write

write is a command for coding agents from BitYoungjae/marketplace. It costs 47 tokens per session (2,940 once invoked), scanned A, original, MIT.

A command that writes one learning-document section through a research, writing, and review process. It can adapt the content to technology, history, science, arts, or general subjects.

In plain words
What is it for?
Use it to write the next incomplete section from task.md or a named section from the command arguments. It reads the project plan and audience details, gathers research, writes the section, and reviews it.
Why use it?
It removes the need to manually find the next unfinished section and coordinate separate research and editing steps. It also checks the project context before writing.

Command

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

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

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 write

README.md
[![agentmods](https://agentmods.dev/badge/commands/bityoungjae/marketplace/write.svg)](https://agentmods.dev/commands/bityoungjae/marketplace/write)
Your own site
<a href="https://agentmods.dev/commands/bityoungjae/marketplace/write"><img src="https://agentmods.dev/badge/commands/bityoungjae/marketplace/write.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,940 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 $0.00047 $0.02940
Opus 5 $0.00023 $0.01470
Sonnet 5 $0.00009 $0.00588
Haiku 4.5 $0.00005 $0.00294

Measured 4d ago against content hash 2de693f095ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write 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.

plugins/dokhak/commands/write.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Document

Write the next incomplete section from task.md, or a specific section if provided via $ARGUMENTS.

Context Files

  • Persona: @persona.md
  • Project Context: @project-context.md

Current State

  • Next task: !grep -m1 "\[ \]" task.md 2>/dev/null || echo "No task.md found"

Process

1. Identify Target Section and Parse Flags

CRITICAL: Parse flags from $ARGUMENTS first:

skip_review = $ARGUMENTS.includes("--skip-review")
use_glm_tools = $ARGUMENTS.includes("--glm") ? "true" : "false"
section_id = $ARGUMENTS.replace("--skip-review", "").replace("--glm", "").trim()

If section_id is empty after flag removal, parse task.md for the first [ ] item.

Extract:

  • Section ID (e.g., "3.2")
  • Section title

2. Get Section Details and Domain

Read plan.md and extract details for the target section:

  • Full title
  • Estimated page count
  • Subtopics to cover
  • Part/Chapter context

Read persona.md and extract domain information:

  • Domain (from Domain Guidelines section header, e.g., "Domain Guidelines: Technology" → technology)
  • If no Domain Guidelines section, default to "technology" for backward compatibility

Domain values: technology, history, science, arts, general

3. Resolve Research Directory

CRITICAL: Use multi-tier search to find existing research directories. This handles naming inconsistencies from different generation sources.

3.1 Normalize Identifiers

Apply normalization functions from research-storage skill:

# Extract chapter and section from section ID (e.g., "1.2" or "01-2")
raw_chapter = extract_chapter(section_id)
raw_section = extract_section(section_id)

# Normalize to canonical format
canonical_chapter = normalizeChapter(raw_chapter)
  # "1" → "01", "01" → "01", "10" → "10"

canonical_section = normalizeSection(raw_section)
  # "1" → "1", "01" → "1", "02" → "2"

canonical_slug = generateSlug(section_title)
  # "Core Concepts" → "core-concepts"
  # "What is React?" → "what-is-react"

canonical_path = ".research/sections/{canonical_chapter}-{canonical_section}-{canonical_slug}/"

Read the full file on GitHub · 392 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 · 392 lines · 47 tokens per session scan A 2de693f095ab

Subscribe to this mod's changes

write is a command published in the GitHub repository BitYoungjae/marketplace (6 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 2,940 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.