oh-my-customcode 1.1.102 → 1.1.103

package/templates/.claude/skills/instinct-extractor/SKILL.md

@@ -72,10 +72,10 @@ find ~/.claude/projects -name "session-*.jsonl" \
 추출된 이벤트를 `(domain, action_verb, error_class)` 튜플로 그룹화:
 
 ```
-Cluster: (agent-design, write, missing-frontmatter)
+Cluster: (agent-delegation, spawn, unverified-permission-mode)
   → sessions: [s1, s3, s7], count: 4
   → first_seen: 2026-05-01, last_seen: 2026-05-15
-  → example_corrections: ["bypassPermissions 누락", "name 필드 없음"]
+  → example_corrections: ["무인 실행 전 유효 권한 모드 미확인", "per-call mode 값을 무인 실행 증거로 간주"]
 ```
 
 필터링 기준:
@@ -88,9 +88,9 @@ Cluster: (agent-design, write, missing-frontmatter)
 각 클러스터를 "instinct 후보"로 명명:
 
 ```
-instinct: prevent-missing-bypassPermissions
-  근거: 4회 반복 (2주), agent spawn 시 mode 누락
-  대응 패턴: spawn 전 bypassPermissions 자가 체크
+instinct: verify-permission-mode-before-unattended
+  근거: 4회 반복 (2주), 무인 실행 전 유효 권한 모드 미확인
+  대응 패턴: 무인 실행 전 유효 권한 모드 실측(R010 Self-Check 1)
   제안 자산: 기존 R010 강화 OR 신규 guard skill
 ```
 
@@ -111,9 +111,9 @@ context fork cap (12개) 확인: 신규 skill이 `context: fork` 필요 시 현
 ```
 [instinct-extractor] {N}개 instinct 후보 발견 (최근 {DAYS}일, {M}개 세션)
 
-  1. [high] prevent-missing-bypassPermissions
-     반복: 4회 | 마지막: 2026-05-15 | 도메인: agent-design
-     대응 본능: spawn 전 mode 체크 → skill 후보: bypassPermissions-guard
+  1. [high] verify-permission-mode-before-unattended
+     반복: 4회 | 마지막: 2026-05-15 | 도메인: agent-delegation
+     대응 본능: 무인 실행 전 유효 모드 실측 → skill 후보: permission-mode-guard
 
   2. [medium] transcript-scan-format-mismatch
      반복: 3회 | 마지막: 2026-05-10 | 도메인: memory

package/templates/.claude/skills/intent-detection/SKILL.md

@@ -301,4 +301,4 @@ Use Claude's WebFetch/WebSearch
 └── Reason: {explanation}
 ```
 
-When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
+Pass `mode: "bypassPermissions"` on Agent calls for compatibility: it is required on CC < 2.1.212 (the per-call default, `acceptEdits`, overrides agent frontmatter `permissionMode`) and ignored on 2.1.212+, where subagents inherit the parent session's permission mode (adjustable via agent frontmatter `permissionMode`). Verify the effective mode before unattended runs: see R010 "Universal bypassPermissions".

package/templates/.claude/skills/multi-model-verification/SKILL.md

@@ -58,7 +58,7 @@ TeamCreate("verification-team")
 └── style-reviewer (haiku) → Style review
 ```
 
-Members communicate findings via SendMessage for cross-cutting concerns.
+Members communicate findings via SendMessage for cross-cutting concerns when their tool set includes it; otherwise they write findings to artifact files whose paths the orchestrator relays (R018 "멤버 도구 부재 시 대체 규약", #1817).
 
 ### Agent Tool Fallback
 
@@ -129,4 +129,4 @@ Multi-model verification uses 3x the tokens of a single review. Reserve for:
 - Architecture decisions
 - Pre-release verification
 
-When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
+Pass `mode: "bypassPermissions"` on Agent calls for compatibility: it is required on CC < 2.1.212 (the per-call default, `acceptEdits`, overrides agent frontmatter `permissionMode`) and ignored on 2.1.212+, where subagents inherit the parent session's permission mode (adjustable via agent frontmatter `permissionMode`). Verify the effective mode before unattended runs: see R010 "Universal bypassPermissions".

package/templates/.claude/skills/omcustom-release-notes/SKILL.md

@@ -210,4 +210,4 @@ mgr-gitnerd: gh release create           ->  create release with notes
 
 ## Permission Mode
 
-When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
+Pass `mode: "bypassPermissions"` on Agent calls for compatibility: it is required on CC < 2.1.212 (the per-call default, `acceptEdits`, overrides agent frontmatter `permissionMode`) and ignored on 2.1.212+, where subagents inherit the parent session's permission mode (adjustable via agent frontmatter `permissionMode`). Verify the effective mode before unattended runs: see R010 "Universal bypassPermissions".

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

@@ -64,7 +64,7 @@ Execute these steps to display available pipelines:
    - **Prompt steps** (`prompt: text`): Execute the described action using appropriate agents/tools
    - **Foreach steps** (`foreach: collection`): Iterate over collection from previous step output
    - **Parallel steps** (`parallel: [step1, step2]`): Execute contained steps concurrently using Agent tool. Each parallel step runs as an independent Agent. Max 4 concurrent per R009. Steps within a parallel block MUST be independent (no shared state, no sequential dependencies). Dependencies between parallel and non-parallel steps use `depends_on:` field.
-   - **Agent mode**: When spawning agents via Agent tool, always pass `mode: "bypassPermissions"` to match agent frontmatter. The Agent tool default (`acceptEdits`) overrides frontmatter `permissionMode`, causing permission prompts during unattended execution.
+   - **Agent mode**: Pass `mode: "bypassPermissions"` on Agent calls for compatibility: it is required on CC < 2.1.212 (the per-call default, `acceptEdits`, overrides agent frontmatter `permissionMode`) and ignored on 2.1.212+, where subagents inherit the parent session's permission mode (adjustable via agent frontmatter `permissionMode`). Verify the effective mode before unattended runs: see R010 "Universal bypassPermissions".
 5. Report completion or failure
 
 ### Resume Mode (/pipeline resume)

package/templates/.claude/skills/pipeline/workflows/auto-dev.yaml

@@ -492,7 +492,7 @@ steps:
       - Parallel execution per R009 (max 4 concurrent, respect dependencies)
       - Issues whose prerequisites failed in-run MUST be skipped (log reason)
       - No direct orchestrator writes (R010)
-      - All Agent tool calls MUST pass mode: "bypassPermissions" to prevent permission prompts during unattended execution
+      - On CC < 2.1.212 Agent tool calls need `mode: "bypassPermissions"` (the per-call default acceptEdits overrides frontmatter `permissionMode`), so pass it for compatibility. On CC >= 2.1.212 `mode` is ignored and subagents inherit the parent session's permission mode (frontmatter `permissionMode` may adjust it). Verify the effective mode before unattended execution per R010 「Universal bypassPermissions」 (pre-triage)
       - Mid-run scope additions (a new issue added via user interrupt AFTER implement began) MUST re-enter the verify-build gate before release — do NOT let a late-added scope item ride to release on a prior verify-build pass. Critical for code changes; benign for docs-only (#1301).
       - When an implement-stage delegation edits rule/skill/guide TEXT, the orchestrator MUST NOT author the final committed wording — the subagent writes it directly from the issue body (`gh issue view <N> --json body`); the delegation prompt supplies pointers, insertion anchors, constraints, verbatim tool-output quotations, and measured facts only
         (R010 「출처 인용과 인접 문구 점검도 같은 규율」 보강 2항목, #1698 #1). The orchestrator's own requirement/scope summary counts as final wording too — copy the issue's proposal sentence from `gh issue view` output verbatim, and tag any orchestrator paraphrase "[요약 — 원문 우선]"
@@ -803,7 +803,7 @@ steps:
 
       ## Sensitive Path Handling (CC v2.1.121+)
 
-      Direct Write/Edit/Bash on `.claude/**` is permitted under `mode: "bypassPermissions"` as of CC v2.1.121 (#1101). The legacy `/tmp/*.sh` bypass is no longer required. Structural changes (new agents/skills) still go through mgr-creator with R017 verification.
+      Direct Write/Edit/Bash on `.claude/**` is permitted under the `bypassPermissions` permission mode as of CC v2.1.121 (#1101). The legacy `/tmp/*.sh` bypass is no longer required. Structural changes (new agents/skills) still go through mgr-creator with R017 verification.
 
       For CC < v2.1.121 see git history for the legacy bypass pattern.
 

package/templates/.claude/skills/post-release-followup/SKILL.md

@@ -27,7 +27,7 @@ Gather unfinished work from multiple sources:
 
 ### Tool: Writing artifacts under .claude/outputs/
 
-Under `mode: "bypassPermissions"`, subagents write directly to `.claude/outputs/sessions/` with the Write tool — direct `.claude/**` writes are permitted (CC v2.1.121+, #1101). No `/tmp` staging or script wrapping is needed. Read-only Bash on `.claude/outputs/` (e.g., `cat`, `head`, `wc`) is allowed for verification.
+Under the `bypassPermissions` permission mode, subagents write directly to `.claude/outputs/sessions/` with the Write tool — direct `.claude/**` writes are permitted (CC v2.1.121+, #1101). No `/tmp` staging or script wrapping is needed. Read-only Bash on `.claude/outputs/` (e.g., `cat`, `head`, `wc`) is allowed for verification.
 
 Reference: R006/R010 sensitive-path handling (direct `.claude/**` write under bypassPermissions), #1101.
 
@@ -180,4 +180,4 @@ Add priority label (`P1`, `P2`, `P3`) based on categorization. Default for auto-
 
 ## Permission Mode
 
-When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
+Pass `mode: "bypassPermissions"` on Agent calls for compatibility: it is required on CC < 2.1.212 (the per-call default, `acceptEdits`, overrides agent frontmatter `permissionMode`) and ignored on 2.1.212+, where subagents inherit the parent session's permission mode (adjustable via agent frontmatter `permissionMode`). Verify the effective mode before unattended runs: see R010 "Universal bypassPermissions".

package/templates/.claude/skills/professor-triage/SKILL.md

@@ -50,13 +50,13 @@ When lightweight mode is used, the triage output (Phase 4E artifact and/or Phase
 
 | Phase | Agent | Mode |
 |-------|-------|------|
-| Phase 2 codebase search | Explore (haiku) | bypassPermissions |
-| Phase 4A Senior Architect | general-purpose (sonnet) | bypassPermissions |
-| Phase 4B Project Colleague | general-purpose (sonnet) | bypassPermissions |
-| Phase 4C Professor Synthesis | general-purpose (opus) | bypassPermissions |
-| Phase 4D triage comment | mgr-gitnerd | bypassPermissions |
-| Phase 4E artifact report | general-purpose | bypassPermissions |
-| Phase 5 GitHub actions | mgr-gitnerd | bypassPermissions |
+| Phase 2 codebase search | Explore (haiku) | pass `bypassPermissions` (required on CC < 2.1.212; ignored on 2.1.212+, where the parent session mode applies unless agent frontmatter `permissionMode` overrides it) |
+| Phase 4A Senior Architect | general-purpose (sonnet) | pass `bypassPermissions` (required on CC < 2.1.212; ignored on 2.1.212+, where the parent session mode applies unless agent frontmatter `permissionMode` overrides it) |
+| Phase 4B Project Colleague | general-purpose (sonnet) | pass `bypassPermissions` (required on CC < 2.1.212; ignored on 2.1.212+, where the parent session mode applies unless agent frontmatter `permissionMode` overrides it) |
+| Phase 4C Professor Synthesis | general-purpose (opus) | pass `bypassPermissions` (required on CC < 2.1.212; ignored on 2.1.212+, where the parent session mode applies unless agent frontmatter `permissionMode` overrides it) |
+| Phase 4D triage comment | mgr-gitnerd | pass `bypassPermissions` (required on CC < 2.1.212; ignored on 2.1.212+, where the parent session mode applies unless agent frontmatter `permissionMode` overrides it) |
+| Phase 4E artifact report | general-purpose | pass `bypassPermissions` (required on CC < 2.1.212; ignored on 2.1.212+, where the parent session mode applies unless agent frontmatter `permissionMode` overrides it) |
+| Phase 5 GitHub actions | mgr-gitnerd | pass `bypassPermissions` (required on CC < 2.1.212; ignored on 2.1.212+, where the parent session mode applies unless agent frontmatter `permissionMode` overrides it) |
 
 **Agent selection constraint**: Phases 4A, 4B, 4C, 4E MUST use `general-purpose` (NOT `arch-documenter`). `arch-documenter` has `disallowedTools: [Bash]` — cannot run the `gh`/shell commands these phases require. See #1043.
 
@@ -69,14 +69,14 @@ When lightweight mode is used, the triage output (Phase 4E artifact and/or Phase
 
 ## Artifact Output (R006/R010)
 
-Under `mode: "bypassPermissions"`, agents write directly to `.claude/outputs/` with Write/Edit — no temp-script wrapping is needed (CC v2.1.121+, #1101). When spawning Phase 4A/4B/4C/4E agents, include verbatim in each agent prompt:
+Under the `bypassPermissions` permission mode, agents write directly to `.claude/outputs/` with Write/Edit — no temp-script wrapping is needed (CC v2.1.121+, #1101). When spawning Phase 4A/4B/4C/4E agents, include verbatim in each agent prompt:
 
