kbo-glossary

kbo-glossary is a skill for Claude Code from sngchn/kbo-analyst. It costs 88 tokens per session (1,205 once invoked), scanned A, original, MIT.

A KBO baseball glossary that translates advanced batting and pitching statistics into everyday fan language. It also explains which figures are measured, estimated, or unavailable in the project’s data.

In plain words
What is it for?
Use it to answer questions about baseball metrics and to explain what project figures mean. It also helps respond honestly when data such as spin rate, exit velocity, launch angle, or bat speed is not available.
Why use it?
It removes the need to know terms such as wOBA, wRC+, BABIP, FIP, or CSW% before reading an analysis. It also prevents estimated values from being mistaken for direct measurements.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the kbo-analyst plugin — 4 skills, 1 MCP server shipped together

Good fit Use it to answer questions about baseball metrics and to explain what project figures mean. It also helps respond honestly when data such as spin rate, exit velocity, launch angle, or bat speed is not available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sngchn/kbo-analyst/kbo-glossary
Install

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.

Any agent
npx skills add sngchn/kbo-analyst --skill kbo-glossary
Clone the repo
git clone --depth 1 https://github.com/sngchn/kbo-analyst

Made for: Claude Code.

Or install kbo-analyst, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

Wrote 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.

agentmods badge for kbo-glossary

README.md
[![agentmods](https://agentmods.dev/badge/skills/sngchn/kbo-analyst/kbo-glossary/github.svg)](https://agentmods.dev/skills/sngchn/kbo-analyst/kbo-glossary)
Your own site
<a href="https://agentmods.dev/skills/sngchn/kbo-analyst/kbo-glossary"><img src="https://agentmods.dev/badge/skills/sngchn/kbo-analyst/kbo-glossary/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.

agentmods 80×15 button for kbo-glossary

Your own site · 80×15
<a href="https://agentmods.dev/skills/sngchn/kbo-analyst/kbo-glossary"><img src="https://agentmods.dev/badge/skills/sngchn/kbo-analyst/kbo-glossary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,205 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00088 $0.01205
Opus 5 $0.00044 $0.00602
Sonnet 5 $0.00018 $0.00241
Haiku 4.5 $0.00009 $0.00120

Measured 10d ago against content hash 84bf5144261c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

kbo-glossary 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 10d 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.

skills/kbo-glossary/SKILL.md · 52 lines

What it actually says

KBO Glossary — 팬 언어 번역

번역 규칙 (숫자를 일상어로)

지표를 처음 말할 때 한 줄 번역을 붙인다. 두 번째부터는 지표명만 써도 된다.

지표 팬 언어 번역
wRC+ 130 "리그 평균 타자보다 30% 더 생산적" (100=평균, 파크 보정 포함)
wOBA .400 "출루의 질까지 반영한 종합 타격 지표 — .400이면 리그 최상위권"
OPS+ / 백분위 96 "리그 상위 4%" — 백분위는 숫자보다 상위 몇 %로
BABIP .380 "인플레이 타구가 안타가 된 비율 — 리그 평균(~.310)보다 크게 높으면 실력+운/수비/타구질이 섞인 결과"
K-BB% 20% "삼진은 많이 잡고 볼넷은 적게 주는 정도 — 투수 실력의 가장 안정적인 한 줄 요약"
FIP 3.50 "수비 도움을 걷어낸 ERA — ERA보다 실력에 가깝다"
CSW% 32% "던진 공 중 루킹+헛스윙 비율 — 30% 넘으면 구위가 통한다는 뜻"
Whiff% 30% "상대가 스윙한 것 중 30%를 헛돌림" (SwStr%=전체 투구 대비와 구분)
파크팩터 HR 1.13 "이 구장은 홈런이 평균보다 13% 잘 나온다" (1.000=중립)
RE24 / run_value "그 상황(주자·아웃)에서 기대되는 득점을 얼마나 바꿨나 — 번트/교체 판단 평가의 근거"

이 프로젝트 수치의 정체 (인용 시 필수 구분)

  • 측정값: 구속, 투구 위치, 카운트, 공식 투수 라인(ERA/K/BB/ER). 네이버 스포츠 공개 중계 데이터 + KBO 공식 라인 대조 검증(validation_status).
  • 유도값: iVB/HB/VAA/축(시계) — PITCHf/x식 초기조건에서 물리식으로 유도. 실측 스핀축이 아니다. wOBA — 표준 선형가중치 근사(공식 아님). wRC+ — 프로젝트 proxy. 파크팩터 — 수집된 경기 기반, 단년은 회귀값 우선.
  • 없는 것 (KBO 어디에도 공개 안 됨, Statiz 포함): 스핀량(RPM), 익스텐션, 타구속도, 발사각, 배트 스피드, 진짜 xwOBA.

측정 불가 → 프록시 매핑

물어본 것 답할 수 없는 이유 대신 답하는 법
"배트 스피드 늘었어?" 배트 트래킹 없음 batter_velo_band: 145km/h+ 패스트볼 상대 Whiff%/성과 변화 = 빠른 공 대응력 (밴드: <140/140-144/145-149/150+). "배트 스피드 자체는 측정 불가, 대응력 프록시로는…"
"타구질이 좋아졌어?" 타구속도/발사각 없음 batter_spray: 타구 방향(당김/밀어침) 변화 + ISO/장타 구성. BABIP을 운/수비/타구질로 분해할 수 없음을 명시
"회전수가 줄었나?" 트랙맨 비공개 무브먼트 유도값(iVB/HB) 변화 — "회전 효율의 간접 신호이지 실측 아님"
"xwOBA로는 어때?" 타구추적 없음 실제 결과 wOBA + BABIP 병기 — "기대치가 아니라 실제 결과"
"익스텐션은?" 릴리스 y 미제공 vRel/hRel(z0/x0)까지만 — 앞뒤 릴리스는 불가

자주 틀리는 정의

  • Strike% = 인플레이 포함 전체 스트라이크 비율 (리그 ~63%). 루킹만이 아니다.
  • Whiff% (스윙 대비) ≠ SwStr% (전체 투구 대비) ≠ CSW% (루킹+헛스윙, 전체 대비).
  • 존 판정 분모는 위치 데이터가 있는 투구만(has_location). 존 폭은 공 반지름 포함 ±0.83ft, 높이는 투구별 개인 존(sz_top/sz_bot).
  • 세부 정의와 뷰 목록은 METRICS.md가 원본이다.
Changes

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.

  1. 10d ago First seen · 52 lines · 88 tokens per session scan A 84bf5144261c

Subscribe to this mod's changes

kbo-glossary is a skill published in the GitHub repository sngchn/kbo-analyst (0 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 1,205 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

teaching-assistant

A teaching guide for explaining concepts, showing working code examples, creating exercises, and planning learning paths.

ntygod/ZhiWei · 37 tokens

yada-yada-yada

Enter Seinfeld Mode. Explain programming, debugging, architecture, and code reviews through observational comedy inspired by Seinfeld. Trigger when the user says "what's the deal", festivus, serenity, yada, soup, shrinkage, sponge-worthy, master of my domain, double dip, newman, vandelay, nostrand, constanza or…

AndreiBozantan/svelte-axum-template · 81 tokens

pf2e-rules

Answer Pathfinder Second Edition rules and character-building questions using the Archives of Nethys. Use whenever the user asks about a PF2e rule, spell, feat, condition, creature, item, or class feature; asks what to pick or what is good ("best melee weapon for a level 3 fighter", "which ancestry feats should I take…

fbonds/oracle-of-nethys · 127 tokens

cert-study

A study session for SQLD, a SQL database certification exam, run inside Codex with SQLite records and error notes for Obsidian.

Merchantlee99/codex_learningsystem · 51 tokens

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens