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/style-clonenpx skills add Ckokoski/AuthorAgent --skill style-clonegit 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/style-clone)<a href="https://agentmods.dev/skills/ckokoski/authoragent/style-clone"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/style-clone.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 | $0.00012 | $0.00798 |
| Opus 5 | $0.00006 | $0.00399 |
| Sonnet 5 | $0.00002 | $0.00160 |
| Haiku 4.5 | $0.00001 | $0.00080 |
Grade A, and why
style-clone 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 5d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Style Clone Skill
Analyze the author's writing to create a quantitative Voice Profile, then use it to match their style.
Use the gateway's analyzer — do NOT hand-roll a freeform analysis. AuthorAgent already ships a 47-marker voice analyzer as a first-class service (
StyleCloneService). It is deterministic, cheap (no AI call), and returns a structuredStyleProfileplus an AI system prompt you can apply to every drafting/revision task. This skill's job is to CALL that service and save the result — not to re-describe the analysis in prose. A parallel markdown-only pass would drift from the real analyzer and produce a worse, unquantified profile.
How to run it
On raw text (5,000+ words → more is better)
Call the analyzer endpoint:
POST /api/style-clone/analyze
Content-Type: application/json
{ "text": "<the author's writing sample>", "source": "manual-paste" }
Response: { "profile": <StyleProfile> } — a 47-marker fingerprint across five
axes (sentence structure, vocabulary, punctuation, syntax, voice) plus a
ready-to-use systemPrompt for maintaining voice.
On a whole project's completed chapters
POST /api/projects/:id/style-clone
The service gathers the project's completed writing-phase chapters, concatenates
them, and analyzes the combined text. Response is the same { "profile": ... }.
After analysis — persist the profile
- Save the returned profile's
systemPrompt(and key markers) toworkspace/soul/VOICE-PROFILE.mdso futurecreative_writing/revisiontasks inherit the voice. - Because the analyzer is local and fast, re-run it on new chapters to detect voice drift — compare the fresh markers against the saved profile.
Style check (drift detection)
When asked to check new text against the author's style:
- Analyze the new text via
POST /api/style-clone/analyze. - Diff its markers against the saved
VOICE-PROFILE.mdbaseline. - Report per axis: ✅ matches, ⚠️ minor drift, ❌ significant departure.
- Offer specific suggestions (never rewrite without permission).
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.
- 5d ago First seen · 86 lines · 12 tokens per session scan A 080acbd50c84
style-clone is a skill published in the GitHub repository Ckokoski/AuthorAgent (103 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 798 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.