 ```
 **Artifact output (for this task)**
 
 If your task involves writing artifacts under `.claude/outputs/`, write the file to
 `.claude/outputs/sessions/<date>/<artifact>.md` using the Write tool directly (create the
-directory if needed). Your Agent tool call runs under `mode: "bypassPermissions"`, so direct
+directory if needed). If your session runs under the `bypassPermissions` permission mode, direct
 Write/Edit on `.claude/` is permitted.
 ```
 
@@ -98,4 +98,4 @@ See R006 "Sensitive Path Handling" (CC v2.1.121+ direct-write convention).
 
 ## Permission Mode
 
-When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
+Pass `mode: "bypassPermissions"` on Agent calls for compatibility: it is required on CC < 2.1.212 (the per-call default, `acceptEdits`, overrides agent frontmatter `permissionMode`) and ignored on 2.1.212+, where subagents inherit the parent session's permission mode (adjustable via agent frontmatter `permissionMode`). Verify the effective mode before unattended runs: see R010 "Universal bypassPermissions".

package/templates/.claude/skills/profile/SKILL.md

@@ -23,7 +23,7 @@ Switch the active plugin set to match a workflow profile, reducing per-spawn ski
 ## Implementation rules
 
 > **.claude/ path handling (CC v2.1.121+)**
-> Direct Write/Edit on `.claude/profiles/.active` and `~/.claude/settings.json` is permitted under `mode: "bypassPermissions"` (CC v2.1.121+, #1101). The legacy `/tmp/*.sh` bypass is deprecated. For CC < v2.1.121, see git history for the legacy pattern.
+> Direct Write/Edit on `.claude/profiles/.active` and `~/.claude/settings.json` is permitted under the `bypassPermissions` permission mode (CC v2.1.121+, #1101). The legacy `/tmp/*.sh` bypass is deprecated. For CC < v2.1.121, see git history for the legacy pattern.
 
 ## Profiles directory
 
@@ -70,10 +70,10 @@ Profile: web-app
   Disable: codex, ralph-wiggum, agent-sdk-dev, ...
 ```
 
-6. Apply changes via direct Edit on `~/.claude/settings.json` (`mode: "bypassPermissions"`, CC v2.1.121+):
+6. Apply changes via direct Edit on `~/.claude/settings.json` (under `bypassPermissions` permission mode, CC v2.1.121+):
    - Read `~/.claude/settings.json`, merge the computed diff into `enabledPlugins` (set enabled plugins to `true`, disabled plugins to `false`), then Write the updated JSON back.
 
-7. Write active marker via direct Write on `.claude/profiles/.active` (`mode: "bypassPermissions"`):
+7. Write active marker via direct Write on `.claude/profiles/.active` (under `bypassPermissions` permission mode):
    - Write the profile `<name>` as plain text content to `.claude/profiles/.active`.
 
 8. Confirm:
@@ -86,7 +86,7 @@ IMPORTANT: Restart this Claude Code session for plugin changes to take effect.
 
 ## Workflow: `/profile reset`
 
-1. Remove `.claude/profiles/.active` marker via direct `Bash: /bin/rm .claude/profiles/.active` (`mode: "bypassPermissions"`)
+1. Remove `.claude/profiles/.active` marker via direct `Bash: /bin/rm .claude/profiles/.active` (under `bypassPermissions` permission mode)
 2. Print: `[Done] Profile marker removed. Full plugin set will be active after restart.`
 3. Note: does NOT revert `~/.claude/settings.json` — user should re-run `/profile load <other>` or manually restore
 

package/templates/.claude/skills/qa-lead-routing/SKILL.md

@@ -9,7 +9,7 @@ context: fork
 
 When this skill spawns a subagent via the Agent tool, the spawned prompt MUST include this directive verbatim (or equivalent):
 
-> 이 스킬이 Agent tool로 서브에이전트를 스폰할 때 mode: "bypassPermissions"를 반드시 포함한다. 서브에이전트는 .claude/ 경로에 직접 Write/Edit/Bash를 사용한다(/tmp 우회 불필요, CC v2.1.121+). See R010.
+> 호환을 위해 Agent 호출에 `mode: "bypassPermissions"`를 전달하십시오. CC 2.1.212 미만에서는 필수이며(호출별 기본값 `acceptEdits`가 에이전트 frontmatter `permissionMode`를 덮어씁니다), 2.1.212+에서는 무시되고 서브에이전트가 부모 세션의 권한 모드를 상속합니다(에이전트 frontmatter `permissionMode`로 조정 가능). 무인 실행 전 유효 모드 확인은 R010 「Universal bypassPermissions」 참조. bypassPermissions 세션에서 서브에이전트는 .claude/ 경로에 직접 Write/Edit/Bash를 사용합니다(/tmp 우회 불필요, CC v2.1.121+).
 
 This directive is preserved inline because Agent-tool prompt synthesis can drop SKILL.md notes; inline mandatory directives survive (#1046 lesson).
 
