article-structure-review

article-structure-review is a skill for Claude Code from AnastasiyaW/codex-claude-code-config. It costs 93 tokens per session (1,890 once invoked), scanned A, original, MIT.

A structural review checklist for technical articles after the first draft and before final editing. It checks whether important claims have supporting evidence, whether the article stays in the intended genre, and whether it includes limitations.

In plain words
What is it for?
Use it to audit each major section of a technical article and compare its claims with its proof. It fits into a workflow that starts with planning and drafting, then continues with style and human-sounding language checks.
Why use it?
It catches gaps that sentence-level editing can miss, such as making several claims without examples, numbers, case studies, code, or sources. It helps separate structural problems from later style and wording edits.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-code-config plugin — 57 skills, 8 agents shipped together

Good fit Use it to audit each major section of a technical article and compare its claims with its proof. It fits into a workflow that starts with planning and drafting, then continues with style and human-sounding language checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anastasiyaw/codex-claude-code-config/article-structure-review
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.

Any agent
npx skills add AnastasiyaW/codex-claude-code-config --skill article-structure-review
Clone the repo
git clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-config

Made for: Claude Code.

Or install claude-code-config, the plugin that ships this one along with the rest of its 57 skills, 8 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 article-structure-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/article-structure-review.svg)](https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/article-structure-review)
Your own site
<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/article-structure-review"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/article-structure-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,890 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium analysis-evasion · line 1
    Suspicious Unicode normalization or mixed-script content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
How audits are shown
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 $0.00093 $0.01890
Opus 5 $0.00046 $0.00945
Sonnet 5 $0.00019 $0.00378
Haiku 4.5 $0.00009 $0.00189

Measured today against content hash 31c950beb3f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

article-structure-review 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 today.

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/writing/article-structure-review/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Структурный review технической статьи

Проверяй, помогает ли статья выполнить обещанную читателю задачу и поддержаны ли её существенные выводы. Количество иллюстраций, длины абзацев и отношение тезисов к примерам сами по себе не измеряют достоверность.

Вход и границы

Используй существующий запрос, черновик, первичные материалы и правила площадки. Не запускай все смежные writing-навыки подряд: подключай только нужный для конкретного оставшегося дефекта. Запрос «проверить» означает review без правок; «исправить/подготовить/опубликовать» включает соответствующую работу.

1. Задача читателя и жанр

Жанр Что должно быть понятно
Reference где найти факт, условие, контракт или действие
Tutorial исходные условия, шаги, результат и проверка
Analysis данные, метод, вывод и границы переноса
Story что действительно произошло и чему научился автор
Opinion что является позицией автора и чем она обоснована

Выбери основной жанр из запроса и назначения текста, не из привычки. Смешение допустимо, если читатель понимает переход. Не превращай справочник в историю или отчёт в рекламный материал, чтобы он выглядел «живее».

Для каждой секции назови её пользу читателю. Определение, таблица или короткий блок могут быть достаточны; им не требуется выдуманная личная история.

2. Тезис и соответствующее доказательство

Различай факт, предположение, вывод из данных, проектную рекомендацию и гипотетический пример. Подбирай основание по типу утверждения.

Утверждение Подходящее основание Чего недостаточно
API ведёт себя так текущая документация нужной версии или реальный probe похожий пример другой версии
изменение исправляет дефект failing case и свежая проверка изменённого пути компиляция или объяснение автора
результат получен в продукте соответствующий runtime/result receipt source review, макет, синтетический тест
метод быстрее сопоставимый baseline, условия и измерение субъективное впечатление
подход рекомендуется явно названные условия и инженерное обоснование представление мнения как доказанного закона
событие произошло с автором реально предоставленное свидетельство правдоподобный придуманный рассказ

Read the full file on GitHub · 139 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. today Changed · -34 lines · -108 tokens per session 31c950beb3f5
  2. 8d ago First seen · 173 lines · 201 tokens per session scan A db09424000f4

Subscribe to this mod's changes

article-structure-review is a skill published in the GitHub repository AnastasiyaW/codex-claude-code-config (149 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 1,890 once invoked, about $0.0005 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.