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 Ckokoski/AuthorAgent --skill preference-learnergit clone --depth 1 https://github.com/Ckokoski/AuthorAgentWrote 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/ckokoski/authoragent/preference-learner)<a href="https://agentmods.dev/skills/ckokoski/authoragent/preference-learner"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/preference-learner/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/ckokoski/authoragent/preference-learner"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/preference-learner.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 | $0.00020 | $0.01728 |
| Opus 5.5 | $0.00008 | $0.00691 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo ago First seen · 221 lines · 20 tokens per session scan A 0794076c1992
preference-learner is a skill published in the GitHub repository Ckokoski/AuthorAgent (124 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 1,728 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
gallery-memory
Sync gallery images into long-term memory files and rebuild the user profile from photo-derived memories.
memory-evolution
Process pending X-OmniClaw task memories, update MEMORY.md, and rebuild the compact USER-PROFILE.md.
gallery-qa
Consume the full memory/IMAGE-MEMORY.md file for all gallery-image questions and operations instead of using retrieval-first search.
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
knowledge-base
Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers…