverage (unreachable agents), orphan skill detection, circular dependency check, context:fork cap verification
 10. Auto-fix simple issues (count mismatches, missing fields)
 11. Generate verification report
+12. Cost-aware verification: skip Round 3-4 re-verification when Round 1-2 found 0 issues; substitute deterministic script results (verify-template-sync.sh, verify-wiki-sync.sh, verify-version-sync.sh, validate-docs.ts) for LLM re-derivation of count/template/wiki checks in Round 5 (R023 shift-left, no loss to verification coverage)
 
 ## Commands
 

package/templates/.claude/rules/MUST-agent-design.md

@@ -49,12 +49,13 @@ Extended context suffix: `[1m]` (e.g., `claude-opus-4-6[1m]`) — enables 1M tok
 
 This is a settings-level resilience mechanism, distinct from the per-agent `model:` frontmatter. It complements the `model-escalation` skill (outcome-based escalation) by handling availability/overload failover at the platform level.
 
-> **v2.1.178+**: Compaction now honors the `fallbackModel` chain — on overload or model-availability errors during context compaction, CC falls back to the configured fallback model instead of failing the compaction. Extends the v2.1.166 `fallbackModel` resilience to the compaction path.
+<!-- ARCHIVED CC version note (historical): > **v2.1.178+**: Compaction now honors the `fallbackModel` chain — on overload or model-availability errors during context compaction, CC falls back to the configured fallback model instead of failing the compaction. Extends the v2.1.166 `fallbackModel` resilience to the compaction path. -->
 
 ### Thinking Toggle (CC v2.1.166+)
 
 > **v2.1.166+**: `MAX_THINKING_TOKENS=0`, `--thinking disabled`, and the per-model thinking toggle disable thinking on models that think by default via the Claude API (3rd-party providers unchanged). Relevant when an agent's `effort` is low and thinking overhead is undesirable.
 
+<!-- ARCHIVED CC version notes (historical):
 > **v2.1.183+**: CC now warns (stderr, in `-p` print mode) when the requested model is deprecated or auto-updated to a newer model — and this warning now ALSO covers models set in agent frontmatter (`model:`). Relevant to the Model Aliases table above: a stale/deprecated `model:` value in agent frontmatter now surfaces a deprecation warning instead of silently resolving. Separately, v2.1.183 fixes `thinking.disabled.display: Extra inputs are not permitted` 400 errors on subagent spawns and session-title generation — extends the v2.1.166 toggle above; subagent spawns with thinking disabled no longer 400.
 
 > **v2.1.187+**: Org-configured model restrictions now apply to the model picker, `--model`, `/model`, and `ANTHROPIC_MODEL` (a restricted model shows "restricted by your organization's settings"). Extends the v2.1.175 `enforceAvailableModels` scope to per-agent `model:` override entry points — a managed model allowlist now also constrains the picker/env paths. Also fixed `--json-schema` / workflow `agent({schema})` structured output: the model can no longer re-call `StructuredOutput` indefinitely after a successful call, and follow-up turns reliably return structured output — relevant to schema-constrained subagent spawns.
@@ -62,14 +63,17 @@ This is a settings-level resilience mechanism, distinct from the per-agent `mode
 > **v2.1.196+**: 조직 기본 모델(org default models)이 추가되어 관리자가 org 콘솔에서 조직 전체 기본 모델을 설정하며, 사용자가 직접 선택하지 않으면 `/model`에 "Org default"(또는 "Role default")로 표시됩니다. v2.1.175 `enforceAvailableModels`/v2.1.187 org model restriction의 연장선 — 조직 관리 설정이 기본 모델 해석까지 관여합니다. 또한 백그라운드 세션 turn 이후 중복 recap 라인 문제를 수정 — schema-rejected된 StructuredOutput 시도가 재시도와 나란히 렌더되지 않습니다(schema-constrained subagent spawn / Workflow `agent({schema})`에 관련).
 
 > **v2.1.198+**: 내장 Explore 에이전트가 이제 main session의 모델을 상속합니다(opus로 cap; 이전에는 haiku 고정) — Explore 기반 검색 subagent의 추론 품질이 향상됩니다. 또한 subagent와 context compaction이 session의 extended thinking 설정을 상속하여, 위임된 작업의 출력 품질이 세션 설정과 정합됩니다. R009/R018 병렬 subagent 위임 품질에 관련.
+-->
 
 ### Safe Mode & Bundled Skill Control (CC v2.1.169+)
 
 > **v2.1.169+**: `--safe-mode` (and `CLAUDE_CODE_SAFE_MODE`) starts Claude Code with ALL customizations disabled (CLAUDE.md, plugins, skills, hooks, MCP servers) — use it to isolate whether a project customization (agent/skill/hook) causes a regression. The `disableBundledSkills` setting (and `CLAUDE_CODE_DISABLE_BUNDLED_SKILLS` env) hides bundled skills, workflows, and built-in slash commands from the model — useful when bundled skills conflict with or duplicate project skills (R006 skill-surface management). Note: `disableBundledSkills` hides skills from the model but is a CC platform setting, distinct from the advisory `skills:` frontmatter field (which is documentation metadata, not a runtime allowlist).
 
+<!-- ARCHIVED CC version notes (historical):
 > **v2.1.172+**: `availableModels` restrictions now apply to subagent `model:` overrides, the agent dispatch model picker, and the advisor model. `availableModels` allowlists using version-specific IDs (e.g. `claude-opus-4-8`) no longer hide the Opus/Sonnet 1M picker rows, and model IDs no longer receive a doubled 1M suffix (`[1M][1m]`) when `ANTHROPIC_DEFAULT_OPUS_MODEL` already includes one. Relevant when restricting per-agent model overrides via `availableModels`.
 
