JunHo Kim
25256ec417
Extracted and cleaned up from a prior WSL/Windows agent-memory setup. Contains only project-agnostic content: - Claude_Memory/: feedback rules, user profile, reusable reference docs, session scratch space (claude_info/, claude_log/), mirrored skill defs - caveman/: ultra-compressed communication mode skill + subcommands - html-slide-deck/: self-contained HTML slide deck builder skill Project-specific knowledge (previously mixed in) was moved out to each project's own repository as part of this cleanup.
500 B
Executable File
500 B
Executable File
name, description, type
| name | description | type |
|---|---|---|
| Agent 도구 자동 승인 | Agent(서브에이전트) 도구는 settings.json allow 목록에 등록되어 있어 자동 실행됨 | feedback |
Agent(*) = ~/.claude/settings.json permissions.allow 등록 → 승인없이 자동실행.
Why: Bash(python3:*) 동일. 코드리뷰·탐색 서브에이전트 매번 승인프롬프트 불필요.
How to apply:
Agent호출 시 확인없이 실행Bash(python3:*)동일 "Don't Ask" 동작