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 sodam-ai/SoDam-Persona --skill persona-safetygit clone --depth 1 https://github.com/sodam-ai/SoDam-PersonaWrote 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/sodam-ai/sodam-persona/persona-safety)<a href="https://agentmods.dev/skills/sodam-ai/sodam-persona/persona-safety"><img src="https://agentmods.dev/badge/skills/sodam-ai/sodam-persona/persona-safety/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/sodam-ai/sodam-persona/persona-safety"><img src="https://agentmods.dev/badge/skills/sodam-ai/sodam-persona/persona-safety.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 | $0.00069 | $0.00898 |
| Opus 5 | $0.00034 | $0.00449 |
| Sonnet 5 | $0.00014 | $0.00180 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
persona-safety 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
정본 안내: 메타 규칙의 정본은 항상켜짐 코어(persona_core.md). 이 스킬은 코드/UI/보안 작업 상세다.
페르소나 안전 작업 (v5)
코어(persona_core.md) 파일 맵에 따라 코드·UI·보안 작업 시 로드.
강도 무관, 항상 적용.
보안 (Always-On)
- API 키·토큰·비밀번호·환경변수·권한·민감 데이터 → 즉시 경계
- 보안은 선택 아닌 기본값
- 개인정보·라이선스·외부 데이터 처리 시 #11 법무 관점 자동 활성
- 민감정보 노출 점검 위치: 코드, GitHub, 로그, 화면 출력, 문서, 커밋 기록, 에러 메시지
- 보안은 나중에 처리할 부가 작업 X. 설계·구현 단계에서 함께 반영
비가역 작업 (반드시 사전 확인)
다음 작업은 자동 실행 절대 금지, 사용자 확인 필수:
- 파일·디렉터리 삭제 (rm, rmdir 등)
- git 강제 푸시 (
--force,--force-with-lease) - 데이터베이스 변경 (drop, truncate, 마이그레이션)
- 프로덕션 배포
- 결제·금융 관련 작업
- 외부 메시지 발송 (이메일·SMS·Slack·Discord 등)
- 글로벌 설정 변경 (
~/.claude/CLAUDE.md,~/.gitconfig등)
사용자가 모르고 위험한 길로 가면 즉시 멈추고 알림.
코드 작업 메타 규칙
- 이전에 편집한 파일 재편집 시 Read 선행 필수 (stale old_string 방지) —
feedback_edit_stale_content.md - if/else 분기 추가 시 cleanup/finally/shutdown 경로의 변수 사용 가드 확인 (UnboundLocalError 방지) —
feedback_cleanup_path_audit.md - 은폐성 우회 금지:
--no-verify,--force,ts-ignore,eslint-disable등 —feedback_fail_safe_continue.md - 클로드코드 터미널 함부로 닫지 말 것 (작업/충돌 시에도) —
feedback_no_close_terminal.md
UI 작업 (UI 트리거 시 자동 적용)
- 데스크톱뿐 아니라 모바일 뷰(375px) 반드시 함께 검증 —
feedback_mobile_first.md - 터치 타겟 (최소 44×44px), hover 대체, 햄버거 메뉴 동시 수정 체크
- 반응형 깨짐, 텍스트 잘림, 가로 스크롤 발생 여부 확인
테스트·로컬 서버
- HTML/웹 테스트 시 로컬 포트는 1601 사용 —
feedback_test_port.md - GitHub AI Explorer 프로젝트 전용 포트는 7719 —
feedback_port_8809.md
외부 도구 도입 검토 (라이브러리·MCP·플러그인·확장 프로그램)
새로운 외부 도구 도입 시 다음 4가지 함께 검토:
- 신뢰성 — 공식 출처/유지보수 활성도/스타·다운로드 수
- 유지보수성 — 마지막 업데이트·이슈 응답 속도·버전 정책
- 보안 위험 — 권한 요구·민감정보 접근·알려진 취약점
- 실제 필요성 — 기존 도구로 해결 가능한지·과잉 의존 위험
기존 32개 메모리 파일·17개 프로젝트 컨텍스트와 충돌하면 보고 후 사용자 위임.
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 · 63 lines · 69 tokens per session scan A 17564f800326
persona-safety is a skill published in the GitHub repository sodam-ai/SoDam-Persona (17 stars, last pushed 11d ago), licensed Apache-2.0. It adds 69 tokens to every session and 898 once invoked, about $0.0003 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 skills, from other repositories
writing-style
Use for technical communication - GitHub/GitLab tickets, PR/MR descriptions, issue comments, code review comments, commit messages. Direct, brief style with no AI-speak. NOT for README.md, public docs, or blog posts.
root-cause-investigator
Systematic root cause analysis for errors, bugs, and unexpected behaviors using 5-Why methodology. Use when user reports errors, build failures, test failures, performance issues, integration problems, or any "it's not working" scenarios.
go
Execute a refined 3-doc (handoff, spec, plan) produced by ready: wave-based parallel implementation with right-sized verification (test-first where it fits), spec-first review, and integration gates. Use when the user invokes the go skill after ready wrote the 3-doc. Requires git.
goal
Run a large or unfamiliar goal through the full ballast pipeline — mobilize what you already hold, terrain scan, full skeleton, atomic foundation learning with verification, then build from bedrock to a verified done. Use when the user hands over a big goal, enters a new field, or asks to learn X in order to achieve Y.
proof-standard
Never make an external-facing claim about a product without evidence from a truth file. Use when writing marketing copy, announcements, docs, landing pages, investor material, or answering "can our product do X".
rehearsal
Test a deliverable on a zero-context reader before it ships. Use before shipping any document, guide, kit, or handoff meant to work without you, and before calling a deliverable done in goal Phase 5.