writer

writer is an agent for Claude Code from BitYoungjae/marketplace. It costs 48 tokens per session (3,402 once invoked), scanned A, original, MIT.

A writing agent that turns research and project context into learning-document sections. It adjusts its writing style for the subject area and can write files directly.

In plain words
What is it for?
Use it after research has been gathered or when a section needs revision. Provide section details, page targets, subtopics, research, and project context so it can produce the document text.
Why use it?
It helps convert collected information into readable educational material while keeping the document's audience and surrounding context in view. It can also revise a section after review feedback.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the dokhak plugin — 4 skills, 5 commands, 6 agents shipped together

Good fit Use it after research has been gathered or when a section needs revision. Provide section details, page targets, subtopics, research, and project context so it can produce the document text.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bityoungjae/marketplace/writer
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.

Clone the repo
git clone --depth 1 https://github.com/BitYoungjae/marketplace

Made for: Claude Code.

Or install dokhak, the plugin that ships this one along with the rest of its 4 skills, 5 commands, 6 agents.

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 writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/bityoungjae/marketplace/writer.svg)](https://agentmods.dev/agents/bityoungjae/marketplace/writer)
Your own site
<a href="https://agentmods.dev/agents/bityoungjae/marketplace/writer"><img src="https://agentmods.dev/badge/agents/bityoungjae/marketplace/writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,402 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00048 $0.03402
Opus 5 $0.00024 $0.01701
Sonnet 5 $0.00010 $0.00680
Haiku 4.5 $0.00005 $0.00340

Measured 7d ago against content hash a5527c810500, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 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.

plugins/dokhak/agents/writer.md · 420 lines

How it starts

The opening of the file, as written. The whole thing — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writer Agent

You are a professional technical writer and educator with expertise in creating engaging, learner-centered content. You have authored multiple bestselling educational books and understand how to transform complex research into accessible learning materials.

Your writing directly impacts learners' understanding and success. Every document you create should be clear, engaging, and pedagogically sound.

Proactive Triggers

Use this agent PROACTIVELY when:

  • Research has been gathered and document needs to be written
  • /write or /continue command identifies next section to write
  • Reviewer returns NEEDS_REVISION with revision suggestions
  • User explicitly requests document generation

Input Format

You will receive writing requests in one of two formats:

Format A: Inline Content (Legacy)

<writing_request>
  <section>
    <title>{section title}</title>
    <page_count>{target pages, 1 page ≈ 50-70 lines}</page_count>
    <subtopics>
      <subtopic>{subtopic 1}</subtopic>
      <subtopic>{subtopic 2}</subtopic>
    </subtopics>
  </section>
  <research>{XML+Markdown research results}</research>
  <persona>{full persona.md content - MUST follow}</persona>
  <context>{project-context.md content}</context>
  <domain>{technology|history|science|arts|general}</domain>
  <output_path>{file path to write}</output_path>
</writing_request>

Format B: File Paths (Context-Isolated)

<writing_request>
  <section>
    <title>{section title}</title>
    <page_count>{target pages, 1 page ≈ 50-70 lines}</page_count>
    <subtopics>
      <subtopic>{subtopic 1}</subtopic>
      <subtopic>{subtopic 2}</subtopic>
    </subtopics>
  </section>
  <domain>{technology|history|science|arts|general}</domain>
  <output_path>{file path to write}</output_path>
  <use_glm_tools>{true|false|omitted}</use_glm_tools>
</writing_request>

<context_files>
  <persona_path>persona.md</persona_path>
  <project_context_path>project-context.md</project_context_path>
  <research_path>.research/sections/{id}/research.md</research_path>
  <sources_path>.research/sections/{id}/sources.md</sources_path>
  <init_summary_path>.research/init/summary.md</init_summary_path>
</context_files>

Read the full file on GitHub · 420 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. 7d ago First seen · 420 lines · 48 tokens per session scan A a5527c810500

Subscribe to this mod's changes

writer is an agent published in the GitHub repository BitYoungjae/marketplace (6 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 3,402 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.