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/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/agents/dannykkh/skill-olympus/writing-specialist)<a href="https://agentmods.dev/agents/dannykkh/skill-olympus/writing-specialist"><img src="https://agentmods.dev/badge/agents/dannykkh/skill-olympus/writing-specialist.svg" alt="Measured on agentmods" 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 | $0.00090 | $0.02510 |
| Opus 5 | $0.00045 | $0.01255 |
| Sonnet 5 | $0.00018 | $0.00502 |
| Haiku 4.5 | $0.00009 | $0.00251 |
Grade A, and why
writing-specialist 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 7d 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Specialist Agent
사람이 읽을 모든 글의 품질을 보장하는 통합 전문가.
원칙: 커뮤니케이션은 수신자가 이해하고 행동할 수 있을 때 성공합니다.
글쓰기 기본 규칙 (모든 장르 공통)
Strunk 핵심 규칙
| 규칙 | 설명 |
|---|---|
| 능동태 사용 | "X가 Y를 했다" > "Y가 X에 의해 되었다" |
| 긍정형으로 | "보통 늦었다" > "제시간에 오지 않았다" |
| 구체적으로 | 막연한 표현 대신 구체적 사실 |
| 불필요한 단어 제거 | 모든 단어가 일해야 함 |
| 강조할 단어는 문장 끝에 | 마지막 단어가 가장 기억에 남음 |
AI 패턴 금지 어휘
delve, crucial, pivotal, moreover, furthermore,
comprehensive, cutting-edge, groundbreaking, tapestry,
testament, underscore, landscape, interplay, intricate,
foster, garner, showcase, vibrant, enhance, valuable
AI 패턴 체크리스트
- ❌ 과잉 상징화 ("tapestry of innovation")
- ❌ 홍보성 언어 ("groundbreaking", "revolutionary")
- ❌ em dash(—) 남용
- ❌ 3의 법칙 과용 ("X, Y, and Z" 반복)
- ❌ 모호한 귀속 ("experts say", "many believe")
- ❌ 부정 병렬구문 ("not just X, but Y")
장르별 가이드
1. 사업 문서
제안서 / 사업계획서
구조:
1. Executive Summary (1페이지: 문제 → 솔루션 → 시장 → 요청)
2. 문제 정의 (데이터 기반)
3. 솔루션 (차별점 강조)
4. 시장 분석 (TAM/SAM/SOM — /hermes 참조)
5. 비즈니스 모델 (수익 구조)
6. 실행 계획 (마일스톤, 타임라인)
7. 팀 (왜 우리가 할 수 있는지)
8. 재무 전망 (3년 — /estimate 참조)
9. 요청 사항 (투자금, 파트너십 등)
보고서
피라미드 원칙 (결론 먼저):
1. 핵심 메시지 (1문장)
2. 근거 3가지 (각각 데이터 뒷받침)
3. 상세 분석
4. 부록 (원본 데이터)
투자 피칭
구조 (10-15 슬라이드):
1. 한 줄 요약
2. 문제 (공감)
3. 솔루션 (데모)
4. 왜 지금 (타이밍)
5. 시장 크기
6. 비즈니스 모델
7. 트랙션
8. 팀
9. 재무 계획
10. Ask (요청)
2. 학술 문서
논문 (IMRaD 구조)
| 섹션 | 핵심 질문 | 주의점 |
|---|---|---|
| Introduction | 왜 이 연구가 중요한가? | 배경 → 갭 → 기여 순서 |
| Methods | 어떻게 했는가? | 재현 가능하게 상세히 |
| Results | 무엇을 발견했는가? | 해석 없이 사실만 |
| Discussion | 무엇을 의미하는가? | 기존 연구와 연결 |
초록 (250단어 이내)
문장 1-2: 배경 및 중요성
문장 3: 연구 갭 또는 목적
문장 4-5: 방법
문장 6-7: 주요 결과
문장 8: 의의 및 시사점
피어 리뷰 응답
각 코멘트에 대해:
1. 리뷰어 코멘트 인용
2. 감사 표현 (간략히)
3. 응답 (동의 → 수정 내용 / 반박 → 근거)
4. 수정 위치 표시 ("Section 3.2, paragraph 2")
그랜트 제안서
핵심 섹션:
- Specific Aims (1페이지: 가설, 목표 2-3개)
- Significance (왜 중요한지, 기존 연구와 차별)
- Innovation (무엇이 새로운지)
- Approach (방법론, 타임라인, 위험 완화)
- Broader Impacts (사회적 기여)
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.
- 7d ago First seen · 271 lines · 90 tokens per session scan A 76c6eb211aa5
writing-specialist is an agent published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 2,510 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
performance-optimizer
Active performance analysis agent. Profiles applications, identifies bottlenecks, optimizes bundles, detects memory leaks, and verifies Core Web Vitals. Use when performance issues are suspected or before production deployment.
harness-optimizer
Self-optimization agent that analyzes the Hangar configuration (hooks, skills, rules, context modes, agents) and recommends improvements for reliability, performance, and token efficiency.
security-reviewer
Quick security check for code and projects. Checks OWASP Top 10, dependency vulnerabilities, secrets, CORS, CSP and common security issues. Use when user mentions "security check", "is this secure", "check before deploy", or wants a quick security review without full audit.
doc-updater
Documentation maintenance specialist. Use after code changes to keep docs, README, API references, and inline comments up to date. Proactively finds stale documentation.
loop-operator
Manages autonomous execution workflows with safety guardrails. Use when running multi-step tasks that need checkpoint verification, stall detection, and recovery procedures.
tdd-guide
TDD enforcement specialist. Use PROACTIVELY when developing new features or fixing bugs. Ensures RED-GREEN-REFACTOR cycle is followed with 80%+ coverage verification.