oh-my-customcode - npm Package Compare versions

Comparing version 1.0.14 to 1.0.15

package.json

@@ -6,3 +6,3 @@ {
   ],
-  "version": "1.0.14",
+  "version": "1.0.15",
   "description": "Batteries-included agent harness for Claude Code",
@@ -9,0 +9,0 @@ "type": "module",

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

@@ -17,2 +17,4 @@ # [MAY] Optimization Guide
 
+> **BSD sed `\?` 미지원 (#1413)**: macOS BSD sed는 `\?`(optional 메타문자, GNU 확장)를 해석하지 않아 `sed 's|https\?://||'` 치환이 무음 실패한다. URL 도메인 추출 등은 `cut -d'/' -f3` 같은 POSIX 호환 수단을 사용한다.
+
 > **Sandbox/container tool gaps (#1401 찐빠 #4)**: `curl`, `wget`, `nc` 등 공통 CLI 도구는 샌드박스·컨테이너 환경에서 미설치일 수 있다. HTTP 요청에는 `WebFetch` 도구를 우선 사용하고, CLI 도구 사용 전 `command -v <tool>` 으로 가용성을 사전 확인한다.
@@ -19,0 +21,0 @@

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

@@ -49,2 +49,4 @@ # [MUST] Agent Design Rules
 
+> **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.
+
 ### Safe Mode & Bundled Skill Control (CC v2.1.169+)
@@ -51,0 +53,0 @@

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

@@ -381,4 +381,6 @@ # [MUST] Agent Teams Rules (Conditional)
 
+> **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
 
 Keep per-member delegation prompts under ~5000 tokens and within a single domain. Oversized or multi-domain prompts risk malformed-parsing truncation in the CC platform (see R009 giant-prompt heuristic and `feedback_agent_malformed_parsing.md`). Large multi-file delegations should be decomposed and split across multiple members or standalone Agents.

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

@@ -328,2 +328,6 @@ # [MUST] Orchestrator Coordination Rules
 
+> **v2.1.186+**: `!` bash commands now trigger Claude to respond to the output automatically (set `"respondToBashCommands": false` to keep the prior context-only behavior). Also fixed Esc/Ctrl+C not responding while background agents run after the main turn ends. `mode: "bypassPermissions"` on every Agent tool call remains required.
+
+> **v2.1.187+**: Fixed subagent depth tracking — resumed subagents restore their original spawn depth, and forked subagents count toward the depth cap. Also fixed background jobs stuck in "working" indefinitely when an agent ended a turn without structured output, and leaked agent worktree registrations are now auto-cleaned. Reinforces the sole-orchestrator design's depth accounting (cf. v2.1.172 5-level nesting note). `mode: "bypassPermissions"` remains required.
+
 ## Agent Capability Pre-Check
@@ -330,0 +334,0 @@

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

@@ -52,2 +52,6 @@ # [MUST] Permission Rules
 
+> **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.
+
 ## Agent Tool Permission Mode
@@ -54,0 +58,0 @@

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

@@ -101,2 +101,4 @@ # [MUST] Safety Rules
 
+> **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.
+
 ## Required Before Destructive Operations
@@ -103,0 +105,0 @@

templates/.claude/skills/claude-native/SKILL.md

@@ -93,3 +93,3 @@ ---
 
-## Release Summary
+## 릴리즈 요약
 
@@ -100,16 +100,16 @@ {release_notes_body — truncated to first 2000 chars if too long}
 
-## Action Items
+## 액션 아이템
 
-- [ ] Review release notes for impact on oh-my-customcode
-- [ ] Update agent definitions if new Claude Code features affect agents
-- [ ] Test compatibility with current oh-my-customcode version
-- [ ] Update CLAUDE.md if new capabilities are relevant
+- [ ] oh-my-customcode 영향도 관점에서 릴리즈 노트 검토
+- [ ] 새 Claude Code 기능이 에이전트에 영향을 주면 에이전트 정의 갱신
+- [ ] 현재 oh-my-customcode 버전과의 호환성 테스트
+- [ ] 새 기능이 관련되면 CLAUDE.md 갱신
 
 ---
 
-_This issue was auto-created by the cc-release-monitor workflow (claude-native skill)._
+_이 이슈는 cc-release-monitor 워크플로우(claude-native 스킬)가 자동 생성했습니다._
 ```
 
 **Notes:**
-- If `body` from the release is empty, use `_No release notes provided._`
+- If `body` from the release is empty, use `_릴리즈 노트가 제공되지 않았습니다._`
 - Truncate release body at 2000 characters and append `... (truncated)` if needed
@@ -116,0 +116,0 @@ - The `automated` and `claude-code-release` labels must exist in the repository; create them if missing:

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

@@ -57,3 +57,3 @@ ---
 ```bash
-DOMAIN=$(echo "$URL" | sed 's|https\?://||' | cut -d'/' -f1)
+DOMAIN=$(echo "$URL" | cut -d'/' -f3)
 gh issue list --state all --label "scout:internalize,scout:integrate,scout:skip" \
@@ -60,0 +60,0 @@ --json number,title,body --jq ".[] | select(.body | contains(\"$DOMAIN\"))" 2>/dev/null

templates/.github/workflows/cc-release-monitor.yml

@@ -125,3 +125,3 @@ name: cc-release-monitor
               if not body_raw:
-                  release_summary = "_No release notes provided._"
+                  release_summary = "_릴리즈 노트가 제공되지 않았습니다._"
               elif len(body_raw) > MAX_BODY:
@@ -139,3 +139,3 @@ release_summary = body_raw[:MAX_BODY] + "... (truncated)"
 
-                  ## Release Summary
+                  ## 릴리즈 요약
 
@@ -146,12 +146,12 @@ {release_summary}
 
-                  ## Action Items
+                  ## 액션 아이템
 
-                  - [ ] Review release notes for impact on oh-my-customcode
-                  - [ ] Update agent definitions if new Claude Code features affect agents
-                  - [ ] Test compatibility with current oh-my-customcode version
-                  - [ ] Update CLAUDE.md if new capabilities are relevant
+                  - [ ] oh-my-customcode 영향도 관점에서 릴리즈 노트 검토
+                  - [ ] 새 Claude Code 기능이 에이전트에 영향을 주면 에이전트 정의 갱신
+                  - [ ] 현재 oh-my-customcode 버전과의 호환성 테스트
+                  - [ ] 새 기능이 관련되면 CLAUDE.md 갱신
 
                   ---
 
-                  _This issue was auto-created by the cc-release-monitor GitHub Actions workflow._\
+                  _이 이슈는 cc-release-monitor GitHub Actions 워크플로우가 자동 생성했습니다._\
               """)
@@ -158,0 +158,0 @@

templates/manifest.json

 {
-  "version": "1.0.14",
+  "version": "1.0.15",
   "lastUpdated": "2026-05-20T00:00:00.000Z",
@@ -4,0 +4,0 @@ "omcustomMinClaudeCode": "2.1.121",

No alert changes

Improved metrics

Total package byte prevSize

3596879

0.1%

No dependency changes