What is write-article?

A workflow for creating a roundup article that compares several services. It uses source material and project examples to guide the writing and review.

Use it to turn an input file into a service roundup, following the project's editorial style and saving the work in a defined output folder.

It organizes the work of researching, drafting, and checking a comparison article without relying on separate review agents.

write-article — Skill for Claude Code and Codex by mikeshu2001: A workflow for creating a roundup article that compares…

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 skills/mikeshu2001/content-factory/write-article

Any agent

npx skills add mikeshu2001/content-factory --skill write-article

Clone the repo

git clone --depth 1 https://github.com/mikeshu2001/content-factory

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mikeshu2001/content-factory/write-article.svg)](https://agentmods.dev/skills/mikeshu2001/content-factory/write-article)

Your own site

<a href="https://agentmods.dev/skills/mikeshu2001/content-factory/write-article"><img src="https://agentmods.dev/badge/skills/mikeshu2001/content-factory/write-article.svg" alt="Measured on agentmods" height="20"></a>

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,101 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.

Model	Per session	Once invoked
Fable 5	$0.00015	$0.02101
Opus 5	$0.00008	$0.01051
Sonnet 5	$0.00003	$0.00420
Haiku 4.5	$0.00002	$0.00210

Measured 4d ago against content hash 70f5b2e07c3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-article 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.

skills/write-article/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Создание статьи-подборки сервисов

Запусти полный цикл создания статьи-подборки.

Исходный материал: $ARGUMENTS

Что важно понимать про этот процесс

Главный инструмент качества — твоя проверка в основном контексте, не агенты. Раньше в цепочке были агенты plan-checker, text-checker, final-reviewer — они вылизывали текст по чек-листам и делали его механическим, не видя полной картины. Теперь эти этапы делаешь ты: читаешь и правишь сам. Ты видишь весь текст целиком, помнишь историю разговора с пользователем и знаешь примеры — поэтому именно ты ловишь книжные конструкции, дубли, расхождения с данными исследования.

Перед тем как писать — прочитай 1–2 подборки из examples/articles/, если они есть. Стиль формируется из примеров, а не из правил. Если примеров нет, работай по ред-политике и профилю проекта.

Рабочая папка

Определи имя рабочей папки из имени исходного файла:

Возьми имя файла из $ARGUMENTS (без пути к директории и без расширения .md)
Рабочая папка: output/[имя файла]/
Создай папку командой: mkdir -p output/[имя файла]/

Все агенты сохраняют файлы в эту рабочую папку. Передавай путь к ней каждому агенту.

Параметры для всех агентов

Тип контента: article
Скилл с ред-политикой: redpolicy-article (файл skills/redpolicy-article/SKILL.md)
Правила письма: skills/good-writing/SKILL.md и skills/good-writing/antipatterns.md
Папка с примерами: examples/articles/

Шаг 1: Исследование сервисов

Используй подагента article-researcher. Передай ему: путь к исходнику ($ARGUMENTS), рабочую папку.

Результат: файл research.md в рабочей папке с актуальными данными о каждом сервисе.

Шаг 2: Планирование

Используй подагента planner. Передай ему: путь к исходнику ($ARGUMENTS), путь к research.md в рабочей папке (дополнительный исходный материал с актуальными данными о сервисах), тип контента (article), путь к ред-политике, рабочую папку, путь к папке с примерами (прочитать 1–2 примера перед составлением плана).

Важно: planner использует ОБА файла — оригинальный исходник и research.md. Данные из research.md актуальнее.

Read the full file on GitHub · 123 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.

4d ago First seen · 123 lines · 15 tokens per session scan A 70f5b2e07c3a

Subscribe to this mod's changes

write-article is a skill published in the GitHub repository mikeshu2001/content-factory (21 stars, last pushed 21d ago), licensed MIT. It adds 15 tokens to every session and 2,101 once invoked, about $0.0001 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 2026-08-30.

Writing and docs agentic-workflows ai-agents content-creation editorial-workflow multi-agent-systems prompt-engineering

agents-best-practices

Use this skill when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, environment-adaptive tools, speculative tool execution…

DenisSergeevitch/agents-best-practices · 125 tokens

loop-library

Compatibility alias for Loopy. Use only when an existing installation or older instruction explicitly invokes loop-library; use Loopy for new installations and requests. Provides the same discovery, recommendation, audit, repair, adaptation, guided crafting, bounded execution, run debrief, project loop saving, and…

Forward-Future/loopy · 65 tokens

write-article