oh-my-customcode 1.1.17 → 1.1.19

package/dist/cli/index.js

@@ -241,7 +241,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "1.1.17",
+    version: "1.1.19",
     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: "1.1.17",
+  version: "1.1.19",
   description: "Batteries-included agent harness for Claude Code",
   type: "module",
   bin: {

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "1.1.17",
+  "version": "1.1.19",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/rules/MAY-optimization.md

@@ -26,6 +26,8 @@
 
 > **v2.1.206+**: `/doctor`에 checked-in CLAUDE.md에서 코드베이스로부터 파생 가능한 내용을 잘라내도록 제안하는 체크가 추가되었습니다 — R005 "Context Optimization via HTML Comments"의 컨텍스트 절감 원칙과 정합(모델 불필요 메타데이터 축소).
 
+> **v2.1.208+**: Fixed several tool-reliability bugs: env vars like `CLAUDE_CODE_MAX_OUTPUT_TOKENS` silently used only the mantissa of scientific-notation values (`1e6` became `1`); Edit now succeeds on a file modified after being read, as long as the target text still matches uniquely; Read no longer misreports empty files as "shorter than offset"; Grep no longer silently returns "No files found" for invalid regex, no longer under-reports paginated count-mode totals; and Glob no longer crashes on a null byte in pattern/path/cwd.
+
 ### Capability-Aware Tool Scheduling
 
 When dispatching parallel tool calls, consider per-tool capabilities to optimize scheduling:

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

@@ -15,6 +15,8 @@ model: sonnet              # sonnet | opus | haiku | opusplan (or full ID: claud
 tools: [Read, Write, ...]  # Allowed tools
 ```
 
+> **v2.1.208+**: The Agent tool no longer launches with no tools when a subagent's `tools:` list resolves to nothing — it now returns a clear error naming the unrecognized entries, catching frontmatter `tools:` typos that previously failed silently.
+
 ### Model Aliases
 
 | Alias | Full ID | Use Case |

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

@@ -344,12 +344,16 @@ 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.
+-->
 
 > **v2.1.200+**: 백그라운드 세션/에이전트 견고성이 추가로 강화되었습니다 — sleep/wake 후 또는 stalled 세션 재개 시 mid-turn으로 조용히 멈추던 문제, stall respawn 후 Esc로 취소한 turn을 재실행하던 문제, 크래시가 남긴 stale `daemon.lock`(OS가 PID를 재사용)으로 백그라운드 에이전트가 다시 시작되지 않던 문제, 재설치된 구버전 빌드가 daemon을 탈취하던 문제(빌드 최신성은 이제 버전의 embedded build timestamp로 판정), 그리고 roster 일시 corruption이 orphan cleanup을 영구 비활성화하던 문제·구버전 바이너리가 신버전이 기록한 필드를 보존하지 못하던 문제·daemon 재시작 중 socket auth token이 제거되던 문제를 수정했습니다. v2.1.195~199 백그라운드-에이전트 lifecycle 견고성 체인의 연장입니다. `mode: "bypassPermissions"`는 모든 Agent tool 호출에 여전히 필수입니다.
 
+> **v2.1.208+**: Added `CLAUDE_CODE_PROCESS_WRAPPER` — the background service and agent view now honor a corporate launcher by routing every Claude Code self-spawn through a required wrapper executable. Also fixed: replies typed to a background agent being lost when delivery fails (now saved and delivered on session restart), background-session attach failing permanently ("Couldn't start the background daemon") after an update replaced the binary a running session was launched from, and an older daemon no longer silently restarting workers spawned by a newer version onto the older binary. Extends the v2.1.195~200 background-agent lifecycle robustness chain. `mode: "bypassPermissions"` remains required on every Agent tool call.
+
+> **v2.1.209+**: Fixed `/model` and other dialogs being blocked in `claude agents` background sessions (reverts an overly broad guard). Continuation of the background-agent lifecycle chain above (cf. v2.1.208). `mode: "bypassPermissions"` remains required.
+
 ## Agent Capability Pre-Check
 
 Before delegating a task to a subagent, MUST verify the target agent's tool capabilities against the task requirements. Failure to pre-check causes round-trip waste (delegation → failure → re-delegation).

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

@@ -45,13 +45,13 @@ On insufficient permission: do not attempt, notify user, suggest alternative.
 
 Use a `"*"` deny rule in `settings.json` to enforce a deny-by-default posture, then add specific allow rules. Complements the Tier-based policy above — settings.json deny rules are evaluated by the CC platform, independent of the advisory tier table.
 
-> **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.
+> **v2.1.208+**: Permission rule matchers (deny/ask rules) are now compiled once and cached, fixing multi-second per-turn slowdowns in sessions with many rules. Complements the deny-by-default posture above — a large deny/allow rule set no longer costs per-turn latency.
 
 <!-- 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. -->
 
 <!-- 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.
+<!-- ARCHIVED CC version note (historical): 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. -->
 
 <!-- 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. -->
 
@@ -59,7 +59,9 @@ Use a `"*"` deny rule in `settings.json` to enforce a deny-by-default posture, t
 
 <!-- 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).
+<!-- ARCHIVED CC version note (historical): 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. -->
+
+<!-- ARCHIVED CC version note (historical): 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). -->
 
 > **v2.1.200+**: `default` permission mode가 CLI·`--help`·VS Code·JetBrains 전반에서 "Manual"로 표기되도록 변경되었습니다 — `--permission-mode manual`과 `"defaultMode": "manual"`이 기존 `default`와 병행 허용됩니다(동일 동작, 라벨만 변경). 위 tier 표의 `default` 모드는 그대로 유효하며 UI 표기만 "Manual"로 노출됩니다(cross-ref R006 Permission Mode Guidance). 또한 `AskUserQuestion` 다이얼로그가 기본적으로 auto-continue하지 않도록 변경되어(이전에는 idle 시 자동 진행), idle timeout은 `/config`로 opt-in해야 합니다 — **자율/비대화 흐름(FSD 등)에서 AskUserQuestion 호출은 이제 사용자 응답까지 블록되므로, 무인 실행 중 질문 도구 사용을 지양하고 best-judgment로 진행하는 R015 directive persistence와 정합**. 그리고 `.claude.json`의 `disabledMcpServers`/`enabledMcpServers`가 non-array 값일 때 발생하던 시작 크래시가 수정되었습니다(Tier-6 MCP).
 

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

@@ -27,6 +27,8 @@ The following git commands have caused working tree loss in past sessions (#1146
 
 > **v2.1.183+**: Auto mode now BLOCKS destructive git commands at the platform level — `git reset --hard`, `git checkout -- .`, `git clean -fd`, and `git stash drop` are blocked when you did not ask to discard local work; `git commit --amend` is blocked when the commit was not made by the agent this session; and `terraform destroy` / `pulumi destroy` / `cdk destroy` are blocked unless you asked for the specific stack. This is the PLATFORM-level complement to this section's (advisory) per-invocation approval requirement and the Pre-Delegation Blast-Radius Enumeration below: the model still enumerates discard targets and requests approval (model-level), and CC now also hard-blocks the destructive command itself in auto mode (platform-level) — defense-in-depth. The advisory approval requirement remains because the platform block gates the COMMAND, not the blast-radius enumeration the user needs for an informed decision.
 
+> **v2.1.208+**: Catastrophic removals (e.g. `rm -rf ~`) wrapped in `$(…)`/backticks/`<(…)` now trigger the same prompt as the plain form in `--dangerously-skip-permissions` and auto mode — closes a subshell-obfuscation gap in the v2.1.183 platform-level destructive-command block above.
+
 ### Pre-Delegation Blast-Radius Enumeration
 
 > Origin: #1307 찐빠 #1 (High) — user chose "discard local changes and pull", and `git reset --hard origin/develop` was delegated immediately → user rejected (interrupt). The blast radius — that "discard local changes" included 18 files of *intended* uncommitted work (rule edits, new skills, new guides), not just a version downgrade — was never enumerated for the user.

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

@@ -27,14 +27,16 @@ Format: `─── [Spawn] {subagent_type}:{model} | {description} ───`
 
 <!-- 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.
+<!-- ARCHIVED CC version note (historical): 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. -->
 
-> **v2.1.196+**: 여러 병렬 요청이 사용량 한도에 도달하는 순간 rate-limit 경고가 깜빡이며 꺼지고 rate-limit telemetry가 과다 집계되던 문제를 수정. R012 관측성의 rate-limit 계측 정확도 개선입니다.
+<!-- ARCHIVED CC version note (historical): v2.1.196+: 여러 병렬 요청이 사용량 한도에 도달하는 순간 rate-limit 경고가 깜빡이며 꺼지고 rate-limit telemetry가 과다 집계되던 문제를 수정. R012 관측성의 rate-limit 계측 정확도 개선입니다. -->
 
 > **v2.1.198+**: `claude agents`에 background agent notifications가 추가되어, 입력이 필요하거나 완료된 세션이 `Notification` hook을 발화합니다(`agent_needs_input` / `agent_completed`). R012 관측성을 백그라운드 subagent 상태 알림까지 확장 — HUD 이벤트 채널과 결합해 백그라운드 위임 작업의 대기/완료 상태를 놓치지 않게 합니다.
 
 > **v2.1.202+**: workflow-spawned agent 텔레메트리에 `workflow.run_id`/`workflow.name` OTel 속성이 추가되어 workflow run 활동을 OTel 데이터로 재구성할 수 있습니다. R012 관측성 확장(monitoring-setup 스킬).
 
+> **v2.1.208+**: Fixed `/release-notes` "Show all" injecting the entire changelog into the model's context (cross-ref R013 context budget). Fixed the context window (and auto-compact indicator) briefly resetting to 200k after CLI auto-update, causing a false "100% context used" on resumed long-context sessions — relevant to the CTX% statusline segment below. Completed background agents now stay listed in `/tasks` until cleanup instead of vanishing on completion — extends the v2.1.198 background-notification observability above.
+
 <!-- DETAIL: HUD Events full spec
 ### When to Display: Multi-step tasks, parallel execution, long-running operations. Skip for single brief operations.
 ### Parallel Display:

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

@@ -109,10 +109,10 @@ Build dependency graph:
 Count skills with context: fork in frontmatter:
   grep "context: fork" .claude/skills/*/SKILL.md
 
-  If count > 10:
-    ERROR: "Context fork cap exceeded: {count}/10"
+  If count > 12:
+    ERROR: "Context fork cap exceeded: {count}/12"
   If count >= 8:
-    WARN: "Context fork usage high: {count}/10 — only {10-count} slots remaining"
+    WARN: "Context fork usage high: {count}/12 — only {12-count} slots remaining"
 ```
 
 All structural lints are **advisory** (WARN level) except circular dependencies and fork cap exceeded (ERROR level — should block commit).

package/templates/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.1.17",
+  "version": "1.1.19",
   "lastUpdated": "2026-07-14T00:00:00.000Z",
   "omcustomMinClaudeCode": "2.1.121",
   "omcustomMinClaudeCodeReason": "Sensitive-path direct Write/Edit on .claude/** under bypassPermissions (R010 deprecation, #1101)",