Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/sma1lboy/rove/auto-motion)<a href="https://agentmods.dev/skills/sma1lboy/rove/auto-motion"><img src="https://agentmods.dev/badge/skills/sma1lboy/rove/auto-motion.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 5.1 | $0.00140 | $0.00772 |
| Opus 5 | $0.00070 | $0.00386 |
| Sonnet 5 | $0.00028 | $0.00154 |
| Haiku 4.5 | $0.00014 | $0.00077 |
Grade A, and why
auto-motion 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 6d 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.
What it actually says
auto-motion(kobe wrapper)
kobe 自己的宣传片优先用
brand-videoskill(单一 Remotion 工程、theme 靠 import、支持真机 replay 镜头)。本 wrapper 只在需要 auto-motion 通用外部工作流(hyperframes 逐镜头子进程)时用。
canonical 执行逻辑在 auto-motion 仓库的 .claude/skills/auto-motion/SKILL.md——本文件不复制那份流程(避免漂移),只做两件事:定位模板根、注入 kobe 的上层 theme。
Step A — 解析模板根(AUTO_MOTION_ROOT)
按顺序取第一个命中的:
../auto-motion(workspace sibling,/Users/jacksonc/i/auto-motion)——本地开发副本,可能领先 fork。refs/auto-motion—— 已存在则用。- 都没有:
git clone --depth 1 https://github.com/Sma1lboy/auto-motion.git refs/auto-motion(我们的 fork,带 theme/引擎改动;refs/ 已 gitignore,40M 模板不进 kobe 仓库)。
然后通读 <AUTO_MOTION_ROOT>/.claude/skills/auto-motion/SKILL.md 并按它执行(storyboard → theme.md → 镜头目录 → 顺序执行监控 → 拼接交付)。单镜头模板是 <AUTO_MOTION_ROOT>/exampleFolder/run-claude-ai.sh;scene skills 本仓库 .claude/skills/ 已 vendor 全套(hyperframes*、general-video、image-gen、motion-graphics),直接从这里复制,不必依赖模板根。
Step B — kobe 的上层 theme(canonical SKILL 里 Step 0.5 优先级 ② 的具体来源)
在 kobe 仓库里跑时,派生 theme.md 前先感知这些品牌源,继承而不是重新发明:
- 品牌视觉/配色/字体:
packages/branding(Remotion 品牌管线,landing 片的既有视觉语言)。 - logo 资产:
docs/assets/brand/logos/。 - 产品气质:TUI 默认主题是
claude(DEFAULT_THEME,品牌身份,见 CLAUDE.md)——终端质感、暗底、Claude 橙系强调是默认调性。 - 用户在对话里给的视觉要求仍然是最高优先级(canonical 优先级 ①)。
工作目录
不要把 scenes/、final.mp4 写进 kobe 源码树。在 scratchpad 或用户指定目录建运行工作区,只把 transcription.srt、storyboard、theme 和产物放那里;需要留档的成片再按用户指示移动。
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.
- 6d ago First seen · 34 lines · 140 tokens per session scan A edda36e098b4
auto-motion is a skill published in the GitHub repository Sma1lboy/rove (116 stars, last pushed today), licensed MIT. It adds 140 tokens to every session and 772 once invoked, about $0.0007 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
omd-grill
锁 plan/SDD 前的对抗式审问:沿决策树走、先给推荐答案、事实自查·技术 Decision 自裁·真 owner 岔口才阻塞问、对标外部实现逼问「为何偏离」;宽解岔口就地开 council;产决策记录表喂 /omd-contract。审议纪律:只讨论不动手。Trigger:/omd-grill、审问、盘问这个方案、把这事讨论清楚、压测计划、stress-test。.
vf-security-checklist
Use when touching auth, user input validation, file paths, redirects, WebSocket, uploads, rate limiting, CORS, or any security-sensitive code in veryfront.
scaffold-ai-app
Scaffold a Veryfront app with AI tools, agent definitions, and knowledge base.
debug-build
Diagnose and fix build failures using structured error output.
omd-council
多视角专家议会:宽解空间的设计/决策问题,经 omd dagresearch(council 模式)并行多 persona 出方案 + 多 lens 择优;领域岔口走接地档(反 happy-path)。Trigger:/omd-council、开会审议、多方案对比、给我几个选项、拿不准选哪个。.
omd-deliver
执行 omd pathfinder 已散尽区域(编译 slice → 跑 DAG 真改文件 → 票翻 delivered),标 delivered 前逐票核对真身(delivered✅≠东西真在)。deliberate/build 的权力闸,仅 owner 明令。Trigger:/omd-deliver、交付、开始执行、动手吧。.