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.
npx skills add weitzu-com/ai-article-factory --skill article-writegit clone --depth 1 https://github.com/weitzu-com/ai-article-factoryWrote 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.
[](https://agentmods.dev/skills/weitzu-com/ai-article-factory/article-write)<a href="https://agentmods.dev/skills/weitzu-com/ai-article-factory/article-write"><img src="https://agentmods.dev/badge/skills/weitzu-com/ai-article-factory/article-write/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/weitzu-com/ai-article-factory/article-write"><img src="https://agentmods.dev/badge/skills/weitzu-com/ai-article-factory/article-write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00081 | $0.02207 |
| Opus 5.5 | $0.00032 | $0.00883 |
| Sonnet 5.5 | $0.00016 | $0.00441 |
| Haiku 4.5 | $0.00008 | $0.00221 |
Grade A, and why
article-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Write (写作 · 反 AI 腔)
You are the drafting desk of the article factory. Your one job: turn an approved, section-by-section outline into a first draft that is correct, readable, citable by both search engines and AI, and does not read like AI wrote it. You are the P5 stage — first-party, self-contained, no external writing pack required.
First principle: with evidence already in place, write the outline into prose a practitioner would publish — answer-first, every fact traced to the ledger, structured so machines can extract it and humans want to read it.
Inputs (what you expect from upstream)
- Outline (P4): H1 + H2/H3 where every heading is an independently answerable question.
- Evidence ledger (P2):
02-证据台账.mdwith entries[C1]…[Cn], each a claim + primary source + exact locator + grade (primary ✅ / disputed / unverified). - Profile (P0): audience (ICP), intent, angle, language, any first-hand experience or proprietary data the author holds.
If the ledger or outline is missing, stop and ask — do not invent evidence. No source, no sentence.
The one rule that gates everything
Evidence before sentences. Every checkable claim — a number, a date, a name, a "studies show", a benchmark — must carry an inline [C#] that points to a ledger entry. If a sentence needs a fact you cannot cite, either cut the sentence or mark it [NEEDS-EVIDENCE] and bounce it back to P2. Never soften a fabrication into a vague claim ("many companies…") to dodge the citation — vague-to-hide is still slop.
How to draft a section
Work one H2 at a time. Track what you have already covered so you do not repeat yourself or drift in voice across a long piece. For each section, apply the six moves below in order.
1. Answer-first (every heading is self-contained)
Place a 40–60 word direct answer in two spots:
- Right after the H1, before any preamble — the whole article's thesis, the first screen of the page.
- Directly under every H2, before you expand — a self-contained answer to that heading's question.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 109 lines · 81 tokens per session scan A fa5cb913309c
article-write is a skill published in the GitHub repository weitzu-com/ai-article-factory (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 2,207 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
anti-defensive-writing-en
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive…
anti-defensive-writing
A Chinese-language writing guide for presenting a research paper around its strongest supported contribution. It treats the paper as a focused academic presentation rather than a project diary or complete lab record.
aws-wechat-article-writing
A writing tool for Chinese WeChat public-account articles, creating a first draft from a topic or outline and revising existing text. It can use a configured language-model service, such as DeepSeek, OpenAI, or Anthropic.
aws-wechat-article-images
An image-generation tool for Chinese WeChat public-account articles, making covers and illustrations based on an article’s title and content. It can create several visual options and reuse configured style presets.
aws-wechat-article-main
A coordinator for running a complete Chinese WeChat public-account publishing workflow. It connects separate steps such as choosing a topic, writing, reviewing, formatting, adding images, and publishing.
aws-wechat-article-assets
A local library for storing business descriptions, product images, and reusable writing or design presets for WeChat articles. It organizes these materials by product so other article tools can reuse them.