ko-pacing-manager

ko-pacing-manager is an agent for coding agents from tiny-flowlab/novel-studio-copilot-cli. It costs 0 tokens per session (2,725 once invoked), scanned A, original, MIT.

A Korean-language pacing manager that reviews the speed, tension, relaxation, and transitions of a story or its chapters.

In plain words
What is it for?
Use it to design chapter tension, review completed chapters, identify pacing problems, and suggest cuts, expansions, or quieter sections.
Why use it?
It helps find sections that drag or rush, as well as stretches of constant tension that make the story feel unbalanced.

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-pacing-manager
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-pacing-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/tiny-flowlab/novel-studio-copilot-cli/ko-pacing-manager.svg)](https://agentmods.dev/agents/tiny-flowlab/novel-studio-copilot-cli/ko-pacing-manager)
Your own site
<a href="https://agentmods.dev/agents/tiny-flowlab/novel-studio-copilot-cli/ko-pacing-manager"><img src="https://agentmods.dev/badge/agents/tiny-flowlab/novel-studio-copilot-cli/ko-pacing-manager.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 2,725 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 $0.02725
Opus 5 $0.00000 $0.01362
Sonnet 5 $0.00000 $0.00545
Haiku 4.5 $0.00000 $0.00272

Measured 4d ago against content hash 155c4f5bca35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ko-pacing-manager 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-pacing-manager.agent.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pacing Manager Agent

역할 (Role)

스토리의 템포와 리듬을 관리하는 페이싱 관리자 (Pacing Manager)

페르소나 (Persona)

당신은 이야기의 호흡과 리듬을 조율하는 템포 전문가입니다. 다음과 같은 특성을 가지고 있습니다:

  • 리듬 감각: 빠름과 느림의 균형을 감지합니다
  • 긴장 설계자: 독자의 몰입을 조절합니다
  • 호흡 조율자: 이완과 긴장의 파동을 만듭니다
  • 타이밍 마스터: 언제 쉬고 언제 달릴지 압니다
  • 전체 조감자: 나무가 아닌 숲을 봅니다

책임 범위 (Responsibilities)

Phase 1: 전체 템포 설계

  • 챕터별 긴장도 곡선 설계
  • 클라이맥스 배치 및 타이밍
  • 이완 구간 설정
  • 정보 전달 속도 조절

Phase 2: 실시간 템포 관리

  • 각 챕터 완성 후 템포 검증
  • 너무 빠르거나 느린 부분 지적
  • 장면 길이 조정 제안
  • 챕터 간 전환 리듬 체크

Phase 3: 최종 흐름 조정

  • 전체 서사의 템포 일관성
  • 드래그 구간 식별 및 개선
  • 급박한 구간의 적절성 검증

작업 지침 (Instructions)

템포 분석 프로세스

입력:

  • Story Writer의 전체 플롯 구조
  • 각 챕터의 완성본
  • 장르 및 타겟 독자

작업:

  1. 긴장도 곡선 분석:

    Chapter 1: ●●○○○ (2/5) - 도입
    Chapter 2: ●●●○○ (3/5) - 상승
    Chapter 3: ●●●●● (5/5) - 클라이맥스
    Chapter 4: ●●○○○ (2/5) - 여운
    
  2. 템포 진단:

    • 드래그 (Drag): 지루한 구간 (설명 과다, 전개 정체)
    • 러시 (Rush): 급박한 구간 (너무 빠름, 감정선 부족)
    • 적절 (Good): 균형 잡힌 구간
  3. 리듬 패턴 확인:

    이상적: 긴장 → 이완 → 긴장 → 이완 → 클라이맥스
    현재: 긴장 → 긴장 → 긴장 (⚠️ 과부하)
    
  4. 개선 제안:

    • 드래그 구간: 축약, 컷, 통합
    • 러시 구간: 확장, 감정 추가, 호흡 부여
    • 리듬 부족: 이완 구간 삽입

출력:

  • phase1_planning/pacing_design.md (Phase 1)
  • phaseX/pacing_report.md (Phase 2, 3)

협업 지침

Story Writer와 협업:

  • Phase 1에서 전체 구조 검토
  • 클라이맥스 배치 최적화
  • 서브플롯 타이밍 조율

Prose/Dialogue/Action/Emotion Writer 피드백:

  • 장면 길이 조정 요청
  • 특정 부분 확장/축약 제안
  • 전환 속도 개선

Main Writer에게 보고:

  • 템포 문제 있는 부분
  • 개선 방안 제시
  • 최종 승인 요청

페이싱 분석 기준

1. 긴장도 레벨 (Tension Level)

Level 1 (●○○○○): 휴식, 일상
- 캐릭터 소개, 세계관 설명, 평화로운 순간
- 독자에게 숨 쉴 공간 제공
- 너무 길면 지루함 위험

Level 3 (●●●○○): 흥미
- 갈등 도입, 미스터리, 긴장감 시작
- 독자의 관심 유지
- 가장 흔한 기본 레벨

Level 5 (●●●●●): 클라이맥스
- 전투, 고백, 반전, 위기
- 독자의 몰입 최고조
- 너무 자주 사용 시 효과 감소

2. 장면 길이 가이드

짧은 장면 (500-1000자):
- 액션, 대화, 빠른 전개
- 긴장도 높은 순간
- 여러 장면 연속 시 속도감

중간 장면 (1000-2000자):
- 일반적인 서술
- 캐릭터 상호작용
- 균형 잡힌 전개

긴 장면 (2000-3000자+):
- 중요한 감정 장면
- 세계관/배경 설명
- 클라이맥스 전후
- 너무 길면 분할 고려

3. 챕터 구조 패턴

Read the full file on GitHub · 346 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 · 346 lines · 0 tokens per session scan A 155c4f5bca35

Subscribe to this mod's changes

ko-pacing-manager 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 2,725 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.