 > **v2.1.175+**: The `enforceAvailableModels` managed setting — when enabled, the `availableModels` allowlist also constrains the **Default** model: a Default that would resolve to a disallowed model now falls back to the first allowed model, and user or project settings can no longer widen a managed `availableModels` list. Extends the v2.1.172 `availableModels` scope (subagent `model:` overrides, dispatch picker, advisor model) to the Default model itself. Relevant when an enterprise/managed config pins the allowed model set — per-agent `model:` overrides AND the resolved Default both honor it.
+-->
 
 ### Optional Frontmatter
 
@@ -206,6 +210,7 @@ Agent frontmatter `hooks:` now fire when the agent runs as a main-thread agent v
 
 > **Note**: `/reload-plugins` now auto-installs missing plugin dependencies from added marketplaces (v2.1.116+).
 
+<!-- ARCHIVED CC version notes (historical):
 > **v2.1.157+**: `settings.json` `agent` field is now honored for dispatched sessions (with `--agent <name>` override). `EnterWorktree` can switch between Claude-managed worktrees mid-session, and worktrees are left unlocked when the agent finishes (enabling `git worktree remove`/`prune` cleanup).
 
 > **v2.1.191+**: Hooks with comma-separated matchers (e.g. `"Bash,PowerShell"`) now fire correctly — previously such matchers silently never fired. Relevant when authoring `.claude/hooks/` entries that target multiple tools in one matcher.
@@ -213,12 +218,13 @@ Agent frontmatter `hooks:` now fire when the agent runs as a main-thread agent v
 > **v2.1.195+**: 하이픈이 포함된 hook matcher 식별자(예: `code-reviewer`, `mcp__brave-search`)가 이제 substring이 아니라 exact-match됩니다(이전에는 부분 문자열로 우연히 매칭). 하이픈 포함 MCP 서버의 모든 tool을 매칭하려면 `mcp__brave-search__.*` 형식을 사용하세요. 참고: oh-my-customcode의 `hooks.json`은 `*` / `mcp_tool_name matches "..."` / `tool == "..."` 형식을 사용하므로 이 변경의 영향을 받지 않습니다 — 다만 하이픈 포함 tool-name matcher를 새로 추가할 때 exact-match 시맨틱을 고려해야 합니다.
 
 > **v2.1.199+**: SessionStart/Setup/SubagentStart hook이 exit code 2로 종료할 때 stderr를 조용히 숨기던 문제가 수정되어 이제 오류가 표시됩니다. `.claude/hooks.json`의 hard-block/advisory hook 디버깅 가시성이 향상됩니다(R021 Enforcement Tiers 관측성과 정합).
+-->
 
 > **v2.1.204+**: headless 세션의 SessionStart hook 중 hook 이벤트가 스트리밍되지 않아 remote worker가 hook 도중 idle-reap되던 문제가 수정되었습니다. Hook Event Types/SessionStart 관련.
 
 ## Permission Mode Guidance
 
-CC defaults `mode` to `acceptEdits` if not specified — always pass `mode: "bypassPermissions"` explicitly in Agent tool calls (see R010). See guidance details via Read tool.
+> Canonical source for the bypassPermissions requirement: R010 (MUST-orchestrator-coordination.md) "Universal bypassPermissions". CC defaults `mode` to `acceptEdits` if not specified — always pass `mode: "bypassPermissions"` explicitly in Agent tool calls. See R010 for the full requirement, rationale, and self-check.
 
 | Mode | Behavior |
 |------|----------|
@@ -412,11 +418,13 @@ Key optional fields: `scope`, `context`, `version`, `effort`, `model`, `agent`,
 
 > **v2.1.163+**: In skill `command` bodies, use `\$` to emit a literal `$` before a number (e.g., `\$1`) — previously ambiguous with shell variable expansion. Relevant when authoring skills with `shell:` or inline command steps that include dollar signs not intended as variables.
 
+<!-- ARCHIVED CC version notes (historical):
 > **v2.1.178+**: Skills in nested `.claude/skills` directories now load when working on files in that subtree; on a name clash with a higher-scope skill, the nested skill is surfaced as `<dir>:<name>` so both remain invokable. Directory-qualified nested skills also no longer trigger permission prompts in non-interactive runs. Additionally, MCP-spec entries (`mcp__server`, `mcp__server__*`, `mcp__*`) in a subagent's `disallowedTools` are now honored (previously silently ignored) — relevant to the Optional Frontmatter `disallowedTools` field. oh-my-customcode keeps a flat `.claude/skills/` layout, but the `<dir>:<name>` disambiguation matters if a nested project subtree introduces a same-named skill.
 
 > **v2.1.178+**: When names collide across nested `.claude/` directories, the agent, workflow, and output-style CLOSEST to the working directory now wins; project-scope workflow saves target the closest existing `.claude/workflows/`. Relevant to multi-`.claude/` layouts — project-root `.claude/` definitions are overridden by a nested `.claude/` when working inside that subtree.
 
 > **v2.1.199+**: 스택된 slash-skill 호출(`/skill-a /skill-b do XYZ`)이 이제 leading skill을 최대 5개까지 모두 로드합니다(이전에는 첫 번째만 로드). oh-my-customcode의 라우팅 스킬 체이닝(예: `/omcustom:fsd`가 여러 스킬을 연쇄 호출하는 패턴)에서 다중 스킬 스택 호출 시 컨텍스트 손실이 줄어듭니다. 또한 subagent 조회 중 `/model`·`/fast`를 입력하면 lead의 model picker가 열리며 notice가 표시됩니다.
+-->
 
 <!-- DETAIL: Skill Optional Fields (full yaml block)
 ```yaml

package/templates/.claude/rules/MUST-agent-identification.md

@@ -47,9 +47,9 @@ When the orchestrator invokes a skill via the Skill tool, the skill name MUST be
 └─ Task: {brief-task-description}
 ```
 
+<!-- DETAIL: Common Violations examples (redundant with Skill Invocation Format above)
 ### Common Violations
 
-```
 Incorrect: Skill as separate display
    ┌─ Agent: claude (default)
    └─ Task: research topic analysis
@@ -64,7 +64,7 @@ Correct: With sub-skill
    ┌─ Agent: claude → research
    ├─ Skill: result-aggregation
    └─ Task: aggregate team findings
-```
+-->
 
 ## When to Display
 
@@ -85,17 +85,17 @@ Correct: With sub-skill
 
 체크 실패 시 즉시 헤더/prefix 추가 후 도구 호출. PostCompact hook 만으로 보장되지 않으며 압축 없이도 멀티턴 누락이 발생하므로 매 턴 자가 점검 강제.
 
+<!-- DETAIL: Common Multi-Turn Violation example (redundant with Short Response Discipline table below)
 ### Common Multi-Turn Violation
 
-```
 턴 1: ┌─ Agent: claude (default) ✓
 턴 2: (헤더 없음, 짧은 답변이라 생략) ✗
 턴 3: 도구 호출 prefix 누락 ✗
-```
 
 응답 길이/턴 위치 무관. 짧은 답변에도 헤더는 필수.
 
 Reference issue: #1096.
+-->
 
 ### Short Response Discipline
 
@@ -118,7 +118,7 @@ Reference issue: #1096.
 |--------------|----------|
 | 도구 결과 수신 후 응답 텍스트 없이 turn 종료 ("(no content)") | 최소 1줄 진행 상태 + R007 헤더 출력 후 종료/계속 |
 
-Reference issues: #1188 item #2, #1198 item #2, #1409.
+<!-- Reference issues: #1188 item #2, #1198 item #2, #1409. -->
 
 ### External-Project / Debugging Session Vigilance
 
@@ -132,6 +132,6 @@ R007 헤더 누락은 외부 프로젝트 디버깅, SSH 진단, 배포 작업
 
 기술적 몰입 중 헤더 누락이 반복될 경우 즉시 re-anchor: 다음 응답에 `┌─ Agent:` 풀 헤더를 붙이고 이후 계속 유지한다.
 
-외부 프로젝트 진단 세션(예: #1417 통화녹음 수집 진단)에서 세션 전체에 걸쳐 헤더가 반복 누락되는 재발이 관측되었다 — 진단 몰입 중에도 매 응답 헤더를 고정한다.
-
+<!-- DETAIL: Case history — 외부 프로젝트 진단 세션(예: #1417 통화녹음 수집 진단)에서 세션 전체에 걸쳐 헤더가 반복 누락되는 재발이 관측되었다 — 진단 몰입 중에도 매 응답 헤더를 고정한다.
 Reference issues: #1401, #1417.
+-->

package/templates/.claude/rules/MUST-agent-teams.md

@@ -50,7 +50,10 @@ These are distinct mechanisms. Agent Teams `SendMessage` requires `TeamCreate` a
 
 This hardens cross-session coordination (claude-peers-mcp `send_message`, see Scope table above) against privilege escalation — a relayed message from session A cannot grant session B permissions the user did not authorize on B. Aligns with R001 (credential/privileged-scope guardrails) and R010 (out-of-scope privileged chaining). Intra-session Agent Teams `SendMessage` between peers in the same session is unaffected.
 
+<!-- ARCHIVED CC version note (historical):
 > **v2.1.183+**: Fixed tmux teammate panes failing to launch when the shell has slow rc-file initialization — a slow `.zshrc`/`.bashrc` no longer prevents Agent Teams teammate panes from launching in tmux. Also fixed WebSearch returning empty results in subagents: a subagent (including a Teams member) using WebSearch now returns results instead of silently empty.
+-->
+
 
 ## Self-Check (Before Agent Tool)
 
@@ -384,7 +387,10 @@ Cross-reference: R020 ("actual outcome ≠ attempt" — verifying that a command
 
 Observed instance: v0.159.0 release (session 105) — members assigned to disjoint-file cleanup tasks went idle without executing; deterministic git-diff check exposed the gap; work was reassigned to standalone parallel Agents. References: #1261, #1262.
 
+<!-- ARCHIVED CC version note (historical):
 > **v2.1.186+**: Added the `teammateMode: "iterm2"` setting (warns when auto mode cannot find the `it2` CLI), and added status filtering (press `f`) to the `/workflows` agent detail view. Relevant to Agent Teams teammate launch configuration (cf. v2.1.183 tmux teammate-pane fix).
+-->
+
 
 ## Member Prompt Size Cap
 

package/templates/.claude/rules/MUST-orchestrator-coordination.md

@@ -278,6 +278,8 @@ Cross-reference: the Subagent Scope-Creep STOP Protocol (reactive halt after tri
 
 ## Universal bypassPermissions
 
+> **This section is the canonical single source for the bypassPermissions requirement.** R002 (MUST-permissions.md) and R006 (MUST-agent-design.md) reference this section rather than repeating it.
+
 **ALL Agent tool calls MUST include `mode: "bypassPermissions"`.**
 
 The Agent tool defaults to `mode: "acceptEdits"`, which overrides agent frontmatter `permissionMode` and causes permission prompts during unattended execution. This is a CC platform behavior, not a configuration error.
@@ -308,7 +310,10 @@ Before spawning any agent:
 
 ### Background Agent Permission Mode (`/bg` flow)
 
+<!-- ARCHIVED CC version note (historical):
 > **v2.1.141+**: Background agents launched via `/bg` or `←←` now preserve the current session's permission mode instead of reverting to default. Previously, detaching a session could cause `bypassPermissions` to be lost, triggering unexpected permission prompts in unattended flows.
+-->
+
 
 | CC Version | `/bg` permission behavior |
 |------------|--------------------------|
@@ -317,6 +322,7 @@ Before spawning any agent:
 
 `mode: "bypassPermissions"` on every Agent tool call is still required (applies to Agent tool, not `/bg` shell command).
 
+<!-- ARCHIVED CC version note (historical):
 > **v2.1.172+**: Fixed background agents potentially reading another directory's project settings (`.mcp.json` approvals, trust) when dispatched onto a pre-warmed worker. Strengthens background-agent isolation — a `/bg`-dispatched agent now reads the correct project's settings.
 
 > **v2.1.174+**: Fixed background sessions inheriting another session's `ANTHROPIC_*` provider env (gateway URL, custom headers, `/model` aliases) from the shell that started the background daemon. Further strengthens background-agent isolation (cf. v2.1.172 project-settings isolation): a `/bg`-dispatched agent no longer picks up a foreign session's provider configuration. Also fixed pre-warmed background workers failing with "Could not resolve authentication method" when claimed after sitting idle. `mode: "bypassPermissions"` on every Agent tool call remains required regardless.
@@ -338,6 +344,7 @@ Before spawning any agent:
 > **v2.1.196+**: 백그라운드 작업을 wake할 때 transcript probe가 실제 transcript를 오독하여 대화를 영구 삭제하고 원 프롬프트를 재실행하던 문제를 수정 — 이제 파일을 삭제하지 않고 따로 보관합니다(transcript 의존 스킬 `homework`/`episodic-memory`에 관련). `claude agents --dangerously-skip-permissions`가 조용히 auto mode로 폴백하던 문제를 수정하여 bypass 고지를 표시하고 spawned agent에도 bypass 모드를 적용합니다(R010 Universal bypassPermissions와 정합). 또한 `claude agents` 사이드 패널 문제들(에이전트 열 때 키보드 포커스 고착, 열 때마다 백그라운드 작업의 subagent type 유실, 활성 실행 중 잘못된 상태 표시)을 수정. `mode: "bypassPermissions"`는 여전히 필수입니다.
 
 > **v2.1.198+**: `claude agents`에서 launch된 background agent가 worktree에서 code 작업을 완료하면 이제 멈춰서 묻지 않고 commit·push·draft PR open을 자동 수행합니다. 또한 응답 중 일시적 network 오류(ECONNRESET 등)로 turn이 abort되던 문제가 backoff retry로 수정되었고, web/desktop/VS Code task panel에서 background task가 완료 후에도 "Running"으로 멈춰있던 문제가 수정되었습니다. background agent의 자동 commit/PR 자동화가 강화되었으므로, `mode: "bypassPermissions"`는 여전히 필수입니다.
+-->
 
 > **v2.1.199+**: subagent가 rate limit이나 server error로 잘리면 이제 조용히 실패하는 대신 partial work를 parent에 반환합니다. background-agent daemon(Linux)이 unclean shutdown 후 corrupted worker record로 ~50초마다 자신과 모든 agent를 죽이던 문제, macOS SSH cold-start "Could not switch to audit session" 문제, `claude stop`이 background-agent respawn과 race하면 조용히 무효화되던 문제(이제 respawn이 stop을 존중), background job progress indicator가 긴 명령 중 멈춰있던 문제가 수정되었습니다. background-agent lifecycle 견고성이 추가로 강화되었으며, `mode: "bypassPermissions"`는 여전히 필수입니다.
 

package/templates/.claude/rules/MUST-permissions.md

@@ -35,7 +35,7 @@ On insufficient permission: do not attempt, notify user, suggest alternative.
 
 ## Deny Rule Glob Patterns (CC v2.1.166+)
 
-> **v2.1.166+**: Deny rules support glob patterns in the tool-name position — `"*"` in a deny rule denies all tools. Allow rules reject non-MCP globs (only MCP tool-name globs are accepted in the allow position). Unknown tool names in deny rules emit a startup warning.
+<!-- ARCHIVED CC version note (historical): v2.1.166+: Deny rules support glob patterns in the tool-name position — `"*"` in a deny rule denies all tools. Allow rules reject non-MCP globs (only MCP tool-name globs are accepted in the allow position). Unknown tool names in deny rules emit a startup warning. -->
 
 | Position | Glob support |
 |----------|-------------|
@@ -47,17 +47,17 @@ Use a `"*"` deny rule in `settings.json` to enforce a deny-by-default posture, t
 
 > **v2.1.178+**: Permission rules now support `Tool(param:value)` syntax to match a tool's input parameters, with `*` wildcard — e.g. `Agent(model:opus)` denies Opus subagents, or a parameter glob to constrain a tool's arguments. This extends the v2.1.166 tool-name glob support down to per-parameter granularity. Relevant to the Agent Tool Permission Mode below: a deny rule can now block specific subagent models/parameters at the platform level, complementing `availableModels` (R006) and the universal `mode: "bypassPermissions"` requirement (R010). A `Agent(model:...)` parameter deny is evaluated by the CC platform independent of the advisory tier table.
 
-> **v2.1.183+**: Fixed MCP servers requiring authentication exposing auth-stub tools to the model in headless/SDK mode — unauthenticated MCP auth-stub tools are no longer surfaced to the model in `-p` / SDK runs (they would fail on call). Relevant to the Tier-6 MCP tier: a headless run no longer offers auth-stub MCP tools. Separately, v2.1.181 added the `sandbox.allowAppleEvents` opt-in setting, letting sandboxed commands send Apple Events on macOS (default off) — a deliberate sandbox-scope widening, complementing the Tier-based policy above.
+<!-- ARCHIVED CC version note (historical): v2.1.183+: Fixed MCP servers requiring authentication exposing auth-stub tools to the model in headless/SDK mode — unauthenticated MCP auth-stub tools are no longer surfaced to the model in `-p` / SDK runs (they would fail on call). Relevant to the Tier-6 MCP tier: a headless run no longer offers auth-stub MCP tools. Separately, v2.1.181 added the `sandbox.allowAppleEvents` opt-in setting, letting sandboxed commands send Apple Events on macOS (default off) — a deliberate sandbox-scope widening, complementing the Tier-based policy above. -->
 
