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 skills/ckokoski/authoragent/preference-learnernpx skills add Ckokoski/AuthorAgent --skill preference-learnergit clone --depth 1 https://github.com/Ckokoski/AuthorAgentWhat 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 | $0.00020 | $0.01728 |
| Opus 5 | $0.00010 | $0.00864 |
| Sonnet 5 | $0.00004 | $0.00346 |
| Haiku 4.5 | $0.00002 | $0.00173 |
Grade A, and why
preference-learner 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 2d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preference Learner — Core Skill
Every author is different. This skill builds a living profile of the user's preferences, habits, and working style — then applies it to every interaction so AuthorClaw feels increasingly personalized.
What Gets Learned
Writing Preferences
writing:
# Detected from user revisions and feedback
dialogue_tags: "simple (said/asked only)"
description_density: "moderate (1-2 sensory details per scene)"
paragraph_length: "short (2-4 sentences)"
chapter_length: "2500-3500 words"
pov_preference: "third person limited"
tense: "past"
profanity_level: "mild"
romance_heat_level: "closed door"
violence_level: "moderate"
humor_style: "dry, situational"
# Specific dos and don'ts
always:
- "Start chapters with action or dialogue, never description"
- "End chapters on a hook or question"
- "Use Oxford comma"
never:
- "Use adverbs in dialogue tags (said softly, whispered quietly)"
- "Start sentences with 'Suddenly'"
- "Use the word 'whilst'"
Communication Preferences
communication:
response_length: "concise (under 200 words unless writing prose)"
status_update_frequency: "after each major step"
question_threshold: "only ask if truly ambiguous (err on acting)"
emoji_usage: "moderate"
formality: "casual, friendly"
explanation_depth: "brief unless asked for detail"
preferred_channel: "telegram"
Working Style
workflow:
active_hours: "6am-10pm"
most_productive_time: "morning (6am-noon)"
session_length: "30-60 minutes"
break_reminders: true
daily_word_goal: 2000
preferred_goal_size: "medium (5-8 steps)"
review_preference: "review after each chapter, not after each scene"
file_organization: "by project, then by chapter"
naming_convention: "chapter-01-title.md"
Genre & Market Preferences
market:
primary_genre: "psychological thriller"
subgenres: ["domestic suspense", "unreliable narrator"]
target_audience: "women 25-45, fans of Gillian Flynn"
publishing_path: "traditional (querying agents)"
comp_titles: ["The Wife Between Us", "The Last Thing He Told Me"]
word_count_target: 80000
series_vs_standalone: "standalone with series potential"
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.
- 2d ago First seen · 221 lines · 20 tokens per session scan A 0794076c1992
preference-learner is a skill published in the GitHub repository Ckokoski/AuthorAgent (102 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 1,728 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.
Other skills, from other repositories
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
app-search
主流APP搜索。当用户想要在拼多多、美团、高德地图、抖音、快手、小红书、哔哩哔哩、知乎、百度、OPPO音乐、OPPO软件商店等APP中搜索时激活。覆盖电商购物、生活服务、短视频内容、知识搜索、音乐搜索、应用商店搜索等场景。.
clipboard-to-shortcut
将剪切板中的 App 跳转链接制作成一个可复用的快捷指令 Skill，下次用户说出 Skill 名称即可一键直达对应 App 页面。 当用户说"把剪切板的链接做成skill"、"帮我保存这个链接为快捷方式"、"用剪切板内容创建一个skill XX"、"把这个链接制作成skill"、"帮我把复制的链接做成一键跳转"等意图时激活。 支持淘宝、拼多多、抖音、快手、知乎、小红书、美团、哔哩哔哩、高德、QQ音乐、支付宝、百度等主流 App 的分享链接。.
capcut-theme-video
CapCut (剪映) one-tap video creation on Android. Always clear Alatest first (copyimagestoalbum clear-only), then retrieve by time (listgalleryimages) or content (image-memories). Copy to Alatest (clearalbumfirst), CapCut 照片视频 → Alatest → 全部, multitap, N=K.
taobao-search
淘宝商品搜索。当用户想要搜索商品、找某品牌产品、比价、查看新款等电商购物场景时激活。.
scheduled-automation
Schedule app automation tasks such as opening an app and performing actions at a specific time.