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 Dannykkh/skill-olympus --skill themisgit clone --depth 1 https://github.com/Dannykkh/skill-olympusWrote 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/dannykkh/skill-olympus/themis)<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/themis"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/themis.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 180 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00122 | $0.04054 |
| Opus 5 | $0.00061 | $0.02027 |
| Sonnet 5 | $0.00024 | $0.00811 |
| Haiku 4.5 | $0.00012 | $0.00405 |
Grade A, and why
themis 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 5d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Themis — 코드 감사 기반 개인정보처리방침 생성 (테미스)
대상 프로젝트의 실제 코드에서 개인정보를 받거나·저장하거나·외부로 보내는 지점을 전수 감사하고, 감사에서 확인된 사실만으로 국가별 개인정보처리방침 초안을 생성합니다.
테미스는 정의의 저울을 든 티타니스 — 코드에 있는 것만 달아서 적고, 없는 것은 지어내지 않습니다.
적용 시점
/themis명시적 실행 (별칭: 테미스)- "개인정보처리방침 만들어줘", "privacy policy 초안", "개인정보 수집 지점 찾아줘" 요청 시
- 앱스토어/플레이스토어 제출, 서비스 오픈, GDPR 대응 준비 시
핵심 원칙 (절대 규칙)
| # | 원칙 | 설명 |
|---|---|---|
| 1 | 추측 금지 | 모든 감사 항목에 file:line 근거. 코드에서 확인 못 하면 "확인 안 됨"으로 표기 |
| 2 | 지어내지 않기 | 코드에 없는 방침 항목은 [빈칸: 무엇을 채워야 하는지]로 남기고 채움 안내 제공 |
| 3 | 법적 판단 분리 | 법률 해석이 필요한 지점(위탁 vs 제3자 제공, 적용 대상 여부 등)은 [확인 필요: 법률 검토] 표시 |
| 4 | 법률 자문 아님 | 모든 산출물 서두에 "법률 자문이 아닌 초안, 시행 전 전문가 검토 권장" 고지 필수 |
Step 1: 개인정보 전수 감사
프로젝트 전체를 5가지 질문으로 감사합니다. 규모가 크고 네이티브 위임이 가능하면 질문 또는
독립 디렉터리 단위로 읽기 전용 탐색 역할을 배정합니다. 각 역할은 코드를 수정하지 않고
file:line 근거와 미확인 범위만 반환합니다. 특정 커스텀 에이전트 이름이나 vendor별 spawn 형식을
요구하지 않습니다. 위임 기능이 없거나 실패하면 메인 컨텍스트에서 5문항을 하나씩 순차 조사합니다.
감사 결과 병합, 중복 제거, 운영자 인터뷰, 방침 파일 작성은 메인 스킬 하네스가 담당합니다.
어느 경로든 file:line 근거 없는 항목은 버립니다.
감사 5문항
- 어떤 정보를 받는가 — 이메일, 이름, 전화번호, 사진, 위치, 접속기록, 대화/입력 내용, 세션 ID, 결제정보, 기기 식별자 등 전부
- 어디에 저장하는가 — 로컬 파일/DB/클라우드, 정확한 경로·테이블
- 받을 때 동의 절차가 있는가 — opt-in/opt-out, 동의 UI, 마스킹, 비활성화 플래그
- 외부로 나가는 정보가 있는가 — 로그인 연동(OAuth), 통계 도구, 결제, AI API 호출, 푸시, 크래시 리포트
- 지우는 기능이 있는가 — 회원 탈퇴 시 실제 삭제 여부, 보존 기한, 자동 파기
grep 힌트 (시작점, 전부는 아님)
| 관점 | 패턴 |
|---|---|
| 수집 | email, phone, birth, gender, address, geolocation, getCurrentPosition, camera, contacts, user_id, session |
| 저장 | INSERT INTO, localStorage, AsyncStorage, UserDefaults, SharedPreferences, S3, bucket, ORM 모델(User/Member/Account/Profile) |
| 동의 | consent, agree, terms, opt, gdpr, privacy |
| 외부 전송 | fetch, axios, requests., http, analytics, gtag, ga4, firebase, posthog, sentry, mixpanel, amplitude, stripe, iamport, toss, oauth, openai, anthropic, googleapis, webhook |
| 삭제 | delete, withdraw, deactivate, purge, retention, TTL, soft_delete |
What ships with it
3 files beside SKILL.md 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.
- 5d ago First seen · 198 lines · 122 tokens per session scan A 890c1faf8fd3
themis is a skill published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 4,054 once invoked, about $0.0006 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
opensource-readiness
Pre-publication audit for repositories about to go public or already public. Catches what other skills miss: secrets in git history (not just HEAD), license compliance, internal references (private URLs, internal hostnames, employee names), trademark exposure, attribution gaps, and community-readiness gaps…
audit-orchestrator
Universal Pre-Scan → Analysis → Optimization → Report orchestrator for ANY project type — web apps (Astro/SvelteKit/Next), infrastructure/homelab repos, CLI tools, libraries, backend services, monorepos, data/ML projects, docs. Self-detects project type and runs the matching analysis track. Session state lives in…
capture-pdf
Website-to-PDF capture (all pages + interactive states). Use when: "capture", "pdf", "print", "screenshot", "capture pages".
audit
Systematic website audit (stack detection, 9 phases). Use when: "audit", "website audit", "site audit", "check website".
consult
Interactive project consultant. Scans your project, asks targeted questions, and creates a structured improvement plan.
freshness-check
Pipeline source freshness check (frameworks, tools, standards). Use when: "freshness", "update check", "is everything current", "check versions".