@@ -54,7 +54,7 @@ quality_analysis   → qa-planner + qa-engineer (parallel)
 full_qa_cycle      → all agents (sequential)
 ```
 
-> **Permission Mode**: When spawning agents via Agent tool, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
+> **Permission Mode**: Pass `mode: "bypassPermissions"` on Agent calls for compatibility: it is required on CC < 2.1.212 (the per-call default, `acceptEdits`, overrides agent frontmatter `permissionMode`) and ignored on 2.1.212+, where subagents inherit the parent session's permission mode (adjustable via agent frontmatter `permissionMode`). Verify the effective mode before unattended runs: see R010 "Universal bypassPermissions".
 
 ### Ontology-RAG Enrichment (R019)
 

package/templates/.claude/skills/release-plan/SKILL.md

@@ -208,4 +208,4 @@ File header format:
 
 ## Permission Mode
 
-When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
+Pass `mode: "bypassPermissions"` on Agent calls for compatibility: it is required on CC < 2.1.212 (the per-call default, `acceptEdits`, overrides agent frontmatter `permissionMode`) and ignored on 2.1.212+, where subagents inherit the parent session's permission mode (adjustable via agent frontmatter `permissionMode`). Verify the effective mode before unattended runs: see R010 "Universal bypassPermissions".

package/templates/.claude/skills/research/SKILL.md

@@ -194,7 +194,7 @@ Convergence expected by round 3. Hard stop at round 30.
 
 ### Tool: Writing artifacts under .claude/outputs/
 
-Under `mode: "bypassPermissions"`, subagents write directly to `.claude/outputs/sessions/` with the Write tool — direct `.claude/**` writes are permitted (CC v2.1.121+, #1101). No `/tmp` staging or script wrapping is needed. Read-only Bash on `.claude/outputs/` (e.g., `cat`, `head`, `wc`) is allowed for verification.
+Under the `bypassPermissions` permission mode, subagents write directly to `.claude/outputs/sessions/` with the Write tool — direct `.claude/**` writes are permitted (CC v2.1.121+, #1101). No `/tmp` staging or script wrapping is needed. Read-only Bash on `.claude/outputs/` (e.g., `cat`, `head`, `wc`) is allowed for verification.
 
 Reference: R006/R010 sensitive-path handling (direct `.claude/**` write under bypassPermissions), #1101.
 
@@ -427,9 +427,9 @@ When running inside an Agent Teams member (not via Skill tool), the research wor
 
 The orchestrator reads this SKILL.md and includes the research instructions directly in the Teams member's prompt. The member then:
 
-1. Executes Phase 1-4 autonomously using its own Agent tool access
-2. Spawns research teams as sub-agents (Teams members CAN spawn sub-agents)
-3. Delivers results via `SendMessage` to the team lead instead of returning to orchestrator
+1. Executes Phase 1-4 autonomously, using its own Agent tool access when its tool set includes Agent (see item 2 otherwise)
+2. Spawns research teams as sub-agents (Teams members can spawn sub-agents only if their tool set includes Agent; otherwise fall back to file-channel handoff relayed by the orchestrator, #1817)
+3. Delivers results via `SendMessage` to the team lead instead of returning to orchestrator when its tool set includes SendMessage; otherwise writes the results to an artifact file and reports the path, which the orchestrator relays (R018 "멤버 도구 부재 시 대체 규약", #1817)
 
 ### Prompt Embedding Pattern
 
@@ -444,6 +444,8 @@ Agent(
 
   Topic: {user's research topic}
   Deliver results via SendMessage to team lead when complete.
+  If SendMessage is not in your tool set, write the results to an artifact
+  file and report its path for the orchestrator to relay.
   """
 )
 ```
@@ -453,7 +455,7 @@ Agent(
 | Aspect | Orchestrator Mode | Teams Mode |
 |--------|------------------|------------|
 | Invocation | `Skill(research)` | Prompt embedding |
-| Result delivery | Return to main conversation | `SendMessage` to team lead |
+| Result delivery | Return to main conversation | `SendMessage` to team lead (if absent: artifact file relayed by orchestrator) |
 | Artifact persistence | Teams member writes artifact | Same |
 | GitHub issue creation | Orchestrator handles | Teams member handles directly |
 | Phase management | Orchestrator manages phases | Member manages phases autonomously |
@@ -478,4 +480,4 @@ Agent(
 | result-aggregation | Team results formatted per aggregation skill |
 | multi-model-verification | Phase 2 uses multi-model verification pattern |
 
-When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
+Pass `mode: "bypassPermissions"` on Agent calls for compatibility: it is required on CC < 2.1.212 (the per-call default, `acceptEdits`, overrides agent frontmatter `permissionMode`) and ignored on 2.1.212+, where subagents inherit the parent session's permission mode (adjustable via agent frontmatter `permissionMode`). Verify the effective mode before unattended runs: see R010 "Universal bypassPermissions".

package/templates/.claude/skills/result-aggregation/SKILL.md

@@ -170,7 +170,7 @@ R006 Artifact Channel Protocol을 소비하는 표준 패턴. 병렬 에이전
 
 ### Tool: Writing artifacts under .claude/outputs/
 
-Under `mode: "bypassPermissions"`, subagents write directly to `.claude/outputs/sessions/` with the Write tool — direct `.claude/**` writes are permitted (CC v2.1.121+, #1101). No `/tmp` staging or script wrapping is needed. Read-only Bash on `.claude/outputs/` (e.g., `cat`, `head`, `wc`) is allowed for verification.
+Under the `bypassPermissions` permission mode, subagents write directly to `.claude/outputs/sessions/` with the Write tool — direct `.claude/**` writes are permitted (CC v2.1.121+, #1101). No `/tmp` staging or script wrapping is needed. Read-only Bash on `.claude/outputs/` (e.g., `cat`, `head`, `wc`) is allowed for verification.
 
