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-issuenpx skills add seungdeok/harness-starter --skill make-issuegit 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-issue)<a href="https://agentmods.dev/skills/seungdeok/harness-starter/make-issue"><img src="https://agentmods.dev/badge/skills/seungdeok/harness-starter/make-issue.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 | $0.00119 | $0.01167 |
| Opus 5 | $0.00060 | $0.00583 |
| Sonnet 5 | $0.00024 | $0.00233 |
| Haiku 4.5 | $0.00012 | $0.00117 |
Grade A, and why
make-issue 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 4d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
make-issue
레포에 이슈 템플릿이 있으면 그 형식으로, 없으면 아래에 명시된 기본 형식으로 GitHub 이슈를 만들어요.
유형 판단(bug/feature) → 템플릿 탐색 → 본문 구성 → 라벨 확인 → 확인 → gh issue create
사전 조건
gh가 인증되어 있어야 해요. 실패하면 사용자에게 안내하세요:
gh auth status || echo "gh 인증이 필요해요: gh auth login -h github.com"
절차
1. 유형 판단 (bug vs feature)
- 인자 첫 값이
bug/버그→ 버그,feature/기능→ 기능. - 명시가 없으면 사용자의 설명에서 판단해요. 애매하면 사용자에게 되물어요.
- 재현 절차·에러·"안 돼요" 류 → 버그. 새 화면·기능·"추가했으면" 류 → 기능.
2. 제목·본문 확보
- 제목이 없으면 사용자에게 요청해요.
- 설명이 부족하면 되물어 채워요. 절대 임의로 지어내지 마세요.
3. 템플릿 탐색
find .github/ISSUE_TEMPLATE -name '*.md' 2>/dev/null
find .github docs . -maxdepth 1 -iname 'ISSUE_TEMPLATE.md' 2>/dev/null
(ls + glob 은 zsh 에서 매칭이 없을 때 2>/dev/null 로도 안 막히는 에러를 내니 find 로 통일해요.)
- 후보가 여러 개면 1단계에서 판단한 유형(bug/feature)에 맞는 걸 골라요 — 파일명(
bug_report.md·feature_request.md등) 또는 frontmatter 의name/about으로 매칭해요. 애매하면 목록을 보여주고 사용자에게 물어요. .yml(Issue Forms)만 있으면 지원하지 않으니 아래 기본 형식으로 가요.
4. 본문 구성
템플릿을 찾았으면 — 맨 위 --- frontmatter 블록은 떼어내고, 남은 마크다운의 헤딩 구조를 그대로 둔 채 내용만 채워요.
- 헤딩을 추가·삭제·번역하지 않아요.
- HTML 주석(
<!-- ... -->)은 작성 지침이니 따르되, 최종 본문에서는 지워요. - frontmatter 의
labels:가 있으면 그 값을 라벨 후보로 쓰고(유형 기본값보다 우선),title:이 있으면 제목 접두어로 써요.
못 찾았으면 — 아래 기본 형식을 써요.
버그 — 라벨 후보 bug:
## 버그 설명
<사용자가 설명한 버그 내용>
## 재현 절차
1. <1단계>
2. <2단계>
기능 — 라벨 후보 enhancement:
## 제안하는 기능
<사용자가 제안한 기능 내용>
5. 라벨 존재 확인
라벨 후보가 레포에 실제로 있는지 확인해요. 없는 라벨을 붙이면 gh issue create 가 실패해요:
gh label list --limit 100 | cut -f1
(--json 은 오래된 gh 에 없어서 실패해요. 위 형태는 버전 무관하게 라벨 이름만 뽑아요.)
- 존재하는 후보만
--label로 붙여요. - 하나도 없으면 라벨을 만들지 말고
--label옵션 자체를 빼고 실행해요.
6. 확인 후 생성
실행 전에 최종 title / label / body를 사용자에게 보여주고 확인받아요. 확인 후:
gh issue create --title "<제목>" --label "<존재하는 라벨>" --body "<본문>"
생성되면 반환된 이슈 URL을 사용자에게 알려줘요.
주의
- 라벨은 레포에 존재하는 것만 붙여요. 없으면 조용히 생략하고, 새로 만들지 않아요.
- 본문 구조는 레포 템플릿이 우선이에요. 템플릿이 없을 때만 위 기본 형식을 써요.
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.
- 4d ago First seen · 113 lines · 119 tokens per session scan A bbc5f02c9b0b
make-issue is a skill published in the GitHub repository seungdeok/harness-starter (2 stars, last pushed 18d ago), licensed MIT. It adds 119 tokens to every session and 1,167 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…