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/epicsagas/velith/loomnpx skills add epicsagas/Velith --skill loomgit clone --depth 1 https://github.com/epicsagas/VelithWrote 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/epicsagas/velith/loom)<a href="https://agentmods.dev/skills/epicsagas/velith/loom"><img src="https://agentmods.dev/badge/skills/epicsagas/velith/loom.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 | $0.00036 | $0.01963 |
| Opus 5 | $0.00018 | $0.00981 |
| Sonnet 5 | $0.00007 | $0.00393 |
| Haiku 4.5 | $0.00004 | $0.00196 |
Grade A, and why
loom 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 4d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Velith — AI-Native Publishing System
Overview
Build books like software. 6-phase pipeline from blank page to published book, with dedicated skills, agents, and quality gates at every stage.
Phase 0: Onboarding → Phase 1: Ideation → Phase 2: Outlining → Phase 3: Drafting → Phase 4: Editing → Phase 5: Publishing
Genre Support
| Genre | Key Differences | Reference File |
|---|---|---|
| Fiction | Plot structure (Save the Cat!/Snowflake), character bible, scene beats | book-fiction |
| Non-Fiction | Problem-solution structure, persona-driven, evidence hierarchy | book-nonfiction |
| Technical | Concept progression (novice→expert), code examples, diagrams, API docs | book-technical |
| Screenplay | 3-act + sequence method, dialogue/action, A/B story | book-screenplay |
| Poetry | Form-driven (sonnet/haiku/free verse), imagery systems, collection arc | book-poetry |
| Game | Quest trees, branching dialogue, lore bible, flag system | book-game |
| Academic | IMRAD, literature review, argument chains, citation practices | book-academic |
| Custom | Compose patterns from any genre via book-genre-creator |
book-genre-creator |
Phase Router
When /velith is invoked without arguments, detect current project state and route:
- No project exists → Run Phase 0 (Onboarding)
- Project exists, no outline → Run Phase 1 (Ideation)
- Outline exists, no drafts → Run Phase 2 (Outlining) validation, then Phase 3
- Drafts exist, incomplete → Continue Phase 3 (Drafting)
- All drafts complete → Run Phase 4 (Editing)
- Editing complete → Run Phase 5 (Publishing)
Detection: check for drafts/ directory, outline.md, STYLE.md, PRD.md in current project.
Phase Details
Phase 0: Onboarding (/velith onboard)
- Genre selection (fiction/non-fiction/technical/screenplay/poetry/game/academic/custom)
- Target audience definition
- Language selection
- Project directory setup
- Source material scan (existing notes, articles, code)
- Generate
STYLE.md(voice, tone, conventions) - Generate
PRD.md(book requirements)
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.
- 4d ago First seen · 175 lines · 36 tokens per session scan A 28b727c21835
loom is a skill published in the GitHub repository epicsagas/Velith (33 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 1,963 once invoked, about $0.0002 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
short-drama
制作多集 AI 微短剧：建立剧集圣经和角色参考，完成分集剧本、逐镜 I2V、对白审计、配音字幕 BGM 与成片，保持跨镜跨集一致性。 当用户说“AI/横屏/竖屏/微短剧、拍短剧、分集剧本、连续剧情视频、做几集短剧”时使用。 单条非剧情视频用 auto-short-video；只写单条脚本用 video-script；只生成一个视频片段用 ai-video-gen。.
clipify
从长视频中自动提取精彩片段，切成独立短视频，支持 16:9→9:16 竖版转制和逐字字幕烧录。 当用户说"视频切片""提取精彩片段""长视频切短""切成短视频""高光剪辑""逐字字幕""转竖版短视频"时使用。 和 video-highlights 的区别：clipify 专做英文口播找笑点+动态人脸 pan；video-highlights 更通用（中文/直播皆可），静态转竖版更稳。.
ecom-details-image
生成电商商品视觉方案：主图概念、场景图、详情页视觉方向和 AI 生图 Prompt。 当用户说"商品主图""详情页视觉""电商配图方案""商品场景图""带货视觉""产品视觉方向""详情页设计"时使用。 本 SKILL 出视觉方案+生图 Prompt（策划）；实际抠白底图用 remove-bg，实际生成图片用 ai-image-gen。.
multi-voice-dubbing
多角色对话配音：按 cast 和逐行对白为不同角色分配音色与情绪，合成多声线音轨和带角色名字幕。 当用户说“多角色/双人/剧本/对话配音、多人对白、不同角色不同声音、有声剧配音”时使用。 单一公共音色用 tts-voiceover；克隆本人音色用 voice-clone；整部短剧制作由 short-drama 编排。.
video-strategy
视频制作策略与工具选型：AI 视频生成模型对比、视频脚本结构设计、制作流程规划，覆盖产品演示/解说/社媒短视频场景。 当用户说"视频怎么做""视频选型""用什么工具做视频""视频制作流程""视频策略""视频系列规划"时使用。 和 video-script 的区别：video-strategy 做内容规划与工具选型，video-script 写具体某条视频的脚本。.
xhs-note-creator
小红书内容总入口：生成标题、正文、caption、hashtags，以及 3-9 张图文卡片或短视频分镜，覆盖素材分析、卖点评估、去 AI 味和质检。 当用户说“写/做小红书笔记、小红书图文/种草/文案、出一套卡片、小红书视频”时使用。 整套笔记用本 SKILL；仅渲染卡片用 card-xiaohongshu；其他平台的通用文案用 social-content。.