open
Open a transaction — cut a tx-* branch off base, seed the repo, and route the change
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
Open a transaction — cut a tx-* branch off base, seed the repo, and route the change
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | open |
| description | Open a transaction — cut a tx-* branch off base, seed the repo, and route the change |
| argument-hint | [change description] |
| effort | high |
transaction은 작업 단위가 아니라 무결성 경계다.
/tx:open은 "지금부터 구현 또는 내용을 무결하지 않은 상태로 만들겠다"는 선언이다.
새 branch tx-<slug>가 최신 origin/<base>에서 cut되어 checkout되어 있다 — slug는
의도를 나타내는 짧은 kebab-case:
"${CLAUDE_PLUGIN_ROOT}/bin/tx-hook" open-tx <slug>
seed가 완료되어 있다 (idempotent) — 산출물은 이 transaction에 실려 함께 merge된다:
"${CLAUDE_PLUGIN_ROOT}/bin/tx-hook" seed
변경이 route되어 있다: 구조·세계관에 영향을 주는 변경은 tx:plan(Skill 도구) —
behavior 불변인 refactor도 구조에 닿으면 여기다. 그 밖의 trivial·docs 표면 변경은
openspec 생략.
command 실패는 stderr가 fix 경로다 — seed 실패만은 openspec 생략 경로로 진행한다.
Answer the owner's questions about a running or finished loop from its records — read-only, in a separate session
Hours-long (3-12h) multi-agent code-architecture optimization — cross-examines antipatterns into consensus, then applies only the highest-ROI refactors. Not for routine refactors.
Hours-long (3-12h) multi-agent documentation-architecture optimization — verifies every claim in every non-executable text (markdown, spec systems, comments) against the code, cross-examines discrepancies into consensus, then applies only the highest-ROI fixes. Code is never modified — defects are reported, not fixed. Not for touching up a single file.
Hours-long (3-12h) multi-agent integrity-boundary optimization — hunts every reachable state the boundary (types, invariants, error definitions, tests) fails to contain, then absorbs only the highest-ROI set into it — code and docs both, pinned by tests. Not for fixing a known bug.
Implement the planned change task by task, then spawn the independent verify stage until it passes
Archive the completed change — task gate, delta sync into main specs, revalidate