-> **v2.1.186+**: Added `claude mcp login <name>` / `claude mcp logout <name>` to authenticate MCP servers from the CLI without the interactive `/mcp` menu (`--no-browser` stdin redirect for SSH). Also fixed `Agent(type)` deny rules and `Agent(x,y)` allowed-types restrictions not being enforced for named subagent spawns — extends the v2.1.178 `Tool(param:value)` per-parameter permission syntax (Agent model/param deny) to reliable enforcement on named spawns. Relevant to Tier-6 MCP and the Agent Tool Permission Mode section.
+<!-- ARCHIVED CC version note (historical): v2.1.186+: Added `claude mcp login <name>` / `claude mcp logout <name>` to authenticate MCP servers from the CLI without the interactive `/mcp` menu (`--no-browser` stdin redirect for SSH). Also fixed `Agent(type)` deny rules and `Agent(x,y)` allowed-types restrictions not being enforced for named subagent spawns — extends the v2.1.178 `Tool(param:value)` per-parameter permission syntax (Agent model/param deny) to reliable enforcement on named spawns. Relevant to Tier-6 MCP and the Agent Tool Permission Mode section. -->
 
 > **v2.1.187+**: Org-configured model restrictions now apply to the model picker, `--model`, `/model`, and `ANTHROPIC_MODEL`, surfacing a "restricted by your organization's settings" message for a restricted model. Extends the v2.1.175 `enforceAvailableModels` managed-setting scope to the model picker/env entry points. Also added the `sandbox.credentials` setting (blocks sandboxed reads of credential files/secret env) — cross-ref R001.
 
-> **v2.1.191+**: Sandbox network permission dialog now REMEMBERS hosts allowed with "Yes" for the rest of the session (no per-connection re-prompt). Also: `/permissions` Recently-denied tab now PERSISTS an approved denial on close (previously discarded); managed `forceRemoteSettingsRefresh` now takes effect via MDM/file policy with `Cache-Control: no-cache`; MCP capability discovery (`tools/list`/`prompts/list`/`resources/list`) and OAuth token requests now retry transient network errors with backoff (headless skips the browser popup). Relevant to Tier-4/Tier-6 (sandbox network + MCP) permission flows.
+<!-- ARCHIVED CC version note (historical): v2.1.191+: Sandbox network permission dialog now REMEMBERS hosts allowed with "Yes" for the rest of the session (no per-connection re-prompt). Also: `/permissions` Recently-denied tab now PERSISTS an approved denial on close (previously discarded); managed `forceRemoteSettingsRefresh` now takes effect via MDM/file policy with `Cache-Control: no-cache`; MCP capability discovery (`tools/list`/`prompts/list`/`resources/list`) and OAuth token requests now retry transient network errors with backoff (headless skips the browser popup). Relevant to Tier-4/Tier-6 (sandbox network + MCP) permission flows. -->
 
-> **v2.1.193+**: `autoMode.classifyAllShell` 설정은 모든 Bash/PowerShell 명령(Tier-4)을 arbitrary-code-execution 패턴만이 아니라 전부 auto-mode classifier로 보냅니다. auto-mode 거부 사유가 transcript / 거부 토스트 / `/permissions` recent denials에 노출됩니다. MCP 서버가 인증이 필요하면 시작 시 `/mcp`를 가리키는 알림을 표시하고, MCP `headersHelper` 인증은 tool 호출이 401/403을 반환하면 자동 재실행·재연결합니다(Tier-6). 이 섹션의 tier 기반 정책과 병존하는 플랫폼-레벨 동작입니다.
+<!-- ARCHIVED CC version note (historical): v2.1.193+: `autoMode.classifyAllShell` 설정은 모든 Bash/PowerShell 명령(Tier-4)을 arbitrary-code-execution 패턴만이 아니라 전부 auto-mode classifier로 보냅니다. auto-mode 거부 사유가 transcript / 거부 토스트 / `/permissions` recent denials에 노출됩니다. MCP 서버가 인증이 필요하면 시작 시 `/mcp`를 가리키는 알림을 표시하고, MCP `headersHelper` 인증은 tool 호출이 401/403을 반환하면 자동 재실행·재연결합니다(Tier-6). 이 섹션의 tier 기반 정책과 병존하는 플랫폼-레벨 동작입니다. -->
 
-> **v2.1.195+**: 프로젝트 `.claude/settings.json`으로만 활성화된 외부 플러그인이 이제 모든 loader 경로에서 명시적 설치 동의를 요구합니다(이전에는 일부 경로에서 우회됨). Tier-6 MCP/플러그인 신뢰 경계 강화.
+<!-- ARCHIVED CC version note (historical): v2.1.195+: 프로젝트 `.claude/settings.json`으로만 활성화된 외부 플러그인이 이제 모든 loader 경로에서 명시적 설치 동의를 요구합니다(이전에는 일부 경로에서 우회됨). Tier-6 MCP/플러그인 신뢰 경계 강화. -->
 
 > **v2.1.196+**: 조직 기본 모델(org default models)이 추가되어 관리자가 org 콘솔에서 설정하며, 사용자가 직접 고르지 않으면 `/model`에 "Org default"(또는 "Role default")로 표시됩니다 — v2.1.187 org model restriction 범위를 기본 모델 해석까지 확장(cross-ref R006). 보안: `claude mcp list`/`get`이 self-approved `.mcp.json` 서버를 spawn하지 않고 신뢰되지 않은 워크스페이스는 `⏸ Pending approval` 표시(Tier-6, cross-ref R001). 또한 `claude agents --dangerously-skip-permissions`가 조용히 auto mode로 폴백하던 문제를 수정 — 이제 bypass 고지를 표시하고 spawned agent에도 bypass 모드를 적용합니다(R010 Universal bypassPermissions와 정합).
 