 Reference: R006/R010 sensitive-path handling (direct `.claude/**` write under bypassPermissions), #1101.
 

package/templates/.claude/skills/roundtable-debate/SKILL.md

@@ -54,13 +54,13 @@ TeamCreate("roundtable-{topic}")
 
 If your task involves writing artifacts under `.claude/outputs/`, write the file to
 `.claude/outputs/sessions/<date>/<artifact>.md` using the Write tool directly (create the
-directory if needed). Your Agent tool call runs under `mode: "bypassPermissions"`, so direct
+directory if needed). If your session runs under the `bypassPermissions` permission mode, direct
 Write/Edit on `.claude/` is permitted (CC v2.1.121+).
 ```
 
 ### Phase 1: Round 1 — Discussion
 
-모든 독립 분석 공개 후 라운드 1 토론. SendMessage로 peer 의견 교환.
+모든 독립 분석 공개 후 라운드 1 토론. SendMessage로 peer 의견 교환 (멤버 도구에 SendMessage가 없으면 의견을 아티팩트 파일에 쓰고 오케스트레이터가 경로를 중계 — R018 「멤버 도구 부재 시 대체 규약」, #1817).
 
 규칙:
 1. 다른 의견을 기각할 때 명시적 정당화 (3개 근거) 필수

package/templates/.claude/skills/scout/SKILL.md

@@ -105,14 +105,9 @@ Before execution, show the plan:
 
 ### Phase 3: Fit Analysis
 
-> **MUST**: Agent tool 호출 시 반드시 `mode: "bypassPermissions"` 파라미터를 포함해야 한다 (R010 Universal bypassPermissions). CC Agent tool의 기본값은 `acceptEdits`이며, 이는 agent frontmatter의 `permissionMode`를 덮어쓴다. `mode` 누락 시 Bash/WebFetch 권한 프롬프트가 발생하여 비대화형 실행이 중단된다.
->
-> ```
-> ❌ Agent(subagent_type: "general-purpose", prompt: "...")
-> ✓  Agent(subagent_type: "general-purpose", mode: "bypassPermissions", prompt: "...")
-> ```
+> 호환을 위해 Agent 호출에 `mode: "bypassPermissions"`를 전달하십시오. CC 2.1.212 미만에서는 필수이며(호출별 기본값 `acceptEdits`가 에이전트 frontmatter `permissionMode`를 덮어씁니다), 2.1.212+에서는 무시되고 서브에이전트가 부모 세션의 권한 모드를 상속합니다(에이전트 frontmatter `permissionMode`로 조정 가능). 무인 실행 전 유효 모드 확인은 R010 「Universal bypassPermissions」 참조.
 
-Spawn 1 sonnet agent with `mode: "bypassPermissions"` and the following analysis prompt.
+Spawn 1 sonnet agent with the following analysis prompt.
 
 **Inputs**:
 - Fetched content summary (Phase 1)
@@ -163,7 +158,7 @@ Return a structured verdict:
 
 ### Phase 4: Issue Creation
 
-> **NOTE**: Phase 4는 orchestrator가 직접 `gh issue create` (Bash)로 처리한다. 만약 이슈 생성을 Agent(mgr-gitnerd 등)에 위임할 경우, 해당 Agent tool 호출에도 반드시 `mode: "bypassPermissions"`를 포함해야 한다 (R010).
+> **NOTE**: Phase 4는 orchestrator가 직접 `gh issue create` (Bash)로 처리한다. 만약 이슈 생성을 Agent(mgr-gitnerd 등)에 위임할 경우, 권한 모드는 R010 「Universal bypassPermissions」를 따른다.
 
 1. Ensure scout labels exist (defensive, idempotent):
 ```bash

package/templates/.claude/skills/sec-agentshield-wrapper/SKILL.md

@@ -171,4 +171,4 @@ CRG 미연결 시 Grep + Read 조합으로 fallback.
 
 ## Permission Mode
 
-이 스킬에서 Agent 도구를 사용하여 에이전트를 스폰할 경우, 항상 `mode: "bypassPermissions"` 를 전달해야 한다. Agent 도구의 기본값(`acceptEdits`)은 에이전트 frontmatter `permissionMode` 를 덮어쓰므로 무인 실행 중 권한 프롬프트가 발생할 수 있다.
+호환을 위해 Agent 호출에 `mode: "bypassPermissions"`를 전달하십시오. CC 2.1.212 미만에서는 필수이며(호출별 기본값 `acceptEdits`가 에이전트 frontmatter `permissionMode`를 덮어씁니다), 2.1.212+에서는 무시되고 서브에이전트가 부모 세션의 권한 모드를 상속합니다(에이전트 frontmatter `permissionMode`로 조정 가능). 무인 실행 전 유효 모드 확인은 R010 「Universal bypassPermissions」 참조.

package/templates/.claude/skills/secretary-routing/SKILL.md

@@ -9,7 +9,7 @@ context: fork
 
 When this skill spawns a subagent via the Agent tool, the spawned prompt MUST include this directive verbatim (or equivalent):
 
-> 이 스킬이 Agent tool로 서브에이전트를 스폰할 때 mode: "bypassPermissions"를 반드시 포함한다. 서브에이전트는 .claude/ 경로에 직접 Write/Edit/Bash를 사용한다(/tmp 우회 불필요, CC v2.1.121+). See R010.
+> 호환을 위해 Agent 호출에 `mode: "bypassPermissions"`를 전달하십시오. CC 2.1.212 미만에서는 필수이며(호출별 기본값 `acceptEdits`가 에이전트 frontmatter `permissionMode`를 덮어씁니다), 2.1.212+에서는 무시되고 서브에이전트가 부모 세션의 권한 모드를 상속합니다(에이전트 frontmatter `permissionMode`로 조정 가능). 무인 실행 전 유효 모드 확인은 R010 「Universal bypassPermissions」 참조. bypassPermissions 세션에서 서브에이전트는 .claude/ 경로에 직접 Write/Edit/Bash를 사용합니다(/tmp 우회 불필요, CC v2.1.121+).
 
 This directive is preserved inline because Agent-tool prompt synthesis can drop SKILL.md notes; inline mandatory directives survive (#1046 lesson).
 
