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 ScottJeong/altium-claude-skills --skill altium-librarygit clone --depth 1 https://github.com/ScottJeong/altium-claude-skillsWrote 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/scottjeong/altium-claude-skills/altium-library)<a href="https://agentmods.dev/skills/scottjeong/altium-claude-skills/altium-library"><img src="https://agentmods.dev/badge/skills/scottjeong/altium-claude-skills/altium-library/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/scottjeong/altium-claude-skills/altium-library"><img src="https://agentmods.dev/badge/skills/scottjeong/altium-claude-skills/altium-library.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 | $0.00256 | $0.07909 |
| Opus 5.5 | $0.00102 | $0.03164 |
| Sonnet 5.5 | $0.00051 | $0.01582 |
| Haiku 4.5 | $0.00026 | $0.00791 |
Grade A, and why
altium-library 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 1mo 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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Altium 라이브러리 제작·검증
라이브러리는 한 번에 맞지 않는다. 틀리는 지점이 정해져 있어서 그걸 순서로 막는 게 핵심이다. 아래 순서는 실제로 10건의 결함이 난 세션에서 역산한 것이다. 잡히는 결함과 안 잡히는 결함이 갈렸다:
- 숫자·기준파일과 대조 가능한 것 → 검산으로 잡힌다
- 그 물건이 물리적으로 뭔지, 툴이 어떻게 그리는지 → 검산으로 안 잡힌다. 그래서 §2 와 §6 이 있다
0. 도구 분담 — 이건 안 바뀐다
| 하는 일 | 도구 |
|---|---|
| 생성·수정 | altium_monkey (파이썬). Altium 없이 파일을 직접 쓴다 |
| 검증·조회 | altium-mcp MCP. 읽기 전용으로만 |
altium-mcp 의 create_schematic_symbol / create_pcb_footprint 는 실행 중인 Altium 의
활성 문서에 직접 쓴다. 사용자가 열어둔 남의 라이브러리를 오염시킬 수 있고, 어느 문서가
활성인지 확실히 보장할 방법이 없다. 생성에 쓰지 마라.
파이썬은 반드시 이 인터프리터:
python
3.12 venv 다. altium-monkey 가 Requires-Python <3.13 이라 시스템 3.13 에는 안 깔린다.
패키지 추가는 uv pip install --python <위 경로> <패키지> (venv 에 pip 가 없다).
작업 폴더 — 부품 하나 = 폴더 하나
<작업폴더> 는 라이브러리 작업을 모아 두는 곳이고 프로젝트 폴더와 별개다.
스킬 폴더 안에 만들지 마라 (git pull 때 섞인다).
정해진 게 없으면 사용자에게 묻고, 답이 없으면 프로젝트 옆에
altium-lib-work/ 를 만들어 쓰고 그 경로를 알린다. 한 번 정하면 계속 거기 쌓는다.
산출물과 중간물을 한 폴더에 몰면 부품 두세 개만 늘어도 뭐가 뭔지 못 찾는다. (커넥터 하나에 파일 29개가 평평하게 쌓이는 일이 실제로 생긴다.)
<작업폴더>\
├── index.md 부품 목록·상태·공용 라이브러리 반영 여부
└── <MPN>/ 폴더명은 MPN. 괄호·슬래시 등 경로에 나쁜 문자는 뺀다
├── build.py 생성 코드. 근거와 판단 이유가 주석에 — 이게 진실이다
├── out/ 산출물(.PcbLib/.SchLib). 공용 라이브러리로 옮기는 건 여기서만
├── work/ 도면 렌더, 측정 기록(measure-commands.md), 일회용 스크립트(adhoc/)
└── check/ 검증용 사본(_chk, _v2 …). 언제든 지워도 되는 것
build.py는OUT = Path(__file__).parent / "out"로 쓴다- 도면에서 잰 명령과 중간 결과를
work/measure-commands.md에 남긴다. clip 좌표·스케일·검산값이 없으면 나중에 재현이 안 된다 - 일회용 분석 스크립트를 부품 폴더마다 복제하지 마라. 범용화해서 이 스킬의
scripts/로 올리고, 부품 폴더에는 쓴 명령만 기록한다 - 새 부품을 끝내면
index.md에 한 줄 추가한다 (산출물·상태·공용 반영 여부·미해결)
1. 이미 있는지 먼저 본다
새로 만들기 전에 기존 라이브러리를 검색한다. 심볼은 이미 있고 풋프린트만 없는 경우가 흔하다.
라이브러리 폴더 경로는 환경마다 다르다. 프로젝트 폴더 → Altium 워크스페이스
(%APPDATA%\Altium\Altium Designer {GUID}\LastWorkspace\*.DsnWrk 안에 .LibPkg
절대경로가 그대로 있다) → 사용자에게 묻는다 순으로 찾는다.
python scripts/survey_library.py <라이브러리 폴더 또는 .PcbLib/.SchLib>
python scripts/survey_library.py <폴더> --find PCN10 # 부분 문자열
python scripts/survey_library.py <폴더> --pins 96 # 핀 수로
What ships with it
8 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.
- references/altium-monkey-api.md 10 KB
- references/drawing-measurement.md 5.3 KB
- references/tool-traps.md 6.6 KB
- scripts/audit_free_copper.py 6.6 KB runs code
- scripts/diff_symbol.py 8.6 KB runs code
- scripts/fit_symbol_body.py 5.9 KB runs code
- scripts/measure_drawing.py 8.9 KB runs code
- scripts/survey_library.py 5.8 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.
- 1mo ago First seen · 477 lines · 0 tokens per session scan A 634928488a54
altium-library is a skill published in the GitHub repository ScottJeong/altium-claude-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 256 tokens to every session and 7,909 once invoked, about $0.0010 per session on Opus 5.5. 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
kicad
Analyze KiCad projects and PDF schematics: schematics, PCB layouts, Gerbers, footprints, symbols, netlists, and design rules. Reviews designs for bugs, traces nets, cross-references schematic to PCB, extracts BOM data, checks DRC/ERC, DFM, power trees, and regulator circuits. Every finding carries a confidence label…
digikey
Search DigiKey for electronic components and download datasheets — primary source for prototype orders and the preferred API method for fetching datasheets. Find parts by keyword or MPN, check pricing/stock, download datasheets via API, analyze specifications. Sync and maintain a local datasheets directory — extract…
emc
EMC pre-compliance risk analysis for KiCad PCB designs — 18 check categories, 44 rule IDs covering ground planes, decoupling, I/O filtering, switching harmonics, clock routing, differential pair skew, board edge radiation, PDN impedance, return paths, crosstalk, ESD protection, shielding, and magnetic leakage from…
lcsc
Search LCSC Electronics for electronic components — find parts by LCSC number (Cxxxxx) or MPN, check stock/pricing, download datasheets, analyze specifications. Sister company to JLCPCB, same parts library. Sync and maintain a local datasheets directory for a KiCad project, or use batch MPN-list seeding (--mpn-list)…
mouser
Search Mouser Electronics for electronic components — secondary source for prototype orders. Find parts, check pricing/stock, download datasheets, analyze specifications. Use with KiCad for BOM creation and part selection. Also supports batch MPN-list seeding (--mpn-list) for bulk datasheet workflows without a KiCad…
datasheets
Extract structured specifications from electronic component datasheet PDFs — pinouts, electrical characteristics, peripherals, topology, and features. Cache extractions per project for consumption by schematic and PCB analyzers. Primary consumer infrastructure for kicad, emc, spice, and thermal analyzers. Use this…