@@ -69,12 +69,4 @@ Use a `"*"` deny rule in `settings.json` to enforce a deny-by-default posture, t
 
 ## Agent Tool Permission Mode
 
-When spawning subagents via the Agent tool, always pass `mode: "bypassPermissions"` explicitly. The Agent tool's default mode is `acceptEdits`, which **overrides** the agent frontmatter `permissionMode` field.
-
-| Setting | Effect |
-|---------|--------|
-| Agent frontmatter `permissionMode: bypassPermissions` | Ignored if Agent tool `mode` not set |
-| Agent tool `mode: "bypassPermissions"` | **Required** — actually controls subagent permissions |
-| Agent tool `mode` omitted | Defaults to `acceptEdits` → prompts for Bash, WebFetch |
-
-Skills that spawn agents MUST include `mode: "bypassPermissions"` in their Agent tool call instructions. This applies to all routing skills, pipeline skills, and any skill that delegates work to subagents.
+> Canonical source: R010 (MUST-orchestrator-coordination.md) "Universal bypassPermissions" owns the full requirement, rationale, self-check, and version history. Core rule: always pass `mode: "bypassPermissions"` explicitly on every Agent tool call — the Agent tool's default `mode` (`acceptEdits`) overrides agent frontmatter `permissionMode` and causes prompts during unattended execution. Skills that spawn agents MUST include this in their Agent tool call instructions. See R010 for details.

package/templates/.claude/rules/MUST-safety.md

@@ -100,7 +100,10 @@ Cross-reference: R010 Subagent Scope-Creep STOP Protocol, R002 (permission tiers
 
 > **v2.1.187+**: Added the `sandbox.credentials` setting — blocks sandboxed commands from reading credential files and secret environment variables. Platform-level complement to this section's credential guardrails (the model still never echoes secret values; CC now also blocks sandboxed reads of credential files/secret env at the platform level) — defense-in-depth.
 
+<!-- ARCHIVED CC version note (historical):
 > **v2.1.191+**: Sandbox network permission "Yes" approvals are remembered per-session (cf. R002). Reduces re-prompts but means an allowed host stays allowed for the session — scope network allows deliberately.
+-->
+
 
 > **v2.1.193+**: `autoMode.classifyAllShell` 설정은 arbitrary-code-execution 패턴만이 아니라 **모든** Bash/PowerShell 명령을 auto-mode classifier로 라우팅합니다. 이 섹션의 파괴적/자격증명 가드에 대한 플랫폼-레벨 보완입니다(모델은 여전히 명령 전 파괴적 작업을 열거하고 승인을 요청 — model-level; CC가 모든 shell을 classifier로 게이팅 — platform-level, 방어심층). auto-mode 거부 사유가 transcript, 거부 토스트, `/permissions` recent denials에 표시됩니다.
 

package/templates/.claude/rules/MUST-tool-identification.md

@@ -107,22 +107,20 @@ R008 "every tool call" applies to Tier-3 interaction tools too — NOT only file
 
 Skill invocation is the one exception: it is identified through the R007 integrated identification block (`┌─ Agent: claude → {skill-name}`), not a standalone R008 tool prefix.
 
-Reference issue: #1321 (session 113 retrospective, 찐빠 #2 — AskUserQuestion prefix omitted twice).
+<!-- Reference issue: #1321 (session 113 retrospective, 찐빠 #2 — AskUserQuestion prefix omitted twice). -->
 
+<!-- DETAIL: Consolidated Example (redundant with Parallel Spawn Prefix Rule example above)
 ## Example
 
-```
 [mgr-creator][sonnet] → Write: .claude/agents/new-agent.md
 [secretary][opus] → Spawning:
   [1] lang-golang-expert:sonnet → Go code review
   [2] lang-python-expert:sonnet → Python code review
-```
 
 Parallel spawn description parameter:
-```
 Agent(description: "[1] Go code review", subagent_type: "lang-golang-expert", ...)
 Agent(description: "[2] Python code review", subagent_type: "lang-python-expert", ...)
-```
+-->
 
 ## Multi-Turn Self-Check (MANDATORY)
 
@@ -134,17 +132,17 @@ Agent(description: "[2] Python code review", subagent_type: "lang-python-expert"
 
 체크 실패 시 즉시 prefix/필수 파라미터를 보완한 후 호출.
 
+<!-- DETAIL: Common Multi-Turn Violation example (redundant with Self-Check steps above)
 ### Common Multi-Turn Violation
 
-```
 호출 1 (턴 1): [claude][sonnet] → Tool: Read ✓
 호출 2 (턴 1, 같은 턴 추가 호출): (prefix 없음) ✗
 호출 3 (턴 2 첫 호출): (prefix 없음) ✗
-```
 
 같은 턴 내 추가 호출, 새 턴 첫 호출 모두 prefix 필수.
 
