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 majiayu000/spellbook --skill repo-filmgit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/repo-film)<a href="https://agentmods.dev/skills/majiayu000/spellbook/repo-film"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/repo-film/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/majiayu000/spellbook/repo-film"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/repo-film.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 | $0.00208 | $0.01713 |
| Opus 5.5 | $0.00083 | $0.00685 |
| Sonnet 5.5 | $0.00042 | $0.00343 |
| Haiku 4.5 | $0.00021 | $0.00171 |
Grade A, and why
repo-film 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 3d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
repo-film:仓库的一段时间 → 一条短片
要支撑的决定:任何仓库的任何一段时间,能不能一行命令、不改场景代码就出一条能发的片子。
放弃条件:到 2026-12-15 为止,除 Keepline 和 Spellbook 两次验收外没有再用过;或者连续两个新仓库都得改 template/scene.html 才能出片。满足任一条就停用,把分支布局脚本并进 motion-stack 的示例。每做完一部,在下方“做过的片子”表里记一行。
用法
node <本 skill 目录>/scripts/make.mjs \
--repo <仓库路径> --since "2026-11-01 20:00" --until "2026-11-02 06:00" \
[--branch main] [--map auto|none|<地图 html>] [--config film.json] [--out <目录>] [--sheet-only]
- 先加
--sheet-only只出关键帧拼图(out/beats.png),自己看一遍再出片。 - 成片在
<out>/out/<仓库名>-film.mp4,1920×1080、30fps,响度约 -14 LUFS。没有地图约 13 秒,有地图约 24 秒。 --out默认是~/Videos/repo-film/<目录名>-<开始日期>,里面就是完整工程,可以直接改scene.html或<out>/assets/film.js再用 motion-stack 的render.mjs重渲。- 依赖:motion-stack skill(装在本 skill 旁边,或在
~/.claude/skills、~/.codex/skills、~/.agents/skills里,也可以用MOTION_KIT指向它的kit/;第一次要在kit/里PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD=1 npm install)、python3、ffmpeg。Tone.js 优先复用 motion-stack 示例的node_modules,没有才npm install。
流水线
scripts/lanes.py:只读 git(--all,所以本地分支也算)。--branch的 first-parent 链是主线(第 0 道),其余提交按 first-parent 串成分支段;每段从分叉点到合并点占一个区间,区间重叠的段分到不同的道(上下交替)。分支名从Merge branch 'x' into y里读,读不到就不标。超过--max(默认 400)只留最新的。scripts/capture.mjs:有地图时,把地图临时排成单栏(阻塞链不再横向滚动,能完整显示),截 2 倍图,并记下各区块位置和阻塞链每条连线的路径。只改截图时的样式,不改地图文件。make.mjs按数据生成字幕和结尾卡片,写进<out>/assets/film.js,再用--config覆盖。- 渲染:关键帧拼图 → 纯度检查(正放和倒放必须一致)→ MP4。响度由 motion-stack 渲染器自动调到 -14 LUFS,数值在成片旁的
.manifest.json里。
film.json(全部可选)
{
"captions": [["你离开了。", "You step away."], ["agent 们接着干。", "The agents keep going."],
["一夜,51 个提交,8 条分支。", "One night. 51 commits. 8 branches."], ["回来,打开一页。", "Come back. Open one page."]],
"sub": "KEEPLINE · 11-01 20:01 → 11-02 04:34",
"startLabel": "20:00 开工",
"end": { "title": "you-are-here", "tagline": "…", "taglineEn": "…",
"lines": ["/plugin marketplace add majiayu000/you-are-here"], "meta": "github.com/…" }
}
字幕四个位置分别是 0.6 秒、3 秒、7.6 秒(全景)和 8.65 秒(只在有地图时出现,引出地图)。end.lines 以 / 或 $ 开头的部分会着色,适合放安装命令。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 65 lines · 208 tokens per session scan A 42e361963521
repo-film is a skill published in the GitHub repository majiayu000/spellbook (290 stars, last pushed 2d ago), licensed MIT. It adds 208 tokens to every session and 1,713 once invoked, about $0.0008 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 2026-11-03.
repo-film compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| repo-filmmajiayu000/spellbook | Skill | 290 | 2d ago | MIT | A | 208 | Claude Code |
| setup-pre-commitvinvcn/mattpocock-skills-zh-CN | Skill | 5.6k | 9d ago | MIT | A | 65 | Claude Code, Codex |
| ratchet-filesdzhng/skills | Skill | 1.4k | 2d ago | MIT | A | 118 | Claude Code, Codex |
| checkpoint-managementa5c-ai/babysitter | Skill | 1.9k | 5d ago | MIT | A | 22 | Claude Code |
| commitdecodingai-magazine/building-a-coding-agent-from-scratch-course | Skill | 1.1k | 13d ago | Apache-2.0 | A | 16 | Claude Code, Codex |
| night-watchsoftspark/ai-toolkit | Skill | 179 | 10d ago | Apache-2.0 | A | 36 | Claude Code |
| daily-retroserejaris/personal-corp-os | Skill | 241 | 3d ago | MIT | A | 126 | Claude Code |