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 agentmods add agents/dannykkh/skill-olympus/writing-guidelinesgit 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-guidelines)<a href="https://agentmods.dev/agents/dannykkh/skill-olympus/writing-guidelines"><img src="https://agentmods.dev/badge/agents/dannykkh/skill-olympus/writing-guidelines.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 | $0.00037 | $0.00955 |
| Opus 5 | $0.00018 | $0.00477 |
| Sonnet 5 | $0.00007 | $0.00191 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
writing-guidelines 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 4d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Guidelines (Optional Reference)
명시적으로 불러 쓰는 글쓰기 참고 규칙. Strunk 핵심 규칙 + AI 글쓰기 패턴 24개 제거 + 영혼 있는 글쓰기.
Strunk's Core Rules
| 규칙 | 설명 |
|---|---|
| 능동태 사용 | "X가 Y를 했다" > "Y가 X에 의해 되었다" |
| 긍정형으로 | "그는 보통 늦었다" > "그는 보통 제시간에 오지 않았다" |
| 구체적으로 | 막연한 표현 대신 구체적 사실 |
| 불필요한 단어 제거 | 간결하게 |
| 관련 단어는 가깝게 | 수식어는 수식 대상 근처에 |
| 강조어는 문장 끝에 | 중요한 내용을 마지막에 |
AI 패턴 제거
금지 어휘
delve, crucial, pivotal, moreover, furthermore,
comprehensive, cutting-edge, groundbreaking, tapestry,
testament, underscore, landscape, interplay, intricate,
foster, garner, showcase, vibrant, enhance, valuable,
game-changing, revolutionary, paradigm, synergy,
leverage, robust, seamless, streamline, utilize
8대 안티패턴
| # | 패턴 | ❌ Before | ✅ After |
|---|---|---|---|
| 1 | 과장된 중요성 | "a pivotal moment in regional statistics" | "established in 1989 to collect regional statistics" |
| 2 | 서술형 -ing | "highlighting its importance, ensuring reliability" | 삭제하거나 구체적 사실로 대체 |
| 3 | 홍보성 언어 | "nestled within the breathtaking region" | "a town in the Gonder region" |
| 4 | 모호한 출처 | "Experts believe it plays a crucial role" | "according to a 2019 survey by [specific source]" |
| 5 | Rule of Three | "innovation, inspiration, and industry insights" | 필요한 것만 나열 |
| 6 | Em Dash 남용 | "not by the people—yet this continues—even in" | 쉼표 또는 문장 분리 |
| 7 | 부정 병렬 | "It's not just X, it's Y" | 직접 진술 |
| 8 | 협업 흔적 | "I hope this helps! Let me know if..." | 삭제 |
영혼 있는 글쓰기
패턴 제거만으로는 부족. 개성이 필요하다:
- 의견 제시: 중립 나열보다 반응을 보여라
- 리듬 변화: 짧은 문장. 그리고 긴 문장으로 숨을 쉬게 하라.
- 복잡성 인정: "인상적이지만 불안하기도 하다"
- 1인칭 사용: "계속 생각나는 건..."
- 약간의 어수선함: 완벽한 구조 = 알고리즘적
Before (깔끔하지만 무미건조)
The experiment produced interesting results. The agents
generated 3 million lines of code.
After (생기 있음)
솔직히 이건 어떻게 받아들여야 할지 모르겠다. 300만 줄의 코드,
아마 인간들이 자는 동안 생성된. 개발자 절반은 열광하고,
절반은 왜 의미 없는지 설명 중이다.
Checklist
- 능동태인가?
- 구체적 사실이 있는가?
- 불필요한 단어가 없는가?
- AI 어휘를 사용하지 않았는가?
- -ing 서술 문구를 제거했는가?
- Em dash를 최소화했는가?
- 소리 내어 읽으면 자연스러운가?
- 개성/의견이 포함되어 있는가?
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.
- 4d ago First seen · 98 lines · 37 tokens per session scan A 9b6a9e1f8388
writing-guidelines is an agent published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 955 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 2026-08-31.
Other agents, from other repositories
document-steward
GOAL: One document per domain. Minimum tokens for maximum clarity.
strategy-fidelity-voc
Evaluates app fidelity and completion against docs/SYSTEMARCHITECTURE.md and domain references. Serves as voice of customer: defines user workflows and outcomes, then validates implementation against them. Use proactively before releases, after major changes, or when validating feature completeness.
cross-project-memory
Designs and executes efficient cross-project and long-term memory so agents build apps better. Use when adding or improving memory that spans projects, sessions, or runs; when defining what to remember, how to scope it, and how to retrieve it for agent context.
architect
Software architecture lead for hybrid systems using traditional architecture (Next.js + PostgreSQL) and AI-agent-supportive architecture (ruvector). Use proactively for system design, module boundaries, interfaces, migration plans, and architecture trade-offs.
investigator
investigates a bug to identify root cause and set success criteria for resolution; creates investigation report for fixer agent to guide implementation.
ai-advocate
Audits the project for poor AI agent behaviors and recommends concrete improvements to make coding workflows more agent-friendly, reliable, and fast. Use proactively when agents struggle, loop, miss context, or produce inconsistent changes.