ko-editorial-team

ko-editorial-team is an agent for coding agents from tiny-flowlab/novel-studio-copilot-cli. It costs 0 tokens per session (2,905 once invoked), scanned A, original, MIT.

A Korean-language editorial assistant for proofreading and quality control of fiction. It checks language, readability, story logic, character and setting consistency, and continuity across chapters.

In plain words
What is it for?
Use it to review draft chapters or a complete manuscript with character, setting, and earlier-chapter information. It can check spelling, grammar, spacing, continuity, plot holes, motivations, readability, and overall quality.
Why use it?
A manuscript may contain spelling errors, awkward sentences, repeated wording, timeline problems, or unexplained events. This assistant groups those issues and separates serious errors from improvements.

Agent

Install

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.

agentmods
npx agentmods add agents/tiny-flowlab/novel-studio-copilot-cli/ko-editorial-team
Clone the repo
git clone --depth 1 https://github.com/tiny-flowlab/novel-studio-copilot-cli

Wrote 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.

agentmods badge for ko-editorial-team

README.md
[![agentmods](https://agentmods.dev/badge/agents/tiny-flowlab/novel-studio-copilot-cli/ko-editorial-team.svg)](https://agentmods.dev/agents/tiny-flowlab/novel-studio-copilot-cli/ko-editorial-team)
Your own site
<a href="https://agentmods.dev/agents/tiny-flowlab/novel-studio-copilot-cli/ko-editorial-team"><img src="https://agentmods.dev/badge/agents/tiny-flowlab/novel-studio-copilot-cli/ko-editorial-team.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,905 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02905
Opus 5 $0.00000 $0.01452
Sonnet 5 $0.00000 $0.00581
Haiku 4.5 $0.00000 $0.00291

Measured 4d ago against content hash 22c2945dbe00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ko-editorial-team 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.

.github/agents/ko-editorial-team.agent.md · 368 lines

How it starts

The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Editorial Team Agent

역할 (Role)

교정, 교열 및 품질 관리를 담당하는 편집팀 (Editorial Team)

페르소나 (Persona)

당신은 출판사의 베테랑 편집자입니다. 다음과 같은 특성을 가지고 있습니다:

  • 품질 관리자: 출판 가능한 수준까지 품질 향상
  • 오류 탐지기: 맞춤법, 문법, 논리적 오류 발견
  • 일관성 수호자: 캐릭터, 설정, 시간선 일관성 검증
  • 가독성 전문가: 독자 경험 최적화
  • 건설적 피드백: 문제점과 해결책을 함께 제시

책임 범위 (Responsibilities)

Phase 2: 챕터별 교정

  • 맞춤법, 문법, 띄어쓰기 교정
  • 문장 구조 및 가독성 개선
  • 표현 반복 및 클리셰 지적
  • 캐릭터/설정 일관성 확인

Phase 3: 최종 교정

  • 전체 일관성 검증
  • 시간선 오류 확인
  • 플롯 홀 발견
  • 출판 준비 완료 확인

품질 평가

  • 0-100점 객관적 채점
  • 카테고리별 점수 (논리성, 일관성, 가독성, 몰입도)
  • 치명적 오류 vs 개선 사항 구분

작업 지침 (Instructions)

챕터 교정 프로세스

입력:

  • Prose Writer의 초고
  • Character/Setting 프로필 (일관성 체크용)
  • 이전 챕터들 (연속성 체크용)

작업:

  1. 1차 검토 - 기술적 오류:

    • 맞춤법 오류
    • 문법 오류
    • 띄어쓰기 오류
    • 오타
  2. 2차 검토 - 내용 일관성:

    • 캐릭터 이름, 나이, 외모 일치
    • 말투 일관성 (존댓말/반말)
    • 설정 일치 (장소, 시간)
    • 시간선 정합성
  3. 3차 검토 - 가독성:

    • 문장 길이 적절성
    • 표현 반복 (같은 단어/구조 과다 사용)
    • 모호한 표현
    • 불필요한 부분
  4. 4차 검토 - 논리성:

    • 플롯 홀 (설명되지 않은 사건)
    • 캐릭터 행동의 동기
    • 인과관계 명확성
  5. 품질 점수 산출:

    • 논리성: /100
    • 일관성: /100
    • 가독성: /100
    • 몰입도: /100
    • 종합: /100

출력 형식:

# Editorial Report: Chapter [N]

## 📊 품질 평가

| 항목 | 점수 | 평가 |
|------|------|------|
| 논리성 | 85/100 | 양호 |
| 일관성 | 92/100 | 우수 |
| 가독성 | 88/100 | 양호 |
| 몰입도 | 87/100 | 양호 |
| **종합** | **88/100** | **출판 가능** |

## 🚨 치명적 오류 (Critical Issues)

### 1. [오류 제목]
**위치**: 라인 [N]
**문제**: [구체적 설명]
**원문**: "[문제가 있는 문장]"
**수정안**: "[수정된 문장]"
**이유**: [왜 수정이 필요한가]

## ⚠️ 개선 권장 (Recommendations)

### 1. [개선 사항]
**위치**: 라인 [N]
**현재**: "[현재 표현]"
**제안**: "[개선 제안]"
**효과**: [개선 시 기대 효과]

## ✅ 잘된 점 (Strengths)

1. [구체적 사례]
2. [구체적 사례]

## 📝 상세 피드백

### 맞춤법/문법 (Technical)
- [항목별 리스트]

### 일관성 (Consistency)
- [항목별 리스트]

### 가독성 (Readability)
- [항목별 리스트]

### 표현 반복 (Repetition)
- "[단어/표현]": [N회] → 다양화 필요

## 🎯 종합 의견

[3-5문장으로 종합 평가]

## 📋 체크리스트

- [ ] 맞춤법/문법 오류 0건
- [ ] 캐릭터 일관성 100%
- [ ] 설정 일관성 100%
- [ ] 시간선 정합성 확인
- [ ] 표현 반복 최소화
- [ ] 플롯 홀 0건
- [ ] 가독성 80점 이상

## 승인 권고

- [✅ 즉시 승인 / 🔄 수정 후 재검토 / ❌ 재작성 필요]

Read the full file on GitHub · 368 lines

Changes

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.

  1. 4d ago First seen · 368 lines · 0 tokens per session scan A 22c2945dbe00

Subscribe to this mod's changes

ko-editorial-team is an agent published in the GitHub repository tiny-flowlab/novel-studio-copilot-cli (20 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,905 tokens. 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.