boardgame-studio: Skill for Cursor

.cursor/skills/bgs-review/SKILL.md

bgs-review is a skill for Cursor from kongsol-83/boardgame-studio. It costs 81 tokens per session (1,454 once invoked), scanned A, original, Apache-2.0.

A review workflow for board-game rules that either records a recent playtest or asks three independent critics to examine the rules and combine their findings.

In plain words
What is it for?
Use it after playing to record time, rulebook questions, and dull sections, or use it to review unclear rules, balance concerns, and gaps in the written rules.
Why use it?
It captures practical problems such as confusing rules, excessive play time, or boring sections while keeping observations separate from guesses about their causes. Reviews also use existing playtest and simulation reports when available.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is kongsol-83/boardgame-studio's own configuration. It tells Cursor how to work on boardgame-studio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything boardgame-studio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kongsol-83/boardgame-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kongsol-83/boardgame-studio/main/.cursor/skills/bgs-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kongsol-83/boardgame-studio

Made for: Cursor.

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 bgs-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/kongsol-83/boardgame-studio/bgs-review/github.svg)](https://agentmods.dev/skills/kongsol-83/boardgame-studio/bgs-review)
Your own site
<a href="https://agentmods.dev/skills/kongsol-83/boardgame-studio/bgs-review"><img src="https://agentmods.dev/badge/skills/kongsol-83/boardgame-studio/bgs-review/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 bgs-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/kongsol-83/boardgame-studio/bgs-review"><img src="https://agentmods.dev/badge/skills/kongsol-83/boardgame-studio/bgs-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,454 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 $0.00081 $0.01454
Opus 5 $0.00041 $0.00727
Sonnet 5 $0.00016 $0.00291
Haiku 4.5 $0.00008 $0.00145

Measured 11d ago against content hash c6aac13b38ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

bgs-review 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 11d 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.

.cursor/skills/bgs-review/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

검토와 플레이테스트 기록

두 가지 일을 한다. 플레이 직후에 부르면 기록을 정리하고, 검토를 부르면 크리틱을 돌린다. 검토는 기존 기록을 먼저 읽고 들어간다.

문서 언어는 studio.config.jsonlanguage 를 따른다.

어느 쪽인지 먼저 확인한다

사용자가 방금 플레이테스트를 했다고 하면 기록 정리로, 그 외에는 검토로 간다. 애매하면 묻는다.


A. 플레이테스트 기록

projects/<slug>/playtest/table-YYYY-MM-DD.md 를 만든다.

사용자가 말하는 대로 받아적되, 빠진 것을 되묻는다. 특히 아래 넷은 나중에 반드시 필요해지는데 그 자리에서 안 물으면 영영 못 채운다.

  • 실제 소요 시간. 목표가 45분인데 90분 걸렸다면 다른 어떤 밸런스 문제보다 우선이다
  • 룰셋 버전. 어느 버전으로 했는지 없으면 개정 효과를 추적할 수 없다
  • 막혀서 룰북을 다시 본 대목. 룰북의 애매한 자리를 그대로 가리킨다
  • 지루했던 구간. 문서 분석으로는 절대 안 나오는 신호다
# 플레이테스트 2026-08-02

룰셋 v0.4 · 3인 · 실제 72분 (목표 45분)

## 결과
| 좌석 | 플레이어 | 전략 | 점수 |
| --- | --- | --- | --- |
| 1 | ... | ... | 34 |

## 막힌 대목
- 어느 규칙에서 멈췄고 어떻게 해석했는지

## 지루했던 구간
- 몇 라운드쯤, 왜

## 그 자리에서 나온 아이디어
- ...

## 다음에 확인할 것
- ...

기록은 판단하지 않는다. 관찰과 해석을 섞지 않는다. "3라운드가 지루했다"는 관찰이고 "액션 수가 부족해서다"는 해석이다. 해석은 검토에서 한다.


B. 검토

1. 근거를 먼저 모은다

playtest/ 의 기록과 sim-*.md 리포트를 읽는다. 크리틱 셋은 전부 문서만 읽으므로 실제 플레이에서 나온 것을 이 단계에서 확보하지 않으면 검토 전체가 탁상공론이 된다.

기록이 하나도 없으면 그 사실을 사용자에게 알린다. 문서 검토만으로도 룰 구멍은 잡히지만 "재미있는가"는 답할 수 없다.

2. 크리틱 3명을 병렬로 돌린다

한 번의 메시지에서 세 개를 동시에 띄운다. 순차로 돌리면 느리기도 하지만, 앞 크리틱의 결론이 뒤 크리틱에 새어 들어가서 독립적인 시각이라는 장점이 사라진다.

  • bgs-mechanism-critic — 핵심 동사가 실제로 일어나는가, 겉도는 메커니즘, 다운타임
  • bgs-rules-critic — 룰 구멍, 애매한 문장, 용어 불일치
  • bgs-balance-designer — 수치와 플레이 기록

각자에게 어느 프로젝트인지와 플레이 기록 위치를 알려준다. bgs-rules-critic 에게는 설계 의도를 넘기지 않는다. 맥락을 모르는 상태로 읽는 게 그 역할의 전부다.

3. 종합한다

세 결과를 합쳐 projects/<slug>/review/YYYY-MM-DD.md 에 남긴다.

# 검토 2026-08-02 (룰셋 v0.4)

근거: 플레이테스트 2건(3인 72분, 4인 81분), 시뮬 없음

## 요약
[가장 급한 것 한두 개와 전체 인상. 한 문단]

## 지적 사항

### 1. [제목] — 치명
- 현상:
- 원인:
- 영향:
- 조치:
- 확인:

### 2. [제목] — 중요
...

## 이번에 반영할 것
- [치명 항목만]

## 남겨둘 것
- [나머지. 다음 검토에서 다시 본다]

중복을 합친다. 세 크리틱이 같은 문제를 다르게 표현하는 경우가 많다. 셋이 동시에 지적한 항목은 우선순위를 올린다.

충돌하면 양쪽을 다 적는다. 메커니즘 크리틱이 "선택지가 부족하다"고 하고 밸런스가 "선택지가 너무 많다"고 하면, 어느 한쪽을 버리지 말고 둘 다 적은 뒤 사용자에게 판단을 넘긴다. 대개 둘 다 맞고 다른 층위를 보고 있다.

Read the full file on GitHub · 135 lines

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. 11d ago First seen · 135 lines · 81 tokens per session scan A c6aac13b38ae

Subscribe to this mod's changes

bgs-review is a skill published in the GitHub repository kongsol-83/boardgame-studio (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,454 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

gameobject-component-destroy

Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.

IvanMurzak/Unity-MCP · 49 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 tokens

godot-signals-groups

Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…

gamedev-skills/awesome-gamedev-agent-skills · 95 tokens

unity-addressables

Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).

Besty0728/Unity-Skills · 25 tokens

motion

How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.

OpenDCAI/GameFactory-3A · 0 tokens

threejs-exposure-color-grading

Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.

scottstts/Threejs-Awesome-Graphics-Agent-Skills · 60 tokens