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 chenyuxiaojin/cyxj-remotion-starter --skill cyxj-remotion-evolvegit clone --depth 1 https://github.com/chenyuxiaojin/cyxj-remotion-starterWrote 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/chenyuxiaojin/cyxj-remotion-starter/cyxj-remotion-evolve)<a href="https://agentmods.dev/skills/chenyuxiaojin/cyxj-remotion-starter/cyxj-remotion-evolve"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/cyxj-remotion-starter/cyxj-remotion-evolve/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/chenyuxiaojin/cyxj-remotion-starter/cyxj-remotion-evolve"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/cyxj-remotion-starter/cyxj-remotion-evolve.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00134 | $0.01948 |
| Opus 5 | $0.00067 | $0.00974 |
| Sonnet 5 | $0.00027 | $0.00390 |
| Haiku 4.5 | $0.00013 | $0.00195 |
Grade A, and why
cyxj-remotion-evolve 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 12d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cyxj-remotion-evolve(文档进化引擎)
Remotion 工作台的"活文档"机制。目标:规则文档每次都跟着进化,不靠人记得改。 学到一条东西 → 路由到正确的真源文件 → 回写 → 保持整条路由链一致。
⚠️ 这不是复盘 / QA(那是查"做对没做对")。这是进化:把"学到的"沉淀成"下次的起点",让视频越做越好。 ⚠️ 也不替代官方核查或硬规则——它只负责"把规则本身改对、改全、放对地方"。
什么时候触发
- 手动:用户说"进化 / 更新文档 / 回写规则 / 把这次学到的写进规则"。
- 自动:收工"文档进化闸"hook(
.claude/hooks/evolve-on-stop.mjs,Stop 时机;搭档record-evolve-touch.mjs记本轮改动)检测到本轮动过镜头/出片代码而规则文档未动 → 拦一次提醒跑本 skill,再次收工放行。 - 主动:对话里出现"纠正 / 新决策 / 新手法 / 旧规则被推翻"时,主动提议跑一次。
铁律(先记住,再动手)
- 绝不静默改文档。 一律先出 diff 提案、按文件分组、说清"为什么写这个文件"、用户批准才写。规则文档是你的宪法。
- 单一真源。 每条事实只在一个真源里写全,别处只放指针。禁止把同一条规则复制进多个文件——发现重复要合并、留指针。
- CLAUDE.md 是路由器,不是仓库。 具体规则进对应真源文件,CLAUDE.md 只留一行指过去;不要把内容堆进 CLAUDE.md 正文。
- 改视觉值走单一真源。 视觉【值】(色 / 字号 / 动效 token)改
kit/theme.ts(或你为它建的生成器),别在组件里到处内联硬编码色值。 - 移动规则要补指针。 一条规则从 A 文件挪到 B 文件,必须同步改掉所有指向它的路由行,别留断链。
执行分工(防上下文污染)
主对话只做两件事:① 采集信号(从本会话对话/diff 里捞,压缩成一段简报——只有主对话知道这轮发生了什么);② 按铁律 1 向用户出提案、拿批准。 批准后派子代理执行(general-purpose,把简报 + 下方路由表 + 目标文件路径喂给它):读真源 → 一致性查重(四步之3)→ 回写 → 记沿革 → 返回 diff 摘要,主对话转达即可。 为什么:路由/查重要读大量真源文件,全在主对话做会吃掉主上下文;子代理烧自己的窗口,主对话只留结论。 边界:批准环节不许下放——子代理不能与用户对话,「用户批准才写」必须发生在主对话;子代理只执行已批准的内容,超出提案范围的发现带回主对话再议。
路由链地图(锚点 = 仓库根)
CLAUDE.md 根路由 + 三层真源索引
kit/CLAUDE.md 共享层(kit)索引 + 组件晋升规则
template/CLAUDE.md 出片层(各工程自己的禁区)
docs/HARD_RULES.md 工程红线唯一真源(frame 驱动 / clamp / 确定性 / public…)
进化四步
1. 采集(找进化信号)
从本会话对话 + git diff / git log(动过的工程)里捞:
- 纠正:用户说过"不对 / 我没说过 / 应该是 X / 你理解错了"。
- 新决策:定了新做法 / 新默认 / 新边界。
- 新手法 / 新能力:造出了好用且会跨片重复的手法,或验证了某引擎用法(3D / anime / 原生武器…)。
- 旧规则被推翻 / 过时描述:文档说 X,现实或代码是 Y。
- 创造 vs 复用事件:这次是真创造,还是又反射式复用了?(给"创作姿态闸"攒账)
2. 分类 + 路由(查路由表)
每条信号落到唯一真源:
| 学到什么 | 写进哪个真源(锚点 = 仓库根) | CLAUDE.md |
|---|---|---|
| 操作纪律 / 流程 | 对应层 CLAUDE.md 正文(根 / kit / 出片层) |
它本身就是 |
| 踩坑 / 框架红线 / 战疤 | docs/HARD_RULES.md |
留指针 |
| 视觉【值】(色 / 字号 / 动效 token) | kit/theme.ts(或你建的生成器) |
— |
| 视觉意图 / 构图 / 色彩语义 | 你自己的设计说明书(本仓不含,建议自建) | 留指针 |
| 动效手法 / 节奏 / spring 手感 | 你自己的动效笔记(本仓不含,建议自建) | 留指针 |
| 引擎能力 / 用法(3D·anime·原生武器) | 你自己的引擎笔记(本仓不含,建议自建) | 留指针 |
| 创作姿态(创造 vs 复用判断) | .claude/skills/cyxj-remotion-overlay/SKILL.md |
— |
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.
- 12d ago First seen · 83 lines · 134 tokens per session scan A eb7f88340025
cyxj-remotion-evolve is a skill published in the GitHub repository chenyuxiaojin/cyxj-remotion-starter (6 stars, last pushed 2mo ago), licensed MIT. It adds 134 tokens to every session and 1,948 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 2026-08-31.
Other skills, from other repositories
video-strategy-orchestrator
Decides WHEN to use Remotion, HyperFrames, AI video generation, or a hybrid of all three. Use when building video production pipelines, choosing a video tool for a task, or when the user asks 'which video tool should I use?'. Evaluates input type, complexity, determinism needs, and output format to pick the right…
video-director
The Video Production Manager — manages ALL video production under 1ai-content. Delegates to HyperFrames, Remotion, AI video, and FFmpeg based on the task. Has memory via 1ai-hub brain, follows 1ai-rules, and reports to Content Director. Use when the user says 'make a video', 'create video', 'edit video', 'video…
notebook-video
Create complete Chinese 2K warm-ivory engineering-notebook explainer and promotional videos with React, TypeScript and Remotion. The default visual route is pure code-drawn composition (SVG diagrams, mascots, progressive checklists, annotation stickers) synchronized frame-accurately to Chinese TTS word timing, so…
super-video-maker
End-to-end AI video production skill for agentic frameworks. Use when the user asks to make, edit, repurpose, caption, soundtrack, or export videos using HeyGen avatars, Seedance or ByteDance b-roll, OpenAI image generation and editing, AI UGC ads, Remotion, HyperFrames, screen recordings, FFmpeg, captions, ElevenLabs…
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
stage-edit
Intelligent editing of real user-supplied footage—understand it with transcript/OCR/scene/silence/quality/vision evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.