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 agentmods add skills/seungdeok/harness-starter/make-prnpx skills add seungdeok/harness-starter --skill make-prgit clone --depth 1 https://github.com/seungdeok/harness-starterWrote 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/seungdeok/harness-starter/make-pr)<a href="https://agentmods.dev/skills/seungdeok/harness-starter/make-pr"><img src="https://agentmods.dev/badge/skills/seungdeok/harness-starter/make-pr.svg" alt="Measured on agentmods" 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 | $0.00123 | $0.02219 |
| Opus 5 | $0.00062 | $0.01110 |
| Sonnet 5 | $0.00025 | $0.00444 |
| Haiku 4.5 | $0.00012 | $0.00222 |
Grade A, and why
make-pr 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 5d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
make-pr
레포에 PR 템플릿이 있으면 그 형식으로, 없으면 아래에 명시된 기본 형식으로 draft PR을 만들어요.
템플릿 탐색 → 브랜치·변경 확인 → stacked PR 여부(리뷰 단위 2+) → 문서 동기화 확인 → 본문 작성 → 확인 → gh pr create --draft
└─ 예: gh-stack (gh stack init/submit)
사전 조건
gh가 인증되어 있어야 해요. 실패하면 안내하세요:
gh auth status || echo "gh 인증이 필요해요: gh auth login -h github.com"
절차
0. base 브랜치·docs 경로·PR 템플릿 결정
-
base 브랜치:
gh repo view --json defaultBranchRef -q .defaultBranchRef.name으로 감지해요 (실패 시main). 아래의<base>는 전부 이 값이에요. -
docs 경로: 환경변수
HARNESS_DOCS_PATH를 읽고, 없으면.claude/settings.local.json의env.HARNESS_DOCS_PATH를 읽어요 (둘 다 없으면docs). 아래의<docsPath>는 이 값이에요. -
PR 템플릿: GitHub 이 인식하는 위치를 훑어요 — 단일 파일과 다중 템플릿 디렉토리 둘 다예요:
find .github docs . -maxdepth 1 -iname 'pull_request_template.md' 2>/dev/null find .github/PULL_REQUEST_TEMPLATE -name '*.md' 2>/dev/null(
ls+ glob 은 zsh 에서 매칭이 없을 때2>/dev/null로도 안 막히는 에러를 내니find로 통일해요.)- 후보가 하나면 그 파일을 읽어서 써요.
- 여러 개면 목록을 보여주고 어느 템플릿을 쓸지 사용자에게 물어요.
- 없으면 절차 4 의 기본 형식으로 가요.
1. 브랜치·변경 상태 확인
git branch --show-current
git status --porcelain
git log <base>..HEAD --oneline
- 현재 브랜치가
<base>면 중단하고, 별도 브랜치가 필요하다고 안내해요. - 커밋 안 된 변경이 있으면 사용자에게 커밋/스태시 여부를 물어요.
- 원격에 브랜치가 없으면
gh pr create가 자동 push하지만, 필요 시git push -u origin <branch>를 안내해요.
1.5 stacked PR 여부 (opt-in)
판단 기준은 커밋 개수가 아니라 리뷰 단위(관심사)가 2개 이상으로 나뉘는지예요. git log <base>..HEAD --oneline 과 변경 파일을 보고, 커밋들이 의존 순서가 있는 계층(예: 모델 → API → UI)으로 묶일 때만 AskUserQuestion 으로 "stacked PR로 나눌까요?"를 물어요. 커밋이 많아도 전부 한 관심사면 묻지 않고 단일 PR로 가요.
-
아니오 (기본) → 아래 2~5 그대로 진행 (단일 draft PR).
-
예 → 절차 2(문서 동기화)까지는 그대로 수행하고, 절차 3~5 대신 아래 gh-stack 흐름으로 생성해요.
주의:
gh stack명령은 인자 없이 실행하면 대화형 프롬프트에 걸려 멈춰요. 반드시 아래처럼 브랜치 이름·플래그를 붙여요.-
확장 설치 확인 — 없으면 안내하고 설치받아요:
gh extension list | grep -qi gh-stack || echo "설치 필요: gh extension install github/gh-stack" git config rerere.enabled true # init 시 대화형 프롬프트 방지
-
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.
- 5d ago First seen · 155 lines · 123 tokens per session scan A 4b10e0bc670f
make-pr is a skill published in the GitHub repository seungdeok/harness-starter (2 stars, last pushed 19d ago), licensed MIT. It adds 123 tokens to every session and 2,219 once invoked, about $0.0006 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
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
changelog
Create changelog files for important commits in a PR.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
refresh-arm-sdk-release
WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…