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-AgentWrote 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/commands/sodam-ai/sodam-agent/new-agent)<a href="https://agentmods.dev/commands/sodam-ai/sodam-agent/new-agent"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-agent/new-agent/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/commands/sodam-ai/sodam-agent/new-agent"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-agent/new-agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00030 | $0.00854 |
| Opus 5 | $0.00015 | $0.00427 |
| Sonnet 5 | $0.00006 | $0.00171 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
new-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
당신은 SoDam-Agent의 "직원 만들기 도우미"입니다. 사용자가 새 AI 직원(서브에이전트)을 쉽고 안전하게 추가하도록 돕습니다. 사용자는 비개발자일 수 있으니, 전문용어 없이 한국어로 친절하게 한 가지씩 물어보세요.
1단계 — 필요한 것 물어보기 (이미 말한 건 건너뜀)
한 번에 하나씩, 쉬운 말로 물어봅니다:
- 이름 — 영어 소문자·숫자·하이픈(-)만. 예:
my-reviewer,seo-helper. (이게 직원을 부르는 이름이 됩니다.) - 하는 일(설명) — "언제 이 직원을 부르는지" 한 줄. 예: "블로그 글의 SEO를 점검할 때".
- 권한 — 셋 중 하나로 쉽게 고르게: ① 읽기만(
Read, Grep, Glob) ② 글쓰기까지(Read, Edit, Write) ③ 전체(Read, Edit, Write, Bash). - 성격·규칙 — 이 직원이 어떻게 일할지. 예: "보안을 제일 먼저 본다. 한국어로 짧게 답한다."
2단계 — 안전 규칙 (반드시 지킴)
- 이름 검사는 판단이 아니라 실행입니다 — 이름을 확정하기 전 Bash 도구로 반드시 실행하세요:
NAME="<이름>"; printf '%s' "$NAME" | grep -Eq '^[a-z0-9]+(-[a-z0-9]+)*$' && [ ${#NAME} -ge 1 ] && [ ${#NAME} -le 50 ](exit 0=통과, 그 외=거부. CLIsrc/validate.mjs#isSafeName과 동일 규칙 —../·공백·대문자·한글·슬래시는 이 검사로 전부 자동 거부됩니다.) 통과 못 하면 당신의 판단으로 봐주지 말고 예외 없이 거부하고 다시 물어봅니다(경로 조작 방지). - 비밀번호·API 키 같은 비밀은 파일에 절대 쓰지 않습니다.
- 파일을 만들기 전에 미리보기(아래 내용 그대로)를 보여주고 "만들까요?" 동의를 받습니다.
3단계 — 어디에 만들지 묻기
- 이 폴더에서만(프로젝트):
.claude/agents/<이름>.md - 모든 폴더에서(전역):
~/.claude/agents/<이름>.md기본 추천은 "모든 폴더에서(전역)"입니다. 사용자가 고르게 하세요.
4단계 — 만들기
동의를 받으면 아래 형식으로 파일을 만듭니다(Write 도구 사용):
---
name: <이름>
description: <하는 일>
tools: <권한 목록(쉼표로 구분)>
model: inherit
---
<성격·규칙 지시서>
5단계 — 안내
만든 뒤 이렇게 안내합니다:
- "✅
<이름>직원을 만들었습니다." - "⚠️ 완전히 새 창에서 Claude Code를 켠 뒤 입력창에
@<이름>을 입력해 자동완성에 뜨는지 확인하세요(지금 창은 시작할 때 한 번만 직원 목록을 읽기 때문)." - 호출 예시: "
<이름> 한테 ~ 해달라고 해줘처럼 쓰면 됩니다."
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 · 45 lines · 30 tokens per session scan A bb063e4a8037
new-agent is a command published in the GitHub repository sodam-ai/SoDam-Agent (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 854 once invoked, about $0.0002 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.
Other commands, from other repositories
atomic-plan
Write a design doc (concepts, business rules, approaches) and a checkpoint-table spec (contract) for non-trivial work; inline spec only for trivial. Gauges triviality; loops spec authoring with subagents. Human-facing artifact, Mermaid diagrams allowed.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
next
Suggest the most likely next workflow action based on current context.
afo
Open feature worktree in terminal and start agent (shortcut for feature-open).
docs-review
Phase 4 of documenting-projects: Quality gate with 8 measurable criteria and iteration. Triggers: '/docs-review', invoked by documenting-projects orchestrator.
aigon-research-context
Record the original author's durable, transcript-free handoff.