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 agentmods add instructions/weitzu-com/ai-article-factory/gemini-mdgit 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/instructions/weitzu-com/ai-article-factory/gemini-md)<a href="https://agentmods.dev/instructions/weitzu-com/ai-article-factory/gemini-md"><img src="https://agentmods.dev/badge/instructions/weitzu-com/ai-article-factory/gemini-md.svg" alt="Measured on agentmods" 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 | $0.00234 | $0.00234 |
| Opus 5 | $0.00117 | $0.00117 |
| Sonnet 5 | $0.00047 | $0.00047 |
| Haiku 4.5 | $0.00023 | $0.00023 |
Grade A, and why
ai-article-factory GEMINI.md 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 6d 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.
What it actually says
GEMINI.md
ai-article-factory — a self-contained skill suite that turns any material/topic/product into a publish-ready, illustrated, SEO+GEO article in Markdown + Word, plus website/LinkedIn/X copy. A human only reviews, confirms, and publishes.
👉 Full agent instructions are in AGENTS.md (single source of truth) — pipeline, worker skills, commands, and rules. The skill orchestrator is SKILL.md; the six workers are under skills/.
Quickstart:
bash scripts/new-article.sh <slug> # scaffold articles/<date>-<slug>/
bash scripts/render-figures.sh <article-dir> # figures → assets/img/
bash scripts/export.sh <article-dir> <slug> # Markdown → .docx
bash tests/harness.sh # regression suite (keep green)
Default path: one sentence → AI infers the profile (no forms) → draft → figures + export → *-final.md + *-final.docx. Apache-2.0 (see NOTICE).
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.
- 6d ago First seen · 15 lines · 234 tokens per session scan A e7dcf36c5b69
ai-article-factory GEMINI.md is an instructions file published in the GitHub repository weitzu-com/ai-article-factory (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 234 tokens to every session, about $0.0012 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.
Other instructions, from other repositories
humanize AGENTS.md
AGENTS.md instructions for shir-danishyar/humanize: This repository is an Agent Skills-format skill. To use it.
humanizer-ko AGENTS.md
Instructions for IsaacEryn/humanizer-ko, covering agents.md, 이 저장소는 무엇인가, 주요 파일, 유지보수 계약 and skill.md 편집.
humanizer-ko CLAUDE.md
Instructions for IsaacEryn/humanizer-ko, a project described as: 한국어 텍스트에서 AI 생성 글의 티를 제거하는 Claude Code 에이전트 스킬. ChatGPT 문체, 이중 피동, 번역투, 문체 혼용 등 33개 패턴 탐지. Korean adaptation of the humanizer agent skill.
claude-linkedin-post-creator CLAUDE.md
Instructions for tarunkorat/claude-linkedin-post-creator, covering claude.md — linkedin post creator, what this is, where the docs live, config files — source of truth and hard rules.
stewie-pixel guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
humanise CLAUDE.md
Claude Code instructions for Nisus74/humanise, covering claude.md, the one rule: body vs soul, repo map, the acceptance gate (read before changing the engine) and commands.