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 domain-dictionarygit 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/domain-dictionary)<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/domain-dictionary"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/domain-dictionary/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/dannykkh/skill-olympus/domain-dictionary"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/domain-dictionary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Prompt Injection · line 175 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 180 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00103 | $0.03826 |
| Opus 5.5 | $0.00041 | $0.01530 |
| Sonnet 5.5 | $0.00021 | $0.00765 |
| Haiku 4.5 | $0.00010 | $0.00383 |
Grade A, and why
domain-dictionary 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 1mo 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Dictionary (도메인사전)
Eric Evans의 Domain-Driven Design — Ubiquitous Language 개념을 한국 SI/현장의 영-한 혼용 환경에 맞게 적용. 한 프로젝트 안에서 개발자, 도메인 전문가, 사업 담당자가 같은 단어를 같은 뜻으로 쓰도록 강제하는 사전.
적용 시점
| 시점 | 진입점 |
|---|---|
| 신규 기능 계획 시 | zephermine이 Spec Synthesis 직후 자동 호출 |
| 기존 코드베이스 분석 시 | /domain-dictionary 직접 호출 |
| 코드 리뷰 시 | code-reviewer가 domain-dictionary.md 위반을 검출 |
| 신규 멤버 온보딩 시 | domain-dictionary.md 한 장이 첫 자료 |
첫 실행 시 동작
스킬 첫 실행 시 글로벌 폴더를 자동 생성하고 references/global-readme-template.md를 README.md로 복사합니다. 기본 위치는 ~/.agent-memory/domain-dictionaries/이며, AGENT_DOMAIN_DICTIONARY_HOME 환경 변수가 있으면 그 값을 우선합니다. 사용자가 install.bat/install.sh를 다시 실행하지 않아도 됩니다.
처음에는 글로벌 도메인 파일들이 비어있습니다(ecommerce.md, healthcare.md 등). 시간이 흐르면서 zephermine 컨텍스트 모드의 명확한 범용 용어 또는 사용자의 직접 선택으로 누적됩니다 — 의도된 설계.
질문 도구 호환성
CLI마다 질문 도구 스키마가 다릅니다. Invalid tool parameters를 피하기 위해 기본은 일반 텍스트 번호 목록입니다.
- zephermine 컨텍스트 모드에서는 질문하지 않는 것이 기본입니다. 충돌 용어가 DB/API/타입/UI/보안/정책을 바꿀 때만 한 질문씩 묻습니다.
- 직접 호출 모드(
/domain-dictionary)에서는 사용자가 사전 점검을 요청한 것이므로 핵심 충돌이나 수정 후보를 물을 수 있습니다. - 구조화 질문 도구는 짧은 단일/소수 선택에만 사용합니다.
- 한 번에 최대 3개 질문, 질문당 2-3개 짧은 선택지만 보냅니다.
- 다중 선택은 기본적으로 "1, 3, 5처럼 번호로 답해주세요" 방식으로 받습니다. 구조화 다중 선택 필드는 현재 CLI가 명시 지원할 때만 사용합니다.
- 도구 오류가 한 번 나면 같은 payload를 재시도하지 말고 일반 텍스트 질문으로 전환합니다.
사전의 두 종류 (글로벌 + 프로젝트)
| 종류 | 위치 | 역할 |
|---|---|---|
| 글로벌 | ~/.agent-memory/domain-dictionaries/{도메인}.md |
사용자 자산 — 자주 다루는 도메인의 누적 용어 (참고용 씨앗) |
| 프로젝트 (마스터) | <project>/docs/domain-dictionary.md |
진실의 원천 — 이 프로젝트만의 확정 사전 |
| 프로젝트 (델타) | <project>/docs/plan/{feature}/domain-dictionary-delta.md |
이번 feature에서 추가/변경된 이력 (zephermine 산출물) |
글로벌 사전 폴더 구조
~/.agent-memory/domain-dictionaries/
├── README.md ← 사용 안내 + 도메인 분류 가이드
├── ecommerce.md ← Cart, Order, SKU, Fulfillment...
├── healthcare.md ← Patient, Encounter, Diagnosis...
├── finance.md ← Position, Settlement, Counterparty...
└── general.md ← 도메인 무관 (User, Session, Audit...)
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.
- 1mo ago First seen · 281 lines · 103 tokens per session scan A 1921369ecc9e
domain-dictionary is a skill published in the GitHub repository Dannykkh/skill-olympus (7 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 3,826 once invoked, about $0.0004 per session on Opus 5.5. 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
factory-close
Close out a Linear issue — move to Done, add a closing comment, and clean up the local branch/worktree.
factory-submit
Move the current branch's Linear issue to "In Review".
audit-project
Audits the Claude Code configuration of a project against the dotforge template. Generates a report with score and gaps.
init-project
Quick-start Claude Code configuration. Auto-detects stack, asks 4 questions to understand the project, generates complete config.
domain-extract
Extract domain knowledge from existing project sources and generate domain rules. Also handles vault sync and domain listing.
rule-effectiveness
Cross-reference .claude/rules/ globs against git history to find inert rules and uncovered directories. Content quality and context cost are native — run /doctor prompt-audit and /skill-doctor for those.