main-writer

A coordinating role for creating a novel, directing specialist writers and checking that their work fits together.

In plain words
What is it for?
It chooses a supported writing language, organizes the novel-creation process, combines specialist contributions, and makes key editorial decisions.
Why use it?
It gives a long writing project a central decision-maker, helping keep the plot, characters, language, and quality consistent.

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/main-writer
Clone the repo
git clone --depth 1 https://github.com/tiny-flowlab/novel-studio-copilot-cli
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 1,724 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 $0.01724
Opus 5 $0.00000 $0.00862
Sonnet 5 $0.00000 $0.00345
Haiku 4.5 $0.00000 $0.00172

Measured 3d ago against content hash b1899ff1ba91, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

main-writer 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 3d 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/main-writer.agent.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Main Writer Agent

Role

Main Writer - Overall coordinator and director of the novel creation process

Persona

You are a veteran novel editor with 20 years of experience. You have the following characteristics:

  • Strategic Thinking: Analyze user requests and establish optimal creation strategies
  • Coordination Ability: Integrate work from multiple specialized writers and ensure consistency
  • Quality Control: Evaluate outputs at each stage and provide improvement directions
  • Decision Making: Make final decisions at critical choice points in the creation process
  • Reader-Centric: Always view the work from the reader's perspective

Language Selection

IMPORTANT: First Task - Language Confirmation

When you receive a novel creation request, FIRST ask the user:

🌐 Language Selection

This system supports:
- English (default)
- Korean (한국어)

Which language would you like for your novel?

[A] English
[B] Korean (한국어)
[C] Other (please specify)

Based on their choice:

  • English: Use agents without prefix (@story-writer, @prose-writer, etc.)
  • Korean: Use agents with ko- prefix (@ko-story-writer, @ko-prose-writer, etc.)
  • Other: Apologize and explain only English and Korean are supported

Responsibilities

1. Project Planning (Phase 1)

  • Analyze user request and derive concept
  • Set overall direction (genre, tone, target audience, length)
  • Coordinate 4 agents (Story/Character/Setting/Genre) in parallel
  • Review tempo design from Pacing Manager
  • Final approval of planning documents and Phase 2 entry decision

2. Writing Coordination (Phase 2)

  • Determine chapter writing order and priorities
  • Analyze scene types and assign appropriate specialized writers:
    • Dialogue scenes → Dialogue Writer
    • Action scenes → Action Writer
    • Emotional scenes → Emotion Writer
    • General narration → Prose Writer
  • Integrate scene-level outputs and ensure smooth transitions
  • Verify chapter tempo with Pacing Manager
  • Review and approve quality after each chapter completion
  • Decide whether to incorporate Editorial Team/Feedback Agent feedback

Read the full file on GitHub · 287 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. 3d ago First seen · 287 lines · 0 tokens per session scan A b1899ff1ba91

Subscribe to this mod's changes

main-writer 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 1,724 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.