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 LeeYudok/agents-scaffold --skill yd-git-shipgit clone --depth 1 https://github.com/LeeYudok/agents-scaffoldWrote 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/leeyudok/agents-scaffold/yd-git-ship)<a href="https://agentmods.dev/skills/leeyudok/agents-scaffold/yd-git-ship"><img src="https://agentmods.dev/badge/skills/leeyudok/agents-scaffold/yd-git-ship/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/leeyudok/agents-scaffold/yd-git-ship"><img src="https://agentmods.dev/badge/skills/leeyudok/agents-scaffold/yd-git-ship.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 | $0.00135 | $0.02320 |
| Opus 5.5 | $0.00054 | $0.00928 |
| Sonnet 5.5 | $0.00027 | $0.00464 |
| Haiku 4.5 | $0.00014 | $0.00232 |
Grade B, and why
yd-git-ship scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
스크립트 위치: 이 스킬 폴더의 `scripts/` (Claude `~/.claude/skills/yd-git-ship`, Codex `~/.agents/skills/yd-git-ship`, Antigravity `~/.gemini/config/skills/yd-git-ship` — 모두 doksam-skills `install.sh` 가 건 같은 원본의 심링크). Copies of this mod
1 near-identical copy found in the catalogue:
- yd-git-ship — 88% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
yd-git-ship — 에이전트 작업을 GitLab 에 올리기
규칙 원본은 ~/.claude/ref-git-agents.md (세 에이전트 공통, agents-mem 의 공통본을 각 호스트에 동기화). 이 스킬은 그 규칙을 따르는 절차와 도구다. 규칙과 이 문서가 다르면 원본이 우선한다. 원본 파일이 없는 환경(새 머신, 외부 설치)에서는 이 문서의 절차가 곧 규칙이다.
스크립트 위치: 이 스킬 폴더의 scripts/ (Claude ~/.claude/skills/yd-git-ship, Codex ~/.agents/skills/yd-git-ship, Antigravity ~/.gemini/config/skills/yd-git-ship — 모두 doksam-skills install.sh 가 건 같은 원본의 심링크).
0. 내 값 정하기
| Claude Code | Codex | Antigravity | |
|---|---|---|---|
AGENT |
claude |
codex |
agy |
커밋 -c |
user.name=claude-ai user.email=claude-ai@<도메인> |
codex-ai / codex-ai@<도메인> |
agy-ai / agy-ai@<도메인> |
| 모델 태그 | 지금 도는 모델 이름, 예 [Claude Opus 5.5] |
예 [GPT-6 Sol] |
예 [Gemini 3.8 Flash] |
모델 태그는 추측하지 말고 자기 시스템 정보에 적힌 실제 모델명을 쓴다.
SK=~/.claude/skills/yd-git-ship/scripts # 에이전트별 경로로
GL="$SK/glab-as.sh claude" # 토큰을 출력하지 않고 자기 계정으로 glab 실행
REPO=<gitlab-host>/<ns>/<repo> # -R 에는 호스트까지 붙인다. 명령은 그 레포 폴더 안에서
$GL api user | grep '"username"' # claude-ai 인지 확인
glab-as.sh 는 Python 3.11 미만(tomllib 없음)에서도 요청한 계정 섹션의 토큰만 읽는다. 호출한 셸의 PATH 에 따라 시스템 Python 3.9 가 잡혀도 동작한다.
1. 시작 전 점검
git status -sb; git branch --show-current
$GL api "projects/<ns>%2F<repo>/merge_requests?state=opened&author_username=claude-ai" # 내 열린 MR 있으면 그것부터 머지
$GL api "projects/<ns>%2F<repo>" | python3 -c 'import json,sys;p=json.load(sys.stdin);print(p["squash_option"],p["merge_method"])'
$SK/install-hook.sh --check || $SK/install-hook.sh # 없으면 설치 → scripts/commit-msg.sh 를 첫 커밋에 포함
squash_option이always면 squash 금지 규칙과 충돌하니 사용자에게 알린다.merge_method가ff면 merge commit 이 안 생기니 역시 알린다.- 레포 AGENTS.md 에 "squash 머지" 같은 옛 문구가 있으면 원본 규칙이 우선이고, 이번 배치에서 같이 고친다.
- hook 은 본문의
Co-Authored-By: Claude와Generated with Claude Code줄을 사람 커밋이어도 거부한다.Merge로 시작하는 제목은 형식 검사에서 뺀다. - jj 레포(
.jj/)는jj commit이 git hook 을 안 돌린다. 커밋 제목을 직접 맞추고 push 전git log로 확인한다.
2. 이슈
작업 단위마다 이슈. 본문은 파일로 쓰고 "누가 판정하나"를 넣는다.
What ships with it
11 files 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.
- scripts/ci_wait.py 2.6 KB runs code
- scripts/commit-msg.sh 1.9 KB runs code
- scripts/glab-as.sh 1.1 KB runs code
- scripts/install-hook.sh 1.6 KB runs code
- scripts/read_token.py 2.2 KB runs code
- tests/claims.json 4.3 KB
- tests/test_ci_wait.py 5.7 KB runs code
- tests/test_commit_msg.py 4.0 KB runs code
- tests/test_glab_as_fallback.py 3.2 KB runs code
- tests/test_glab_as.py 3.4 KB runs code
- tests/test_install_hook.py 3.5 KB runs code
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.
- today First seen · 109 lines · 135 tokens per session scan B 4336b7b56c12
yd-git-ship is a skill published in the GitHub repository LeeYudok/agents-scaffold (36 stars, last pushed today), licensed MIT. It adds 135 tokens to every session and 2,320 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-25.
Other skills, from other repositories
github-workflow
GitHub best practices for pull requests, code reviews, issues, Actions workflows, and repository management.
lerna
Best practices for Lerna monorepo management, versioning, and publishing.
ops-standup
Cross-repo morning briefing. Aggregation of recent commits, PRs, CI, blockers and priorities of the day. Trigger when the user wants a standup, an activity summary, or to know what happened.
work-batch
Sequential execution of user stories from a PRD file. Autonomous mode that implements and commits each story one by one. Trigger when the user wants to process a backlog, execute multiple stories, or launch an autonomous mode.
quick
Execute an ad-hoc task with atomic commits. Skips full plan/review.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.