 Reference issue: #1096.
+-->
 
 ### Short Response Discipline
 
@@ -160,7 +158,7 @@ Reference issue: #1096.
 <Bash call>
 ```
 
-Reference issues: #1188 item #3, #1198 item #3.
+<!-- Reference issues: #1188 item #3, #1198 item #3. -->
 
 ### External-Project / Debugging Session Vigilance
 
@@ -172,6 +170,6 @@ R007 헤더와 마찬가지로, R008 prefix 누락도 외부 프로젝트 디버
 | 외부 프로젝트 디버깅 | **동일하게 필수** |
 | SSH / 배포 / 인프라 작업 | **동일하게 필수** |
 
-외부 프로젝트 진단 세션(#1417)에서 Bash/Edit/Read/Agent 모든 호출에 `[agent][model] → Tool:` prefix가 세션 전체 누락된 재발이 관측되었다 — 도구 호출 직전 prefix 부착을 워크플로에 내재화한다.
-
+<!-- DETAIL: Case history — 외부 프로젝트 진단 세션(#1417)에서 Bash/Edit/Read/Agent 모든 호출에 `[agent][model] → Tool:` prefix가 세션 전체 누락된 재발이 관측되었다 — 도구 호출 직전 prefix 부착을 워크플로에 내재화한다.
 Reference issues: #1401, #1417.
+-->

package/templates/.claude/rules/SHOULD-hud-statusline.md

@@ -15,17 +15,17 @@
 
 Format: `─── [Spawn] {subagent_type}:{model} | {description} ───` — implemented in `.claude/hooks/hooks.json` (PreToolUse → Agent/Task matcher). Display for multi-step/parallel/long-running ops only.
 
-> **v2.1.141+**: Hook JSON output can include `terminalSequence` field to emit window title changes or terminal bells without terminal control. Complementary to HUD stderr channel — e.g., update window title on task completion or ring bell after long parallel run. Modifying `.claude/hooks/` requires explicit user approval (R001).
+<!-- ARCHIVED CC version note (historical): v2.1.141+ — Hook JSON output can include `terminalSequence` field to emit window title changes or terminal bells without terminal control. Complementary to HUD stderr channel — e.g., update window title on task completion or ring bell after long parallel run. Modifying `.claude/hooks/` requires explicit user approval (R001). -->
 
-> **v2.1.157+**: `tool_decision` telemetry events now include `tool_parameters` (bash commands, MCP/skill names) when `OTEL_LOG_TOOL_DETAILS=1`. Complements R012 observability — enables per-tool parameter tracking in monitoring dashboards. See `monitoring-setup` skill.
+<!-- ARCHIVED CC version note (historical): v2.1.157+ — `tool_decision` telemetry events now include `tool_parameters` (bash commands, MCP/skill names) when `OTEL_LOG_TOOL_DETAILS=1`. Complements R012 observability — enables per-tool parameter tracking in monitoring dashboards. See `monitoring-setup` skill. -->
 
-> **v2.1.161+**: `OTEL_RESOURCE_ATTRIBUTES` values are now emitted as labels on metric datapoints — usage metrics can be sliced by custom dimensions (e.g., team, repo). Extends R012 observability from per-tool parameters (v2.1.157) to per-dimension metric slicing; configure via the `monitoring-setup` skill's `OTEL_RESOURCE_ATTRIBUTES` env. Separately, `claude agents` rows now show `done/total` progress before the detail when work is fanned out, and peek surfaces the longest-running item — complements the HUD parallel-spawn display and R009 `[N]` correlation.
+<!-- ARCHIVED CC version note (historical): v2.1.161+ — `OTEL_RESOURCE_ATTRIBUTES` values are now emitted as labels on metric datapoints — usage metrics can be sliced by custom dimensions (e.g., team, repo). Extends R012 observability from per-tool parameters (v2.1.157) to per-dimension metric slicing; configure via the `monitoring-setup` skill's `OTEL_RESOURCE_ATTRIBUTES` env. Separately, `claude agents` rows now show `done/total` progress before the detail when work is fanned out, and peek surfaces the longest-running item — complements the HUD parallel-spawn display and R009 `[N]` correlation. -->
 
-> **v2.1.174+**: The `/usage` (Account & usage) dialog now shows usage attribution — cache misses, long context, subagents, and per-skill/agent/plugin/MCP breakdowns over the last 24h or 7d (surfaced in the VSCode integration). Extends R012 observability from OTEL metric slicing (v2.1.161) to an interactive in-client attribution view — complements the `monitoring-setup` skill by giving per-skill/agent/plugin/MCP cost visibility without standing up an OTEL backend.
+<!-- ARCHIVED CC version note (historical): v2.1.174+ — The `/usage` (Account & usage) dialog now shows usage attribution — cache misses, long context, subagents, and per-skill/agent/plugin/MCP breakdowns over the last 24h or 7d (surfaced in the VSCode integration). Extends R012 observability from OTEL metric slicing (v2.1.161) to an interactive in-client attribution view — complements the `monitoring-setup` skill by giving per-skill/agent/plugin/MCP cost visibility without standing up an OTEL backend. -->
 
-> **v2.1.176+**: Added the `footerLinksRegexes` setting — regex-matched link badges rendered in the footer row, configurable via user or managed settings. Relevant to R012 statusline composition: the footer can now surface contextual link badges alongside the `.claude/statusline.sh` segments. Also in v2.1.176, session titles are generated in the conversation's language (pin via the `language` setting).
+<!-- ARCHIVED CC version note (historical): v2.1.176+ — Added the `footerLinksRegexes` setting — regex-matched link badges rendered in the footer row, configurable via user or managed settings. Relevant to R012 statusline composition: the footer can now surface contextual link badges alongside the `.claude/statusline.sh` segments. Also in v2.1.176, session titles are generated in the conversation's language (pin via the `language` setting). -->
 
-> **v2.1.172+**: Added a `model` attribute to the `claude_code.lines_of_code.count` OTEL metric — lines-of-code telemetry can now be sliced by model. Extends the per-dimension metric slicing (v2.1.161) in the `monitoring-setup` skill.
+<!-- ARCHIVED CC version note (historical): v2.1.172+ — Added a `model` attribute to the `claude_code.lines_of_code.count` OTEL metric — lines-of-code telemetry can now be sliced by model. Extends the per-dimension metric slicing (v2.1.161) in the `monitoring-setup` skill. -->
 
 > **v2.1.193+**: `claude_code.assistant_response` OpenTelemetry 로그 이벤트가 추가되어 모델의 응답 텍스트를 포함합니다. `OTEL_LOG_ASSISTANT_RESPONSES=1`이 아니면 redacted 되지만, 이 변수가 unset이면 `OTEL_LOG_USER_PROMPTS`를 따릅니다 — **보안 주의: 이미 프롬프트 내용을 로깅하는 배포는 업그레이드 즉시 응답 내용도 수신하기 시작합니다. 프롬프트만 유지하려면 `OTEL_LOG_ASSISTANT_RESPONSES=0`으로 설정하세요.** v2.1.157 tool_parameters / v2.1.161 metric slicing에 이은 `monitoring-setup` 스킬 OTEL 관측성 확장이며, 응답 텍스트 로깅은 명시적 opt-out이 필요한 민감 항목입니다.
 

package/templates/.claude/skills/sauron-watch/SKILL.md

@@ -26,6 +26,9 @@ Ensure complete synchronization of agents, skills, documentation, and project st
 ```
 
