What is doksam-skills AGENTS.md?

Repository instructions for doksam-skills, a collection of AI-agent skills installed through symbolic links and organized as separate skill folders.

Use them when adding, testing, documenting, or installing skills in the doksam-skills repository.

They explain the repository's shared rules, file ownership, supported tools, language policy, and runtime discovery paths, reducing inconsistent changes across skills.

How LeeYudok/doksam-skills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to LeeYudok/doksam-skills. 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/LeeYudok/doksam-skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/LeeYudok/doksam-skills

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/leeyudok/doksam-skills/agents-md/github.svg)](https://agentmods.dev/instructions/leeyudok/doksam-skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/leeyudok/doksam-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/leeyudok/doksam-skills/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/leeyudok/doksam-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/leeyudok/doksam-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7,683 This file is loaded in full into every session.

When invoked 7,683 The same file — it is already loaded in full.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.07683	$0.07683
Opus 5.5	$0.03073	$0.03073
Sonnet 5.5	$0.01537	$0.01537
Haiku 4.5	$0.00768	$0.00768

Measured 7d ago against content hash fc12bbad4ad3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

doksam-skills AGENTS.md scanned grade B with 1 finding 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| Antigravity | `~/.gemini/config/skills/` · 프로젝트 `.agents/skills/` | 플러그인 `agents/*.md` (`agy plugin install`) | `agy agents` |

AGENTS.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

doksam-skills — 에이전트 지침

AI 에이전트(Claude Code·Codex·Antigravity)가 이 저장소에서 작업할 때 지킬 규칙이다. 기계 판독용 정보(구성요소 그래프·명령·환경변수 키·정책·알려진 문제)는 AGENTS.yaml 에 있다.

한눈에

먼저 지킬 것	근거
스킬 하나가 자기 자산을 전부 소유한다. 스킬 전용 파일을 루트 `scripts/`·`tests/` 에 두지 않는다	2장
사용자에게는 한국어로 답한다. 문서·커밋·이슈·PR 본문도 한국어이고 문장은 `yd-writer-kr` 규칙을 따른다	1장
Python 은 stdlib 만 쓴다. 예외는 `scripts/check-agents-yaml.sh` 하나다	4장
`install.sh` 와 루트 테스트에 스킬 이름을 적지 않는다. 스킬을 순회한다	4장
등록 여부는 파일이 아니라 런타임 출력으로 판정한다	3장
이모지 아이콘, 한쪽 색 띠 같은 AI 냄새 나는 UI 장식을 쓰지 않는다	5장
구성요소·경로·명령·환경변수가 바뀌면 이 문서와 `AGENTS.yaml` 을 함께 고친다	아래

./scripts/run_tests.sh                    # 루트 규약 + 모든 스킬 + 설치기 테스트
python3 scripts/score_skills.py --write   # 스킬을 고쳤으면 README 완성도 표를 다시 만든다
scripts/check-agents-yaml.sh              # AGENTS.yaml 검증 (PyYAML 필요)
./install.sh --verify --with-agent        # 세 런타임에 실제로 등록됐는지 확인

두 파일이 어긋나면 실제 코드·파일시스템을 확인해 둘 다 고친다. 날짜·버전 값은 항상 따옴표로 감싼다. 코드·구성이 바뀐 뒤 남은 낡은 참조는 yd-doc-sync 로 찾는다(범위는 AGENTS.yaml 의 x-doc-sync).

1. 개요와 언어

성격: Agent Skill 모음이다. skills/ 아래 스킬 하나가 배포 단위이고, install.sh 가 전부를 세 런타임 경로에 심링크로 노출한다.
기술 스택: 스킬 정의는 Markdown, 템플릿은 HTML5 + Vanilla CSS 다. 검증·테스트는 Python 3 stdlib 와 bash 다. 앱을 품은 스킬은 TypeScript + Vite 다(yd-blueprint 템플릿은 React, yd-script-editor 앱).
응답 언어: 사용자에게 항상 한국어로 답한다. 영어로 묻거나 영어 자료를 다룰 때도 같다. 사용자가 다른 언어를 명시한 경우만 예외다.
작성 언어: SKILL.md 본문·frontmatter description·어댑터·문서·커밋/이슈/PR 본문은 한국어로 쓴다. 영어를 유지하는 것은 셋이다. 코드 식별자·명령어·파일/키 이름, 고유 기술용어(IA, Storyboard, SSOT, frontmatter 등), 외부 도구가 요구하는 형식. description 은 한국어 문장으로 쓰되 핵심 키워드는 한/영을 병기할 수 있다.
문장: 사람이 읽을 문서는 yd-writer-kr 규칙으로 쓴다(번역투·군더더기 없이, 문장 60자 안팎). 자가 점검은 python3 skills/yd-writer-kr/scripts/check_writing.py <파일> 이다.

2. 스킬 레이아웃 규약

skills/<skill>/
  SKILL.md            필수. frontmatter 는 name·description 두 개뿐이고 name 은 디렉터리명과 같다
  agents/             선택. 아래 넷을 한 세트로 둔다
    claude.md         Claude Code 어댑터
    codex.toml        Codex custom agent (name 은 스킬명의 - 를 _ 로 바꾼 것)
    antigravity.md    Antigravity 플러그인 에이전트 / Gemini API Managed Agent 등록 원본
    openai.yaml       Codex UI 용 스킬 메타데이터
  references/         SKILL.md 가 가리키는 상세 문서
  resources/·assets/  템플릿
  scripts/            이 스킬 전용 스크립트
  tests/              이 스킬 전용 테스트와 claims.json

Read the full file on GitHub · 233 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.

7d ago Changed · +9 tokens per session fc12bbad4ad3
9d ago Changed · +7 tokens per session f8cfee6966e1
13d ago Changed · -95 lines · -1,149 tokens per session 5ef0c5d4d9b4
14d ago Changed · +3 tokens per session a102fc6487f5
19d ago Changed · +15 lines · +670 tokens per session f44e48ec62bc
20d ago Changed · +18 lines · +1,328 tokens per session 99a0fabb14c3
1mo ago First seen · 295 lines · 6,815 tokens per session scan B 6e2db6b0c832

Subscribe to this mod's changes

doksam-skills AGENTS.md is an instructions file published in the GitHub repository LeeYudok/doksam-skills (14 stars, last pushed 7d ago), licensed MIT. It adds 7,683 tokens to every session, about $0.0307 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code agent-skills antigravity codex information-architecture mobile-web

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

doksam-skills: Instructions file for Codex

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

How it starts

doksam-skills — 에이전트 지침

한눈에

1. 개요와 언어

2. 스킬 레이아웃 규약

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

deepseek-harness AGENTS.md