@@ -105,7 +105,7 @@ If the selected agent has `soul: true` in frontmatter, read and prepend `.claude
 5. Report result to user
 ```
 
-> **Permission Mode**: When spawning agents via Agent tool, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
+> **Permission Mode**: Pass `mode: "bypassPermissions"` on Agent calls for compatibility: it is required on CC < 2.1.212 (the per-call default, `acceptEdits`, overrides agent frontmatter `permissionMode`) and ignored on 2.1.212+, where subagents inherit the parent session's permission mode (adjustable via agent frontmatter `permissionMode`). Verify the effective mode before unattended runs: see R010 "Universal bypassPermissions".
 
 ### 2. Batch/Parallel Task Routing
 

package/templates/.claude/skills/skill-extractor/SKILL.md

@@ -208,7 +208,7 @@ feedback memory에 누적된 실패 패턴을 분석하여 영구 구조(스킬
 
 ### Tool: Writing artifacts under .claude/outputs/
 
-Under `mode: "bypassPermissions"`, subagents write directly to `.claude/outputs/sessions/` with the Write tool — direct `.claude/**` writes are permitted (CC v2.1.121+, #1101). No `/tmp` staging or script wrapping is needed. Read-only Bash on `.claude/outputs/` (e.g., `cat`, `head`, `wc`) is allowed for verification.
+Under the `bypassPermissions` permission mode, subagents write directly to `.claude/outputs/sessions/` with the Write tool — direct `.claude/**` writes are permitted (CC v2.1.121+, #1101). No `/tmp` staging or script wrapping is needed. Read-only Bash on `.claude/outputs/` (e.g., `cat`, `head`, `wc`) is allowed for verification.
 
 Reference: R006/R010 sensitive-path handling (direct `.claude/**` write under bypassPermissions), #1101.
 

package/templates/.claude/skills/structured-dev-cycle/SKILL.md

@@ -181,7 +181,7 @@ rm -f /tmp/.claude-dev-stage-$PPID                   # Clear (disable blocking)
 
 ## Permission Mode
 
-When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
+Pass `mode: "bypassPermissions"` on Agent calls for compatibility: it is required on CC < 2.1.212 (the per-call default, `acceptEdits`, overrides agent frontmatter `permissionMode`) and ignored on 2.1.212+, where subagents inherit the parent session's permission mode (adjustable via agent frontmatter `permissionMode`). Verify the effective mode before unattended runs: see R010 "Universal bypassPermissions".
 
 ## Display Format
 

package/templates/.claude/skills/task-decomposition/SKILL.md

@@ -230,7 +230,7 @@ When granularity validation triggers a split, update the DAG spec:
 
 ## Permission Mode
 
-When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
+Pass `mode: "bypassPermissions"` on Agent calls for compatibility: it is required on CC < 2.1.212 (the per-call default, `acceptEdits`, overrides agent frontmatter `permissionMode`) and ignored on 2.1.212+, where subagents inherit the parent session's permission mode (adjustable via agent frontmatter `permissionMode`). Verify the effective mode before unattended runs: see R010 "Universal bypassPermissions".
 
 ## Integration
 

package/templates/.claude/skills/worker-reviewer-pipeline/SKILL.md

@@ -91,7 +91,11 @@ When Agent Teams is enabled, the pipeline SHOULD use Agent Teams:
 TeamCreate("review-pipeline")
   Worker (team member) ←→ Reviewer (team member)
   SendMessage for feedback exchange
+    (if a member lacks SendMessage: artifact files relayed by the
+     orchestrator, R018 "멤버 도구 부재 시 대체 규약", #1817)
   Shared TaskList for tracking issues
+    (if TaskList is absent — not registered by default, R002: follow
+     R018 "Task 도구 부재 시 대체 규약", #1582)
 ```
 
 When Agent Teams is NOT available, falls back to sequential Agent tool calls:
@@ -164,4 +168,4 @@ config: {max_iterations: 1, quality_gate: majority_pass}
 - Nested pipelines not supported (use dag-orchestration for complex flows)
 - Pipeline does not auto-commit; orchestrator decides post-pipeline actions
 
-When spawning agents via the Agent tool during this skill's execution, always pass `mode: "bypassPermissions"`. The Agent tool default (`acceptEdits`) overrides agent frontmatter `permissionMode`, causing permission prompts during unattended execution.
+Pass `mode: "bypassPermissions"` on Agent calls for compatibility: it is required on CC < 2.1.212 (the per-call default, `acceptEdits`, overrides agent frontmatter `permissionMode`) and ignored on 2.1.212+, where subagents inherit the parent session's permission mode (adjustable via agent frontmatter `permissionMode`). Verify the effective mode before unattended runs: see R010 "Universal bypassPermissions".

package/templates/guides/claude-code/15-version-compatibility.md

@@ -417,7 +417,7 @@ Rewind 메뉴에 이전 턴까지의 컨텍스트를 압축하되 최근 대화
 
 `/bg` 또는 `←←`로 실행된 백그라운드 에이전트가 기본값으로 되돌아가지 않고 현재 세션의 권한 모드를 유지합니다.
 
-**oh-my-customcode 연관**: R010 `bypassPermissions` 맥락에서 중요한 개선. 이전에는 `/bg`로 에이전트를 분리하면 `bypassPermissions` 설정이 유실되어 unattended 실행 중 권한 프롬프트가 발생할 수 있었습니다. **v2.1.141+에서는 `/bg` 플로우에서 권한 모드 드롭이 더 이상 발생하지 않음** — R010 Universal bypassPermissions 규칙은 Agent tool 호출에 여전히 필요하지만, `/bg` 전환 시 추가 workaround 불필요.
+**oh-my-customcode 연관**: R010 `bypassPermissions` 맥락에서 중요한 개선. 이전에는 `/bg`로 에이전트를 분리하면 `bypassPermissions` 설정이 유실되어 unattended 실행 중 권한 프롬프트가 발생할 수 있었습니다. **v2.1.141+에서는 `/bg` 플로우에서 권한 모드 드롭이 더 이상 발생하지 않음** — R010 Universal bypassPermissions 규칙에 따라 Agent tool 호출의 `mode: "bypassPermissions"`는 CC 2.1.212 미만에서 필요하고 2.1.212+에서는 무시되지만 호환을 위해 계속 전달하며, `/bg` 전환 시 추가 workaround 불필요.
 
 ### `claude agents`: 백그라운드 셸 잔류 에이전트 상태 수정
 

package/templates/guides/deep-plan/phases.md

@@ -18,7 +18,7 @@ Phase 1: Discovery Research
 ### Execution Modes
 
 - **Orchestrator mode**: Delegates to `/research` skill via `Skill(research, args="<topic>")`.
-- **Teams mode**: Executes the research workflow inline — the member spawns research teams directly as sub-agents. Does NOT use `Skill(research)` because fork context blocks sub-agent spawning in Teams mode.
+- **Teams mode**: Executes the research workflow inline — the member spawns research teams directly as sub-agents when its tool set includes Agent (otherwise it reports the needed spawns and the orchestrator spawns them, R018). Does NOT use `Skill(research)` because fork context blocks sub-agent spawning in Teams mode.
 
 The executor waits for completion before proceeding to Phase 2.
 
@@ -126,7 +126,7 @@ Phase 1 research artifact is persisted by the `/research` skill.
 
 Phase 3 verification report path: `.claude/outputs/sessions/{YYYY-MM-DD}/deep-plan-{HHmmss}.md`
 
-**Artifact write protocol**: Under `mode: "bypassPermissions"`, write artifacts under `.claude/outputs/` directly with the Write tool (create the dated directory first if needed). Direct `Write`/`Edit`/`Bash` on `.claude/` is permitted since CC v2.1.121 — no `/tmp/*.sh` wrapping is needed (R006/R010). Only catastrophic shell operations (`rm -rf /`) remain blocked by independent safety guards.
+**Artifact write protocol**: Under `bypassPermissions` (CC < 2.1.212: pass `mode: "bypassPermissions"` per call; CC >= 2.1.212: `mode` is ignored and the parent session's mode is inherited — verify the effective mode per R010 「Universal bypassPermissions」), write artifacts under `.claude/outputs/` directly with the Write tool (create the dated directory first if needed). Direct `Write`/`Edit`/`Bash` on `.claude/` is permitted since CC v2.1.121 — no `/tmp/*.sh` wrapping is needed (R006/R010). Only catastrophic shell operations (`rm -rf /`) remain blocked by independent safety guards.
 
 When spawning the final synthesis agent to write this artifact, include these instructions verbatim in the agent prompt:
 
@@ -136,7 +136,7 @@ When spawning the final synthesis agent to write this artifact, include these in
 Write the artifact under `.claude/outputs/` directly with the Write tool:
 1. Ensure the dated directory exists: .claude/outputs/sessions/<date>/
 2. Write .claude/outputs/sessions/<date>/deep-plan-<HHmmss>.md with the Write tool.
-This Agent tool call runs with mode: "bypassPermissions", under which direct Write/Edit/Bash on `.claude/` is permitted (CC v2.1.121+) — no /tmp/*.sh wrapping needed.
+This Agent call needs `mode: "bypassPermissions"` on CC < 2.1.212 and inherits the parent session's mode on CC >= 2.1.212; under bypassPermissions, direct Write/Edit/Bash on `.claude/` is permitted (CC v2.1.121+) — no /tmp/*.sh wrapping needed.
 ```
 
 Artifact metadata header:
@@ -196,12 +196,12 @@ After PASS verdict:
 
 ## Teams Mode (Agent Teams)
 
-When running inside an Agent Teams member (not via Skill tool), the deep-plan workflow operates identically with these adaptations:
+When running inside an Agent Teams member (not via Skill tool), the deep-plan workflow operates identically with these adaptations. Sub-agent spawning and `SendMessage` delivery below apply only when the member's tool set includes Agent and SendMessage respectively; when either is absent, follow R018 "멤버 도구 부재 시 대체 규약" — file channels and orchestrator relay (#1817):
 
-1. Phase 1: Executes research workflow inline (not via `Skill(research)`) — spawns 10 research teams as sub-agents
+1. Phase 1: Executes research workflow inline (not via `Skill(research)`) — spawns 10 research teams as sub-agents (requires Agent)
 2. Phase 2: Uses EnterPlanMode/ExitPlanMode and Explore agents normally
-3. Phase 3: Spawns 3 verification teams as sub-agents
-4. Delivers final verified plan via `SendMessage` to team lead
+3. Phase 3: Spawns 3 verification teams as sub-agents (requires Agent)
+4. Delivers final verified plan via `SendMessage` to team lead (if SendMessage is absent: artifact file relayed by orchestrator)
 
 ### Prompt Embedding Pattern
 
@@ -219,6 +219,8 @@ Agent(
 
   Topic: {user's planning topic}
   Deliver verified plan via SendMessage to team lead when complete.
+  If SendMessage is not in your tool set, write the plan to an artifact
+  file and report its path for the orchestrator to relay.
   """
 )
 ```
@@ -229,8 +231,8 @@ Agent(
 |--------|------------------|------------|
 | Invocation | `Skill(deep-plan)` | Prompt embedding |
 | Phase 1 research | `Skill(research)` | Inline execution |
-| Result delivery | Return to main conversation | `SendMessage` to team lead |
-| Plan approval | User via ExitPlanMode | Team lead via SendMessage |
+| Result delivery | Return to main conversation | `SendMessage` to team lead (if absent: artifact file relayed by orchestrator) |
+| Plan approval | User via ExitPlanMode | Team lead via SendMessage (if absent: via orchestrator-relayed artifact file) |
 
 ## Fallback Behavior
 

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

@@ -43,6 +43,7 @@ Deep Insight가 제안하는 4계층 구조는 oh-my-customcode에 이미 구현
 메인 대화 → Write(".claude/agents/new.md", content)  ← R010 위반
 
 # 교정: Executor에게 위임
+# mode: CC < 2.1.212에서 필요; 2.1.212+에서는 무시되고 부모 세션 모드 또는 에이전트 frontmatter `permissionMode`(mgr-creator: bypassPermissions)가 적용됨
 메인 대화 → Agent(mgr-creator, mode: "bypassPermissions") → Write(".claude/agents/new.md", content)
 ```
 
@@ -167,7 +168,7 @@ opt-in: hard-enforce (filter 모드, --hard-enforce 플래그) — 명시적 사
 | R005 (Capability-aware Tool Scheduling) | ouroboros PR #353 capability graph 패턴. action-validator Capability Hints와 직접 연동 |
 | R006 (Agent Design) | `tools`, `domain`, `limitations`, `isolation` 필드가 하네스 행동 제어의 선언 계층 |
 | R009 (Parallel Execution) | Executor 병렬화 원칙. adaptive-harness `--scan`의 병렬 Glob/Grep 호출 근거 |
-| R010 (Orchestrator Coordination) | Coordinator 계층의 파일 수정 금지 + Universal bypassPermissions 강제 |
+| R010 (Orchestrator Coordination) | Coordinator 계층의 파일 수정 금지 + CC < 2.1.212에서는 호출별 `mode: "bypassPermissions"` 필요, 2.1.212+에서는 부모 세션 권한 모드 상속(R010 Universal bypassPermissions 절) |
 | R013 (Ecomode) | Context budget thresholds가 Context Engineering 섹션의 per-agent 예산 할당 기반 |
 | R017 (Sync Verification) | mgr-sauron이 Supervisor 계층 역할. 하네스 구조 변경 후 R017 검증 필수 |
 | R018 (Agent Teams) | 3+ 에이전트 또는 review cycle → Agent Teams. 하네스 설계 검토에도 적용 |

package/templates/guides/professor-triage/README.md

@@ -38,5 +38,5 @@ The SKILL.md is intentionally thin — it carries only the workflow contract and
 ## Key Design Decisions
 
 - **Phase 4 uses `general-purpose` (NOT `arch-documenter`)**: `arch-documenter` has `disallowedTools: [Bash]` — cannot run `gh` (comment posting) or shell scripts these phases require. `general-purpose` has Bash access. See #1043 and R010 Known Limitations.
-- **Artifact write**: `.claude/outputs/` writes use the Write tool directly under `mode: "bypassPermissions"` — direct Write/Edit/Bash on `.claude/` is permitted since CC v2.1.121 (R006/R010); no `/tmp/*.sh` wrapping needed. See phases.md Phase 4E.
+- **Artifact write**: `.claude/outputs/` writes use the Write tool directly under `bypassPermissions` (CC < 2.1.212: pass `mode: "bypassPermissions"` per call; CC >= 2.1.212: `mode` is ignored, parent session mode inherited; verify per R010 「Universal bypassPermissions」) — direct Write/Edit/Bash on `.claude/` is permitted since CC v2.1.121 (R006/R010); no `/tmp/*.sh` wrapping needed. See phases.md Phase 4E.
 - **Parallelization**: Phase 4A + 4B parallel; Phase 4C after both; Phase 4D + 4E parallel; Phase 4F verification gate.

package/templates/guides/professor-triage/phases.md

@@ -229,7 +229,7 @@ _`/professor-triage` v2.3.0에 의해 현재 코드베이스 대비 분석됨
 
 Delegate to general-purpose. Path: `.claude/outputs/sessions/YYYY-MM-DD/professor-triage-HHmmss.md`
 
-**Artifact write**: Under `mode: "bypassPermissions"`, write the artifact directly with the Write tool (create the dated directory first if needed). Direct Write/Edit/Bash on `.claude/outputs/` is permitted since CC v2.1.121 — no `/tmp/*.sh` wrapping is needed (R006/R010). Only catastrophic shell operations (`rm -rf /`) remain blocked by independent safety guards.
+**Artifact write**: Under `bypassPermissions` (CC < 2.1.212: pass `mode: "bypassPermissions"` per call; CC >= 2.1.212: `mode` is ignored, parent session mode inherited; verify per R010 「Universal bypassPermissions」), write the artifact directly with the Write tool (create the dated directory first if needed). Direct Write/Edit/Bash on `.claude/outputs/` is permitted since CC v2.1.121 — no `/tmp/*.sh` wrapping is needed (R006/R010). Only catastrophic shell operations (`rm -rf /`) remain blocked by independent safety guards.
 
 Artifact template:
 

package/templates/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.1.102",
+  "version": "1.1.103",
   "lastUpdated": "2026-09-03",
   "omcustomMinClaudeCode": "2.1.121",
   "omcustomMinClaudeCodeReason": "Sensitive-path direct Write/Edit on .claude/** under bypassPermissions (R010 deprecation, #1101)",

package/templates/workflows/auto-dev.yaml

@@ -492,7 +492,7 @@ steps:
       - Parallel execution per R009 (max 4 concurrent, respect dependencies)
       - Issues whose prerequisites failed in-run MUST be skipped (log reason)
       - No direct orchestrator writes (R010)
-      - All Agent tool calls MUST pass mode: "bypassPermissions" to prevent permission prompts during unattended execution
+      - On CC < 2.1.212 Agent tool calls need `mode: "bypassPermissions"` (the per-call default acceptEdits overrides frontmatter `permissionMode`), so pass it for compatibility. On CC >= 2.1.212 `mode` is ignored and subagents inherit the parent session's permission mode (frontmatter `permissionMode` may adjust it). Verify the effective mode before unattended execution per R010 「Universal bypassPermissions」 (pre-triage)
       - Mid-run scope additions (a new issue added via user interrupt AFTER implement began) MUST re-enter the verify-build gate before release — do NOT let a late-added scope item ride to release on a prior verify-build pass. Critical for code changes; benign for docs-only (#1301).
       - When an implement-stage delegation edits rule/skill/guide TEXT, the orchestrator MUST NOT author the final committed wording — the subagent writes it directly from the issue body (`gh issue view <N> --json body`); the delegation prompt supplies pointers, insertion anchors, constraints, verbatim tool-output quotations, and measured facts only
         (R010 「출처 인용과 인접 문구 점검도 같은 규율」 보강 2항목, #1698 #1). The orchestrator's own requirement/scope summary counts as final wording too — copy the issue's proposal sentence from `gh issue view` output verbatim, and tag any orchestrator paraphrase "[요약 — 원문 우선]"
@@ -803,7 +803,7 @@ steps:
 
       ## Sensitive Path Handling (CC v2.1.121+)
 
-      Direct Write/Edit/Bash on `.claude/**` is permitted under `mode: "bypassPermissions"` as of CC v2.1.121 (#1101). The legacy `/tmp/*.sh` bypass is no longer required. Structural changes (new agents/skills) still go through mgr-creator with R017 verification.
+      Direct Write/Edit/Bash on `.claude/**` is permitted under the `bypassPermissions` permission mode as of CC v2.1.121 (#1101). The legacy `/tmp/*.sh` bypass is no longer required. Structural changes (new agents/skills) still go through mgr-creator with R017 verification.
 
       For CC < v2.1.121 see git history for the legacy bypass pattern.