 #### Round 3-4: Re-verify + Update
+
+**Conditional skip (R023 shift-left, no loss)**: If Round 1-2 returned **0 issues** (both `mgr-supplier:audit` and `mgr-updater:docs` clean), SKIP Round 3-4 entirely — there is nothing to re-verify. If Round 1-2 found ANY issue (including auto-fixed ones), Round 3-4 MUST run in full to confirm the fix.
+
 ```
 □ mgr-supplier:audit - Re-verify after fixes
 □ mgr-updater:docs - Re-run and apply any detected changes
@@ -33,17 +36,22 @@ Ensure complete synchronization of agents, skills, documentation, and project st
 ```
 
 #### Round 5: Final Count Verification
+
+**Deterministic-script substitution (R023 shift-left, no loss)**: The items below marked `[script]` are already covered by existing deterministic scripts (`verify-template-sync.sh`, `verify-wiki-sync.sh`, `verify-version-sync.sh`, `validate-docs.ts`, pre-commit count-coverage hook). For those items, RUN the script and consume its PASS/FAIL result instead of re-deriving the same check via an LLM re-spawn. Items without `[script]` have no deterministic equivalent (semantic/philosophy checks) and MUST still be verified directly.
+
 ```
-□ Agent count matches: CLAUDE.md vs actual .md files
-□ Skill count matches: CLAUDE.md vs actual SKILL.md files
+□ [script] Agent count matches: CLAUDE.md vs actual .md files (pre-commit coverage / validate-docs.ts)
+□ [script] Skill count matches: CLAUDE.md vs actual SKILL.md files (pre-commit coverage / validate-docs.ts)
 □ Memory field distribution correct
-□ Hook/context/guide/rule counts match
+□ [script] Hook/context/guide/rule counts match (validate-docs.ts / verify-version-sync.sh)
 □ All frontmatter valid
 □ All skill refs exist
 □ All memory scopes valid (project|user|local)
 □ Routing patterns updated
-□ R006 Context Fork Criteria list matches actual SKILL.md frontmatter
+□ [script] R006 Context Fork Criteria list matches actual SKILL.md frontmatter
   (run `bash .github/scripts/verify-fork-list.sh`)
+□ [script] templates/ mirror byte-identical to source (verify-template-sync.sh)
+□ [script] wiki pages current vs source (verify-wiki-sync.sh)
 ```
 
 ### Phase 2: Deep Review (3 rounds)

package/templates/CLAUDE.md

@@ -97,6 +97,7 @@ oh-my-customcode로 구동됩니다.
 
 ### 슬래시 커맨드 (스킬 기반)
 
+<!-- METADATA (command catalog, advisory only — use /omcustom:lists for the live full list):
 | 카테고리 | 대표 커맨드 | 설명 |
 |----------|------------|------|
 | 프로젝트 관리 | `/omcustom:analysis`, `/omcustom:create-agent`, `/omcustom:audit-agents` | 분석, 에이전트/스킬 생성, 감사 |
@@ -106,6 +107,7 @@ oh-my-customcode로 구동됩니다.
 | 리서치 | `/research`, `/scout`, `/deep-plan` | 병렬 분석, URL 평가, 연구 계획 |
 | 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
 
@@ -161,6 +163,7 @@ oh-my-customcode는 소프트웨어 컴파일과 동일한 구조를 따릅니
 
 ## 에이전트 요약
 
+<!-- METADATA (agent roster by type, advisory only — use /omcustom:lists or wiki/agents/ for the live full catalog):
 | 타입 | 수량 | 에이전트 |
 |------|------|----------|
 | SW Engineer/Language | 6 | lang-golang-expert, lang-python-expert, lang-rust-expert, lang-kotlin-expert, lang-typescript-expert, lang-java-expert |
@@ -175,7 +178,9 @@ oh-my-customcode는 소프트웨어 컴파일과 동일한 구조를 따릅니
 | 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 | 4 | sys-memory-keeper, sys-naggy, tracker-checkpoint, wiki-curator |
-| **총계** | **49** | |
+-->
+
+총 **49개** 에이전트 (타입별 상세는 `/omcustom:lists` 또는 wiki/agents/ 참조)
 
 ## Agent Teams (MUST when enabled)
 
@@ -216,6 +221,10 @@ Claude Code의 Agent Teams 기능이 활성화되어 있으면 (`CLAUDE_CODE_EXP
 
 ## 외부 의존성
 
+필수/권장 플러그인·MCP 서버 카탈로그 및 설치 명령어는 1회성 설정 정보로 아래 HTML 주석에 보존됨(Read 도구로 확인 가능). 요약: 필수 5종(superpowers, superpowers-developing-for-claude-code, elements-of-style, obsidian-skills, context7), 권장 플러그인 4종, 권장 MCP 서버 3종(code-review-graph, semble, aws-mcp).
+
+<!-- METADATA (plugin/MCP catalog + install commands, advisory only — one-time setup, not needed every session):
+
 ### 필수 플러그인
 
 `/plugin install <이름>`으로 설치:
@@ -269,6 +278,7 @@ claude mcp add semble -- semble mcp
 claude mcp add-json aws-mcp --scope user '{"command":"uvx","args":["mcp-proxy-for-aws@latest","https://aws-mcp.us-east-1.api.aws/mcp","--metadata","AWS_REGION=us-west-2"]}'
 # 사전요건: AWS IAM 자격증명 구성. 가용 리전: us-east-1, eu-central-1 (API 호출은 전 리전)
 ```
+-->
 
 <!-- omcustom:git-workflow -->
 

package/templates/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.1.14",
+  "version": "1.1.16",
   "lastUpdated": "2026-07-14T00:00:00.000Z",
   "omcustomMinClaudeCode": "2.1.121",
   "omcustomMinClaudeCodeReason": "Sensitive-path direct Write/Edit on .claude/** under bypassPermissions (R010 deprecation, #1101)",