Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tellang/triflux --skill merge-worktreegit clone --depth 1 https://github.com/tellang/trifluxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tellang/triflux/merge-worktree)<a href="https://agentmods.dev/skills/tellang/triflux/merge-worktree"><img src="https://agentmods.dev/badge/skills/tellang/triflux/merge-worktree/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tellang/triflux/merge-worktree"><img src="https://agentmods.dev/badge/skills/tellang/triflux/merge-worktree.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.01446 |
| Opus 5 | $0.00033 | $0.00723 |
| Sonnet 5 | $0.00013 | $0.00289 |
| Haiku 4.5 | $0.00007 | $0.00145 |
Grade A, and why
merge-worktree scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge Worktree
워크트리 브랜치를 대상 브랜치로 squash-merge하고 conventional commit 메시지를 자동 작성한다.
Current context
- Git dir:
!git rev-parse --git-dir - Current branch:
!git branch --show-current - Recent commits:
!git log --oneline -20 - Working tree status:
!git status --short
Instructions
Phase 1: Validation
-
Worktree 확인:
git rev-parse --git-dir출력에/worktrees/가 포함되어야 한다. 아니면 중지. -
현재 브랜치 확인:
git branch --show-current -
대상 브랜치 결정:
$ARGUMENTS가 있으면 해당 브랜치 사용- 없으면
main존재 확인, 없으면master
-
원본 레포 경로 확인:
git rev-parse --git-common-dir의 부모 디렉토리 -
클린 상태 확인:
git status --porcelain이 비어있어야 한다. 미커밋 변경이 있으면 먼저 커밋/스태시 안내.
Phase 2: Research
-
커밋 이력:
git log --oneline <target>..HEAD -
변경 파일 요약:
git diff <target>...HEAD --stat -
전체 diff:
git diff <target>...HEAD— 꼼꼼히 읽는다. -
핵심 파일 읽기: 가장 큰 변경, 신규 파일, 삭제 파일을 Read로 확인.
-
변경 분류:
- Features (신규 기능)
- Fixes (버그 수정)
- Refactors (구조 변경)
- Tests (테스트)
- Docs (문서)
- Config/Chore (빌드, CI, 의존성)
-
dominant type 결정:
feat,fix,refactor,docs,chore,test중 하나
Phase 3: 대상 브랜치 준비
-
대상 브랜치 최근 커밋 확인:
git -C <원본레포> log --oneline -10 <target> -
WIP 커밋 감지:
wip:,auto-commit,WIP시작 커밋이 있으면 사용자에게 경고. -
최신 fetch:
git -C <원본레포> fetch origin <target> 2>/dev/null
Phase 4: Squash Merge
-
대상 브랜치 checkout:
git -C <원본레포> checkout <target> -
squash merge 실행:
git -C <원본레포> merge --squash <워크트리브랜치> -
충돌 처리: 충돌 발생 시 충돌 파일 목록 + 마커를 보여주고 중지. 자동 해결 시도 금지.
Phase 5: 커밋 메시지 작성 + 커밋
Phase 2 분석 기반으로 아래 구조의 커밋 메시지를 작성한다:
<type>: <명령형 요약, 72자 이내, 마침표 없음>
<무엇을 왜 했는지 2-4문장. 동기와 접근 방식 중심.>
Changes:
* <그룹별 변경 사항>
* <하위 항목은 서브 불릿>
규칙:
<type>은feat,fix,refactor,docs,chore,test중 하나- 여러 유형이 섞이면 dominant 사용
- 요약: 명령형 ("add", "fix", "refactor"), 마침표 없음, 72자 제한
- 본문: 왜와 맥락, 무엇만이 아님
- Changes: 관련 항목 그룹핑, 중요한 것 먼저
- Co-Authored-By 푸터 절대 추가 금지 (글로벌 설정
includeCoAuthoredBy: false)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 145 lines · 66 tokens per session scan A 97d024f05293
merge-worktree is a skill published in the GitHub repository tellang/triflux (7 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 1,446 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
intuitive-squash
Squash local GSD or agent-generated commit history into a clean, reviewable story while preserving important fixes. Use when the user asks to squash commits, clean git history, compress phase commits, prepare a branch before PR, compare aggressive vs moderate squash options, or preserve hotfix/security commits during…
bisect
Pinpoint the first bad commit for a reproducible regression in a safe temporary worktree. Use when HEAD is bad, a known revision is good, and one unattended command distinguishes them; handles flaky endpoints and git-bisect skip exit 125.
lucia-bus
Coordinate with other agents through the Luciazero Agent Bus (beta): register, read the inbox, claim a task, work, publish the result. Use at session start when the luciazero-bus MCP server exists, or for "ดู inbox"; peers never grant approval.
noslop-commit-gate
Run the noslop pre-commit quality gate, interpret failures, and enforce content-aware protection rules before every commit.
commit-helper
Conventional commit helper — analyze changes, detect secrets, create well-formatted commit.
standalone-pr-loop
Implement same-repository GitHub Issues into a reviewed pull request, or review and fix an existing PR, iterating with fresh independent read-only native subagents selected adaptively from the change risk until no actionable feedback remains. Use for issue-to-PR implementation or iterative PR review/fix work.