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 adenaufal/anti-slop-writing --skill indonesiangit clone --depth 1 https://github.com/adenaufal/anti-slop-writingWrote 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/adenaufal/anti-slop-writing/indonesian)<a href="https://agentmods.dev/skills/adenaufal/anti-slop-writing/indonesian"><img src="https://agentmods.dev/badge/skills/adenaufal/anti-slop-writing/indonesian/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/adenaufal/anti-slop-writing/indonesian"><img src="https://agentmods.dev/badge/skills/adenaufal/anti-slop-writing/indonesian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00106 | $0.13491 |
| Opus 5 | $0.00053 | $0.06746 |
| Sonnet 5 | $0.00021 | $0.02698 |
| Haiku 4.5 | $0.00011 | $0.01349 |
Grade A, and why
anti-slop-writing-id 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 12d 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 — 637 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prinsip Utama
Tulisan AI gagal karena mengoptimalkan probabilitas statistik. Hasilnya: teks yang paling diharapkan, aman, dan bisa diterima semua orang. Tulisan manusia datang dari satu kepala dengan sejarah, pendapat, konteks spesifik, dan tujuan. Semua aturan di bawah ada untuk memecah optimasi probabilitas itu, dan nyuntikin spesifisitas, ketidaksempurnaan, dan kepribadian yang jadi ciri tulisan manusia.
Aturan-aturan ini menargetkan tiga metrik utama yang dipakai detektor AI (Turnitin, GPTZero, Originality.ai):
- Perplexity: seberapa tidak tertebak pilihan katanya. AI bikin teks low-perplexity (halus, nggak bikin kaget). Manusia bikin teks high-perplexity.
- Burstiness: variasi panjang dan struktur kalimat. AI punya burstiness rendah (kalimat 10 sampai 20 kata, struktur konsisten). Manusia bisa nyampur kalimat 3 kata dengan kalimat 30 kata. HATI-HATI (2026): model terbaru bisa memalsukan burstiness secara bimodal, lihat Aturan Struktur #1.
- Stilometri: sidik jari statistik tulisan. Frekuensi kata fungsi, kekayaan kosakata, pola tanda baca, kedalaman sintaktis. Turnitin (update 2025 ke 2026) menganalisis "ritme, alur, dan prediktabilitas seluruh paragraf".
Pergeseran 2026: Struktur Ngalahin Tanda Baca
Per pertengahan 2026, tell-nya udah pindah. OpenAI men-suppress em dash di GPT-5.1, dan kosakata legacy ("delve", "tapestry", "menyelami", "permadani") udah di-train keluar dari model Claude terbaru. Ketiadaan tell lama bukan bukti tulisan manusia. Yang bertahan lewat pergantian prompt dan model adalah pola struktural:
- Cadence uniformity adalah tell nomor satu 2026. Kalimat yang panjangnya 18 sampai 24 kata terus-menerus, paragraf demi paragraf. Ini bertahan lewat edit kosmetik apa pun.
- Tes 30 detik (editor dan pembaca sekarang pakai ini secara manual):
- Lihat kata pertama tiap kalimat dalam satu paragraf. Kalau lebih dari setengahnya mulai dengan "Hal ini", "Ini", "Dalam", "Selain itu", atau "Dengan", teks terbaca sebagai buatan AI.
- Hitung panjang kalimat. Tiga atau lebih kalimat berturut-turut di rentang 17 sampai 23 kata = kesimpulan sama.
- Sinyal tanda baca pindah ke Claude. Analisis korpus Januari 2026 (200 sampel Opus 4.5 vs 6.000 teks manusia): em dash 16,9x rate manusia, titik dua 4,1x, titik koma 3,1x. Sementara output GPT-5.1+ bisa nyaris bebas dash. Aturan nol dash tetap berlaku, DAN sekarang pantau juga kepadatan titik dua.
- Repetisi kata kunci prompt. Ciri khas output ID yang di-copy-paste mentah: istilah dari instruksi diulang-ulang secara nggak natural, kayak konten SEO jadul. Variasikan penyebutan topik.
What ships with it
7 files 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.
- 12d ago First seen · 637 lines · 106 tokens per session scan A 1f4b37332cb2
anti-slop-writing-id is a skill published in the GitHub repository adenaufal/anti-slop-writing (126 stars, last pushed 2mo ago), licensed MIT. It adds 106 tokens to every session and 13,491 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.
Other skills, from other repositories
ai-slop-detector
Universal prose audit. Scores writing on TWO axes — AI-Slop (does this read like AI wrote it?) and Comprehension (can a fresh reader follow this?). Use PROACTIVELY as a mandatory final QA pass on ANY prose generated for humans to read — every email (internal or external), proposal, report, status update, blog post…
humanizer-czech
Odstraň znaky AI-generovaného psaní z českého textu. Použij při editaci nebo revizi textu, aby zněl přirozeněji a lidštěji. Detekuje a opravuje 27 vzorců včetně: nafouklého významu, propagačního jazyka, anglického slovosledu, kalků, nominalizace, monotónního rytmu, nadužívání spojek, typických českých AI klišé…
shuorenhua
A writing and editing guide for making Chinese and English text sound natural and less machine-generated, with special attention to Taiwan Traditional Chinese usage. It preserves technical terms, facts, and the responsible subject.
simple-english
Rewrite text to ASD-STE100 Simplified Technical English.
whisper
Transcribe and translate speech in 99 languages.
website-maintainer
Use this skill when working on the Repomix documentation website in website/ directory, including VitePress configuration, multi-language content, or translation workflows.