원클릭으로
git-reword-commits
Rewrite in-scope commit messages to single-line git-workflow messages with git history reword.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Rewrite in-scope commit messages to single-line git-workflow messages with git history reword.
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
| name | git-reword-commits |
| description | Rewrite in-scope commit messages to single-line git-workflow messages with git history reword. |
Use the code:cli and git-workflow skills.
Use git history reword only. Do not use interactive rebase, amend, filter-branch, filter-repo, or replay. Do not change commit content, authors, dates, parents, or trees.
Default scope is commits on the current branch not on upstream, or not on main/master when no upstream exists. If the user asks for all branches, collect every local branch's unique commits not on its upstream or fallback base.
Read full messages:
git log --format='%H%n%B%n--END-COMMIT--' <range>
Draft a replacement one-line message for every commit. Show before/after for every commit and ask for confirmation.
Apply approved rewrites oldest first:
MSG="<new single-line message>" GIT_EDITOR='sh -c "printf %s\\n \"$MSG\" > \"$1\"" --' git history reword <sha>
If any rewrite fails, stop and report the SHA and error. Do not push.
Restore claude/codex agents from a tmux-reboot snapshot after tmux-resurrect reopens their windows.
Snapshot running tmux claude/codex agents immediately before a reboot so their sessions can be restored afterward.
Commit changes, run git-test precommit checks, and fix failures. Use when asked to fix build, test, lint, typecheck, or precommit failures.
Running precommit checks and build validation. ALWAYS use after ANY code changes.
This skill should be used after completing any task, before returning control to the user. Always run this skill — it handles the case where there's nothing to do.
Coordination guidelines for leading a team of task-executing agents