gstack-ko AGENTS.md

A Korean-language documentation and skill layer for gstack, an upstream collection of coding-agent skills. It contains translated guidance and supporting documents, while the upstream project owns the executable code and build system.

In plain words
What is it for?
Use it when maintaining Korean `SKILL.md` files, translating supporting documentation, or checking whether a proposed change belongs in this repository.
Why use it?
It gives Korean-speaking users access to the same agent guidance while keeping translated documentation separate from the software that runs it. It also records what contributors may and may not change.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/lucas-flatwhite/gstack-ko/agents-md
Clone the repo
git clone --depth 1 https://github.com/lucas-flatwhite/gstack-ko

Made for: Codex, OpenCode.

Per session 284 This file is loaded in full into every session.
When invoked 284 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00284 $0.00284
Opus 5 $0.00142 $0.00142
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00028 $0.00028

Measured 2d ago against content hash 3820c97959b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gstack-ko AGENTS.md 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 2d 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.

AGENTS.md · 35 lines

What it actually says

gstack-ko 에이전트 안내

gstack-ko는 upstream gstack의 한국어 문서/스킬 레이어입니다. 이 저장소에서 에이전트가 기본적으로 따라야 할 원칙은 아래와 같습니다.

우선 원칙

  • 이 저장소는 문서/스킬 전용 저장소다.
  • 실행 코드, 테스트, 바이너리, 빌드 체계는 upstream garrytan/gstack의 책임이다.
  • 한국어 SKILL.md와 supporting docs를 유지하는 것이 1차 목적이다.

수정해도 되는 것

  • 루트 문서
  • 각 스킬 디렉터리의 SKILL.md
  • supporting reference docs
  • 정책 문서와 sync 운영 문서

수정하면 안 되는 것

  • 실행 코드 반입
  • 테스트나 fixture 반입
  • build / install / CI 자산 반입

번역 규칙

  • 명령어, 옵션, 코드 블록, 경로, 변수명, 고유 명칭은 번역하지 않는다.
  • 설명 텍스트만 한국어로 유지한다.
  • 실행 동작은 upstream를 기준으로 설명한다.

작업 전 확인 문서

  • README.md
  • CONTRIBUTING.md
  • docs/translation-sync-policy.md
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. 2d ago First seen · 35 lines · 284 tokens per session scan A 3820c97959b9

Subscribe to this mod's changes

gstack-ko AGENTS.md is an instructions file published in the GitHub repository lucas-flatwhite/gstack-ko (43 stars, last pushed 5mo ago), licensed MIT. It adds 284 tokens to every session, about $0.0014 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 2026-08-30.