메뉴
Audit installed Claude/Codex agents, skills, commands, metadata-level reference counts, and source-level token pressure to decide what to prune, keep, or route. This inventory skill does not mine historical correction content or decide the current session's handoff state.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Review and edit Korean technical docs, READMEs, UI copy, and prompts when terminology sounds machine-translated or a canonical English term was unnecessarily translated. Classify each disputed term as canonical English to preserve, established Korean to keep, or an awkward calque to rewrite naturally. Also strips surface AI-tell symbols from Korean prose — em/en dashes and spaced --, arrows (→), curly/smart quotes, ellipsis (…), and middle-dot (·) bullets or noun enumerations. Use for 기술 용어, 번역투, 직역, 영어로 써야 할 표현, 원어 유지, 한글화가 어색함, 용어 통일, 화살표 제거, em대시 없애, 가운뎃점 없애, AI 티 기호, AI slop 기호, Korean technical writing, or terminology review. Do not use as a general spelling or tone checker.
Auto-research and improve a repo's skills, hooks, and scripts: external real-world web research + internal audit + Codex cross-model verification, behind a propose then approve then apply gate with freeze-on-success and auto-revert. Use when asked to improve, audit, harden, or research-improve skills/hooks/scripts in the current repo.
Use public web, GitHub, social/community, video, RSS, and career search surfaces from the CLI/MCP when local repo evidence is not enough. Routes to public-only research tools while avoiding internal/company URLs and secret-bearing pages.
Clean up runaway/orphaned agent processes: stuck zip/tail/python/node, high CPU, dead Claude/Codex/OMX sessions.
Diagnose codegraph/serena MCP setup, Codex config, and per-repo indexes when code intelligence is broken or stale.
Check Claude/Codex/OMX context, cache, headroom, and handover pressure; advise continue, compact, clear, or hand off.
| name | agent-usage-audit |
| description | Audit installed Claude/Codex agents, skills, commands, metadata-level reference counts, and source-level token pressure to decide what to prune, keep, or route. This inventory skill does not mine historical correction content or decide the current session's handoff state. |
Prefer deterministic local audit scripts. Do not paste transcript contents, prompts, raw command output, private paths, or project text.
Resolve the dotfiles checkout explicitly before running its repo-backed helpers:
DOTFILES_DIR="${DOTFILES_DIR:-$HOME/work/dotfiles}"
test -f "$DOTFILES_DIR/scripts/agent_usage_audit.py"
python3 "$DOTFILES_DIR/scripts/agent_usage_audit.py"
Use this to separate installed local assets, recent usage signals, and gaps where an install exists but usage is absent or unproven. Counts are references, not successful outcomes.
python3 "$DOTFILES_DIR/scripts/agent_usage_audit.py" session-report --since 7d --format markdown --redact
Use this when deciding where token pressure is coming from across RTK, Claude local logs, and Codex local logs. The report separates exact counters from estimated tool-result pressure.
python3 "$DOTFILES_DIR/scripts/rtk_safety_report.py" --since 30d
Use this to inspect fallback, explicit bypass, and repeat-after-compression candidate counts. Repeat candidates are correlation only: same hashed command and cwd within the repeat window after a high-compression event.