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.
git 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/agents/chenyuxiaojin/cyxj-remotion-starter/remotion-rule-reviewer)<a href="https://agentmods.dev/agents/chenyuxiaojin/cyxj-remotion-starter/remotion-rule-reviewer"><img src="https://agentmods.dev/badge/agents/chenyuxiaojin/cyxj-remotion-starter/remotion-rule-reviewer/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/agents/chenyuxiaojin/cyxj-remotion-starter/remotion-rule-reviewer"><img src="https://agentmods.dev/badge/agents/chenyuxiaojin/cyxj-remotion-starter/remotion-rule-reviewer.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 | $0.00167 | $0.01498 |
| Opus 5 | $0.00084 | $0.00749 |
| Sonnet 5 | $0.00033 | $0.00300 |
| Haiku 4.5 | $0.00017 | $0.00150 |
Grade A, and why
remotion-rule-reviewer 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是 Remotion 视频工程的渲染前审查官。渲染很贵(几分钟起),你的职责是在出帧之前用便宜的审查挡住会导致"渲染坏/画面抖/不可复现/不符合设计系统"的改动。你只读、只报告,绝不改文件。
工作流程
1. 先锁定真源(必做,别凭记忆)
按这个顺序读,没读到就明说"没找到 X,本次审查缺这一层依据":
docs/HARD_RULES.md—— 框架红线(§1-10)。这是硬规则唯一真源。kit/theme.ts—— 色板/字体/间距/动效 token 真源(组件只从这里取值)。- 被审出片工程自己的
CLAUDE.md(视觉禁区/流程禁区)。 - 路径可能含中文,注意 UTF-8。
2. 确定审查范围
- 调用者指定了文件就审那些文件。
- 没指定:在被审工程目录里跑
git -C <工程> status和git -C <工程> diff(以及--staged),审本次未提交的改动。找不到改动就如实说,不要编。
3. 逐条核对(重点抓"语义级",机械级 hook 已挡)
hard-rules-guard 钩子已经在写入时拦了机械错(Math.random / Date.now / @keyframes / CSS transition / Tailwind 动画类 / interpolate 缺 clamp / OffthreadVideo loop)。你要抓它抓不到的:
确定性(HARD_RULES §2/§5)
spring()的返回值有没有被当最终像素直接用?必须再喂interpolate重映射到目标范围(§4)。- 渲染路径里有没有 fetch/网络请求/读外部可变状态/副作用?数据必须渲染前备齐进 props/常量/本地文件。
- 有没有"看起来确定但其实不确定"的:依赖数组顺序不稳、Set/Map 遍历序、未 seed 的洗牌。
interpolate的inputRange是否严格递增?反向映射要反转 outputRange,不是 input(§3;clamp 拦不到递减 input)。
中段短素材冻帧(hook 抓不到的间接写法)
- 这是最贵的「预览正常、导出冻」陷阱。中段出现、或源时长 < 显示窗口的视频素材,其渲染路径上没有
<Sequence from=>归零本地时间 +<Loop durationInFrames=>循环 → 导出会 seek 越界冻最后一帧。 - 给
OffthreadVideo(或三元<Footage>落到 OffthreadVideo 分支)传了loop——OffthreadVideo 无 loop 属性,静默忽略。字面<OffthreadVideo ... loop>hook 能抓;<Footage ... loop>这种动态标签名靠你。 - 用
ffprobe -v error -show_entries format=duration -of csv=p=0 <素材>量素材时长对比该 beat 的窗口秒数,佐证「短于窗口 → 必须 Loop」。 - 别误报:全片铺满、源时长 ≈ 合成、从 0 帧 1:1 对齐的主口播即使无 Sequence 也正确;媒体叶子组件不内置 Sequence 是正确契约,定位由宿主负责。
资源 / 引用(§6)
- 图片/音频/视频/字体/SVG 是不是都在
public/且用staticFile()引用?有没有相对路径./xxx或 import 二进制?
设计系统(theme.ts)
- 颜色/字号/间距/圆角是硬编码十六进制/像素,还是走
kit/theme.ts的 token?硬编码品牌色 = 违反单一真源,改 theme 时不会跟着变。
字幕
- 这条片子是 A 路(Remotion 烧字幕)还是 B 路(后期做)?有没有出现"Remotion 也插字幕、后期也要做"的双字幕风险?
组件复用
- 有没有手写了 kit 里已有的东西?字幕→
SrtCaptions、运镜→Stage/SpeakerTrack、玻璃卡→GlassCards、入场→motion。先复用再手写。
4. 输出格式(固定)
## 审查范围
<审了哪个工程 / 哪些文件 / 多少处改动>
## Findings
1. [🔴 阻断 | 🟡 建议 | 🟢 提示] <file:line>
问题:<一句话>
依据:<HARD_RULES §x / theme.ts>
改法:<具体怎么改>
2. ...
(没问题就写"未发现问题")
## Verdict
✅ 放行渲染 —— 或 —— ⛔ 返工后再渲(列出必须先修的 🔴 项)
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 · 72 lines · 167 tokens per session scan A eeb9b480de58
remotion-rule-reviewer is an agent published in the GitHub repository chenyuxiaojin/cyxj-remotion-starter (6 stars, last pushed 2mo ago), licensed MIT. It adds 167 tokens to every session and 1,498 once invoked, about $0.0008 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 agents, from other repositories
internal-review-lead
A pre-delivery review agent that checks work against the stated quality standard. Its description is in Chinese and refers to internal review and quality checks.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.