agentmods.dev

create

create is a command for Claude Code from sodam-ai/SoDam-Persona. It costs 45 tokens per session (2,075 once invoked), scanned A, original, Apache-2.0.

An interactive command for creating a new specialist persona for an AI coding workspace. It asks questions, suggests trigger words, updates related files, and validates the result.

In plain words
What is it for?
It is for adding a new expert viewpoint, such as one for healthcare, property, or education, to the persona system.
Why use it?
It removes the need to manually design a persona, choose when it should activate, and keep several configuration files in sync.

Command for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: $skill-name invocation.

Part of the sodam-persona plugin — 9 skills, 2 commands, 2 hooks shipped together

not rated 20repo +3 9d ago A scan 45 tokens original Apache-2.0

Good fit It is for adding a new expert viewpoint, such as one for healthcare, property, or education, to the persona system.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/sodam-ai/sodam-persona/create
View source ↗ sodam-ai/SoDam-Persona
Install

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.

Clone the repo
git clone --depth 1 https://github.com/sodam-ai/SoDam-Persona

Made for: Claude Code.

Or install sodam-persona, the plugin that ships this one along with the rest of its 9 skills, 2 commands, 2 hooks.

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.

agentmods badge for create

README.md
[![agentmods](https://agentmods.dev/badge/commands/sodam-ai/sodam-persona/create/github.svg)](https://agentmods.dev/commands/sodam-ai/sodam-persona/create)
Your own site
<a href="https://agentmods.dev/commands/sodam-ai/sodam-persona/create"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-persona/create/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.

agentmods 80×15 button for create

Your own site · 80×15
<a href="https://agentmods.dev/commands/sodam-ai/sodam-persona/create"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-persona/create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,075 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.02075
Opus 5 $0.00023 $0.01038
Sonnet 5 $0.00009 $0.00415
Haiku 4.5 $0.00005 $0.00208

Measured 10d ago against content hash df6cdcb7651e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

create 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 10d 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.

plugins/sodam-persona/commands/create.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

$persona-create — 새 페르소나 생성 (인터뷰 방식)

이 명령이 실행되면 아래 순서를 하나씩, 인터뷰 형식으로 진행한다. 한 번에 여러 질문을 던지지 말고, 답을 받은 뒤 다음 질문으로 넘어간다.

0단계. 사전 확인

  • plugins/sodam-persona/skills/persona-triggers/SKILL.md를 읽어 ## B. 섹션 표에서 현재 마지막 관점 번호(N)를 확인한다.
  • 같은 파일에서 ## ([A-Z])\. 형태의 마지막 알파벳 섹션 글자를 확인한다(현재 A~T).
  • 새 관점 번호 = N+1, 새 패턴 알파벳 = 다음 알파벳 1글자.

1단계. 인터뷰 (한 번에 하나씩)

  1. "새 페르소나가 다룰 전문 분야가 무엇인가요? (예: 의료·건강, 부동산, 교육 등 한글로)"
  2. "영문 폴더/파일 이름에 쓸 짧은 영어 슬러그를 정해주세요 (예: doctor, realestate). 소문자·하이픈만."
    • 입력값 검증(필수): 답변이 ^[a-z][a-z0-9-]*$ 형식(소문자로 시작, 소문자·숫자·하이픈만, 공백·슬래시(/)·역슬래시·마침표 2개 연속(..)·특수문자 없음)이 아니면 파일 경로에 절대 사용하지 말고, "영문 소문자와 하이픈만 사용해주세요 (예: doctor)"라고 다시 요청한다. 이 슬러그는 곧바로 plugins/sodam-persona/skills/persona-<슬러그>/ 폴더 경로에 쓰이므로, 검증 없이 그대로 사용하면 경로 조작(path traversal) 위험이 있다.
  3. "이 페르소나가 답변할 때 챙겨야 할 책임 영역을 간단히 알려주세요 (몇 가지 항목이어도 됩니다)."
  4. "이 도메인이 신고·계약·처방·진단처럼 '실행성 답변'을 다뤄서, #14(회계세무)·#11(법률)처럼 면책 문구가 반드시 필요한 영역인가요? (예/아니오)"

2단계. 추천 트리거 단어 생성

13단계 답변을 바탕으로, 기존 도메인 섹션(J 투자·K 법률·S 회계세무·T 마케팅, persona-triggers/SKILL.md 참고)과 같은 형식으로 **한국어 트리거 단어 1530개를 직접 생성**해 보여준다. 사용자에게 "이대로 등록할까요? 추가/삭제하고 싶은 단어가 있나요?"라고 확인한다. 확정 전까지는 파일을 건드리지 않는다.

