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 skills add Insajin/autopus-adk --skill writing-skillsgit clone --depth 1 https://github.com/Insajin/autopus-adkWrote 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/skills/insajin/autopus-adk/writing-skills)<a href="https://agentmods.dev/skills/insajin/autopus-adk/writing-skills"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/writing-skills/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.
<a href="https://agentmods.dev/skills/insajin/autopus-adk/writing-skills"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/writing-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00021 | $0.01016 |
| Opus 5 | $0.00010 | $0.00508 |
| Sonnet 5 | $0.00004 | $0.00203 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
writing-skills 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 8d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Skills
명확하고 유용한 기술 문서와 OMP 구성 요소를 작성하는 스킬입니다.
OMP 스킬 작성 (2.0+)
스킬 파일 구조
스킬은 .omp/skills/<skill-name>/SKILL.md 에 정의합니다.
프론트매터 필드
표준 필드:
| 필드 | 필수 | 설명 |
|---|---|---|
name |
Yes | 스킬 식별자 (소문자, 하이픈) |
description |
Yes | 목적 설명 (YAML folded scalar > 사용, 최대 1024자) |
allowed-tools |
No | 쉼표 구분 도구 목록 (자동 승인) |
user-invocable |
No | / 메뉴 노출 여부 (기본: true) |
effort |
No | 모델 effort 오버라이드: low, medium, high |
model |
No | 모델 오버라이드: opus, sonnet, haiku |
context |
No | "fork" — 포크된 서브에이전트에서 실행 |
agent |
No | context: fork 시 사용할 서브에이전트 타입 |
hooks |
No | 스킬 스코프 라이프사이클 훅 |
disable-model-invocation |
No | true — OMP 자동 로딩 방지 |
주의: CC 2.1.19부터 allowed-tools가 없는 스킬은 도구 사용 시 사용자 승인이 필요합니다.
템플릿 변수
$ARGUMENTS— 사용자가 전달한 전체 인자$ARGUMENTS[N]/$N— N번째 위치 인자${CLAUDE_SKILL_DIR}— 스킬 자체 디렉터리 경로 (모듈 참조에 유용)
스킬 예시
---
name: my-skill
description: >
스킬이 하는 일을 설명합니다.
여러 줄은 YAML folded scalar (>)를 사용합니다.
allowed-tools: Read, Grep, Glob, Bash
user-invocable: true
effort: medium
---
# My Skill
스킬 본문 내용...
OMP 에이전트 작성 (2.0+)
에이전트 정의 가이드는 subagent-dev 스킬을 참조하세요.
핵심 프론트매터: name, description, model, tools, permissionMode, maxTurns, skills, isolation, background, memory
문서 유형별 가이드
README 작성
# 프로젝트명
한 줄 설명
## 설치
\```bash
go get github.com/...
\```
## 빠른 시작
\```go
// 핵심 사용 예시
\```
## API
[주요 API 설명]
## 기여하기
[기여 방법]
API 문서
각 엔드포인트에 대해:
- Method: HTTP 메서드
- Path: URL 경로
- Request: 요청 형식 (Body, Params)
- Response: 응답 형식
- Errors: 에러 코드 목록
- Example: 실제 예시
기술 설계 문서
## 문제 정의
[해결할 문제]
## 제약 조건
[기술적, 비즈니스 제약]
## 설계 결정
[결정 사항과 이유]
## 대안 검토
[고려한 대안과 기각 이유]
## 구현 계획
[단계별 구현 계획]
작성 원칙
독자 중심
- 독자가 누구인가? (초보자 vs 전문가)
- 독자가 무엇을 알고 싶어하는가?
- 독자가 무엇을 하고 싶어하는가?
명확성
- 짧은 문장 (20단어 이하 권장)
- 능동태 사용
- 전문 용어는 처음 사용 시 정의
실용성
- 모든 개념에 예시 포함
- 복사-붙여넣기 가능한 코드 스니펫
- 실제 사용 시나리오 기반
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.
- 8d ago First seen · 146 lines · 21 tokens per session scan A c5449db361af
writing-skills is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 1,016 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
automations
Create, inspect, edit, archive, delete, run, and search scheduled or executable automation assets.
job
Execution behavior for one saved automation job running in a fresh agent conversation.
api-interface-design
Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.
Using OmniForge Framework
Primary guide for using OmniForge CLI, MCP Server, workflows, and agent skills effectively.
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
windows-deployment
Deploy FastAPI + React/Vite apps to Windows Server with NSSM services, reverse proxy (IIS or nginx), and git-pull workflow. Use when deploying any web app to a Windows prod server, setting up NSSM services, configuring IIS or nginx reverse proxy, making code environment-aware for dev/prod, or troubleshooting prod…