메뉴
Add, fix, or update logging in project code
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
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
Cross-repo visibility for agent loops. Lists running, completed, and crashed loops. Reads the registry and per-repo tracking logs. Shows tmux attach commands. Use when checking what loops are active, what ran recently, or loop details.
Capture feedback about wf, util, or vault plugins and file it as a GitHub issue for improvement. Use after any session where the tooling fell short — wrong agent behavior, missing skill coverage, misleading prompts, workflow friction, or convention gaps. Only for generic plugin improvements that would help ANY project, not repo-specific config. Files to JSai23/claude-tooling with the plugin-feedback label.
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
| name | logging |
| description | Add, fix, or update logging in project code |
| argument-hint | [scope: file|module|all] |
| context | fork |
| agent | log-writer |
$ARGUMENTS
Add, fix, or update logging following strict principles.
Logs that don't get read are useless. Every log statement must earn its place.
Before adding a log, ask:
Cut ruthlessly. Then cut more.
What the service is doing at a glance.
Log these:
Never log:
Details for troubleshooting. Off in production unless investigating.
Log these:
Recoverable errors you're explicitly allowing to continue.
Log these:
Never log:
Log at the handling point. Once.
/logging after significant code changesReview ALL logging against current code. Fix level mismatches. Remove noise. Add missing service narrative. Report what was changed.