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.
git clone --depth 1 https://github.com/sodam-ai/SoDam-Prompt-EngWrote 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/plugins/sodam-ai/sodam-prompt-eng/sodam-prompt-eng)<a href="https://agentmods.dev/plugins/sodam-ai/sodam-prompt-eng/sodam-prompt-eng"><img src="https://agentmods.dev/badge/plugins/sodam-ai/sodam-prompt-eng/sodam-prompt-eng/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/plugins/sodam-ai/sodam-prompt-eng/sodam-prompt-eng"><img src="https://agentmods.dev/badge/plugins/sodam-ai/sodam-prompt-eng/sodam-prompt-eng.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sodam-prompt 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 12d 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.
What it actually says
{
"name": "sodam-prompt",
"displayName": "SoDam Prompt",
"version": "0.1.0",
"description": "AI 처음 쓰는 초보자를 위한 한국어 글쓰기 스킬 10종 — 독후감·정중한 메시지·긴글 3줄요약·쉽게 설명·공부 계획표·자기소개 다듬기·SNS 캡션·영어 변환·발표 대본·부탁·사과 메시지. 슬래시 커맨드와 자연어 둘 다 지원.",
"author": {
"name": "SoDam AI Studio"
},
"license": "Apache-2.0",
"keywords": ["education", "korean", "student", "writing", "beginner", "prompt-engineering"],
"skills": ["./skills/"]
}
What it installs
The manifest is a name and a version. 11 skills, 11 commands travel with it, and installing the plugin installs all of them — 728 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill skill-maker A 53 tokens
- Skill study-planner A 0 tokens
- Skill book-report-helper A 0 tokens
- Skill explain-simply A 0 tokens
- Skill long-text-summary A 49 tokens
- Skill natural-english A 50 tokens
- Skill polite-message A 0 tokens
- Skill presentation-script A 0 tokens
- Skill request-apology-message A 0 tokens
- Skill self-intro-polish A 0 tokens
- Skill sns-caption A 0 tokens
- Command skill-maker A 50 tokens
- Command long-text-summary A 45 tokens
- Command presentation-script A 56 tokens
- Command explain-simply A 53 tokens
- Command self-intro-polish A 54 tokens
- Command sns-caption A 54 tokens
- Command book-report-helper A 59 tokens
- Command study-planner A 45 tokens
- Command natural-english A 46 tokens
- Command polite-message A 57 tokens
- Command request-apology-message A 57 tokens
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 13 lines scan A ba2dacd58075
sodam-prompt is a plugin published in the GitHub repository sodam-ai/SoDam-Prompt-Eng (1 stars, last pushed 11d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
sodam-reverse
A Korean-language Claude Code plugin for defensive and educational reverse engineering, which means examining how software works.
humanizer-kr
Korean-specialized writing skill for rewriting AI-sounding Korean into natural, source-grounded Korean.
lecture-deck-kit
A plugin for building and editing self-contained HTML lecture slide decks in a browser. It lets you select text on a slide and describe the change in chat.
learnus-course-copilot
A course assistant for LearnUs, Yonsei University’s online learning platform, used with the “오늘의 연세·포털 연결” add-on’s browser login. It organizes lectures, assignment deadlines, and study materials.
yonsei-academic-copilot
An academic-planning assistant for Yonsei University students, including Underwood students. It uses official academic information and student-specific details such as student number and major.
yonsei-course-registration
A course-registration helper for Yonsei University's public Underwood course catalogue, written in Korean. It can also use personal mileage history, available seats, and graduation importance when needed.