3단계. 파일 반영 (확정 후에만, 순서대로)

  1. plugins/sodam-persona/skills/persona-triggers/SKILL.md
    • ## B. 표에 새 행 추가: | N+1 | <도메인명> (15년+) | <트리거 표현들> |
    • 새 알파벳 섹션(예: ## U. "<도메인>" 도메인 패턴 → #N+1 <도메인> 페르소나 활성) 추가 — J/K/S/T 섹션과 동일 구조(트리거 단어군 / 책임 영역 / PR 체크리스트 / 다른 관점과의 경계)
    • frontmatter description과 본문의 A~T 20패턴 표기를 A~<새글자> <새패턴수>패턴으로 갱신
    • "매칭 예시" 표에 새 도메인 예시 1줄 추가
  2. plugins/sodam-persona/hooks/persona_core.md
    • "도메인 트리거 (조건부 활성)" 섹션에 새 도메인 소단원 추가 (트리거 단어·책임 영역, 기존 4개와 동일 형식)
    • 면책 필요 시 "[면책 강제]" 섹션에 새 도메인 추가
    • "15명 다관점 균형 검토"의 "15개 도메인 관점" 목록에 새 관점 이름 추가, 숫자를 N+1로 갱신
    • "파일 맵" 표의 도메인 스킬 목록에 persona-<슬러그> 추가
  3. plugins/sodam-persona/hooks/persona_marker.txt
    • "도메인 (조건부)" 한 줄 문구에 새 도메인 트리거·활성 문구 추가 (persona_core.md와 동일 내용)
    • "persona-* 자동 활성" 목록에 persona-<슬러그> 추가
    • 면책 필요 시 "[도메인 면책 강제]" 항목에 새 도메인 추가
  4. plugins/sodam-persona/skills/persona-<슬러그>/SKILL.md (신규 생성)
    • persona-investor/persona-lawyer/persona-accountant/persona-marketer 중 하나를 그대로 구조 참고: frontmatter(name=폴더명과 반드시 일치, description) → 정본 안내 → 트리거 단어군 → 필요 시 "⚠️ 필수 면책" 박스 → 책임 영역 → PR/작업 체크리스트 → 다른 관점과의 경계
  5. plugins/sodam-persona/skills/persona-format/SKILL.md
    • "다관점 판단 (15개)" 제목과 목록에 새 관점 추가, 숫자 갱신
  6. plugins/sodam-persona/reference/persona_full_core.md, plugins/sodam-persona/reference/test_scenarios.md
    • 관점 수 숫자 표기 갱신 (validate.mjs가 이 두 파일도 검사 대상에 포함함)
  7. README.md / README.en.md (2개 전부. 2026-07-27부로 GUIDE.md/GUIDE.en.md는 폐지되어 README에 통합됨)
    • "15명"/"15개 관점"/"15 perspectives" 등 전부 새 숫자로
    • "20개 트리거 패턴(A~T)" → 새 글자·새 개수로
    • "스킬 7개"/"Skills (7)" → 새 개수로
    • 관점 목록·업데이트 내용 요약에 새 도메인 한 줄 추가
  8. validate.mjs
    • DOMAINS 배열(현재 ['persona-investor', 'persona-lawyer', 'persona-accountant', 'persona-marketer'])에 persona-<슬러그> 추가 (이래야 5번 검사가 새 도메인도 배선 확인함)

Read the full file on GitHub · 74 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.

  1. 10d ago First seen · 74 lines · 45 tokens per session scan A df6cdcb7651e

Subscribe to this mod's changes

create is a command published in the GitHub repository sodam-ai/SoDam-Persona (20 stars, last pushed 9d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,075 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.

Building agentsClaude Codeai-assistantclaude-code-pluginhookskoreanmarketplace
Related

Other commands, from other repositories

patterns

List makoto's integrity pattern catalog (read-only).

Clear-Sights/Makoto · 11 tokens

generate-report

Generate a professional HTML report from assessment results in the conversation.

sigistry/marketplace · 11 tokens

data-flow-analysis

Trace how data flows through the system from input to output.

sigistry/marketplace · 11 tokens

improve-test-quality

Analyze and improve existing test quality with better assertions, coverage, and maintainability.

sigistry/marketplace · 15 tokens

test-gap-analysis

Identify untested code paths and missing test coverage across the codebase.

sigistry/marketplace · 13 tokens

format-converter

Convert between data formats (JSON, CSV, YAML, XML, TOML, Excel). Bidirectional conversion with schema preservation and intelligent type handling.

sigistry/marketplace · 29 tokens