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 agentmods add instructions/dalestudy/skills/agents-mdgit clone --depth 1 https://github.com/DaleStudy/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/instructions/dalestudy/skills/agents-md)<a href="https://agentmods.dev/instructions/dalestudy/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/dalestudy/skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.01618 | $0.01618 |
| Opus 5 | $0.00809 | $0.00809 |
| Sonnet 5 | $0.00324 | $0.00324 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
skills 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 4d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Overview
DaleStudy 커뮤니티의 Agent Skills 모음집. AI 코딩 어시스턴트(Claude Code, Cursor, GitHub Copilot)용 재사용 가능한 스킬 정의를 제공한다.
이 저장소는 빌드 과정 없는 순수 콘텐츠 저장소다. 각 스킬은 SKILL.md 파일로 정의되며, 배포 시 단순히 ZIP으로 압축되어 dist/ 디렉토리에 .skill 확장자로 저장된다.
Development Commands
스킬 테스트 (로컬)
# 로컬 저장소에서 특정 스킬 설치 테스트
npx skills add . --skill bun --agent claude-code --global --yes
# Bun 사용 시
bunx skills add . --skill bun --agent claude-code --global --yes
설치 후 ~/.agents/skills/{skill-name} 및 ~/.claude/skills/{skill-name} (심볼릭 링크)에서 확인 가능
배포 방식
이 저장소는 GitHub를 통해 직접 배포된다. npx skills add dalestudy/skills는:
- GitHub 저장소 클론
skills/디렉토리에서 SKILL.md 파일 읽기- 선택한 스킬을
~/.agents/skills/에 설치
별도 빌드/패키징 과정 없음. skills/{skill-name}/SKILL.md 파일을 수정하면 즉시 배포된다.
CI 테스트
GitHub Actions가 자동으로 실행됨 (스케줄: 매일 11:00, 23:00 UTC):
- 모든 스킬의 설치 가능성 검증
.github/workflows/ci.yml의matrix.skill배열에 명시된 스킬만 테스트 대상
새 스킬 추가 시 CI 업데이트 필수: matrix.skill 배열에 스킬명 추가
Repository Architecture
스킬 구조
각 스킬은 Agent Skills 스펙을 따른다:
skills/{skill-name}/
└── SKILL.md # YAML frontmatter + Markdown 지시사항 (필수)
핵심 원칙:
- SKILL.md는 실행 가능한 지시사항이자 메타데이터를 포함
description필드는 스킬 활성화 조건을 명확히 기술 (파일 패턴, 키워드, 사용 상황)allowed-tools는 스킬이 요구하는 도구 권한을 선언 (예:Bash(bun:*))
SKILL.md 작성 규칙
---
name: skill-name
description: "스킬 설명 + 활성화 조건. 다음 상황에서 사용: (1) ..., (2) ..., (3) ..."
license: MIT
compatibility: 필요한 CLI 도구 (예: Requires bun CLI)
metadata:
author: DaleStudy
version: "1.0"
allowed-tools: Bash(command:*) Bash(another:*) # 공백으로 구분
---
# 스킬 제목
스킬 지시사항 (Markdown)
중요:
description은 AI 에이전트가 언제 이 스킬을 사용할지 판단하는 주요 기준- 구체적인 파일 패턴 (
.stories.tsx), 키워드 (bun,CSF), 사용 상황을 명시 allowed-tools는 권한 프롬프트 최소화를 위해 정확히 기술
배포 구조
스킬은 GitHub 저장소를 통해 직접 배포된다:
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.
- 4d ago First seen · 171 lines · 1,618 tokens per session scan A 535f5b946e26
skills AGENTS.md is an instructions file published in the GitHub repository DaleStudy/skills (4 stars, last pushed 4mo ago), licensed MIT. It adds 1,618 tokens to every session, about $0.0081 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.
Other instructions, from other repositories
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
bread CLAUDE.md
Instructions for tjakoen/bread, covering claude.md — start here, what this is, start here (reading order), this repo is the stack's control plane — run it and non-negotiables (see conventions for the full rules).
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
rosetta command-versions-vs-presence.instructions.md
Instructions for tikoci/rosetta, a project described as: MCP Server with RouterOS docs + commands + products + changelogs, using SQLite-as-RAG, sourced from MikroTik.
ob-1 AGENTS.md
Instructions for Overbrilliant/ob-1, covering agents.md, project index, stack, commands and key files.
bxc GEMINI.md
Instructions for aphrody-code/bxc: This repository's operating guide is CLAUDE.md — read it first.