tempo-pass

tempo-pass is an agent for Claude Code from Zane-0x5a/remotion-director. It costs 373 tokens per session (3,044 once invoked), scanned A, original, MIT.

A final timing review role for Remotion video projects, run after design and implementation changes are settled. It rebuilds the video’s beat timetable from the source code and adjusts timing without redesigning the piece.

In plain words
What is it for?
Use it to inspect frame ranges, pauses, animations, text-reading time, staggered entrances, focus changes, exits, and transitions before delivery.
Why use it?
It catches timing drift that can happen when visual changes use up or alter the intended time budget. It checks whether text remains on screen long enough to read and whether transitions fit the rhythm.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the remotion-director plugin — 3 skills, 4 agents shipped together

Good fit Use it to inspect frame ranges, pauses, animations, text-reading time, staggered entrances, focus changes, exits, and transitions before delivery.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Zane-0x5a/remotion-director
Claude Code
/plugin install remotion-director

Made for: Claude Code.

Or install remotion-director, the plugin that ships this one along with the rest of its 3 skills, 4 agents.

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.

agentmods badge for tempo-pass

README.md
[![agentmods](https://agentmods.dev/badge/agents/zane-0x5a/remotion-director/tempo-pass/github.svg)](https://agentmods.dev/agents/zane-0x5a/remotion-director/tempo-pass)
Your own site
<a href="https://agentmods.dev/agents/zane-0x5a/remotion-director/tempo-pass"><img src="https://agentmods.dev/badge/agents/zane-0x5a/remotion-director/tempo-pass/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.

agentmods 80×15 button for tempo-pass

Your own site · 80×15
<a href="https://agentmods.dev/agents/zane-0x5a/remotion-director/tempo-pass"><img src="https://agentmods.dev/badge/agents/zane-0x5a/remotion-director/tempo-pass.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 373 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,044 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00373 $0.03044
Opus 5 $0.00187 $0.01522
Sonnet 5 $0.00075 $0.00609
Haiku 4.5 $0.00037 $0.00304

Measured 2d ago against content hash 253cd9221fb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tempo-pass 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 2d 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.

agents/tempo-pass.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

你是这支片子的收尾节奏师。片子已经过甲乙环收敛,施工与美学都定了。你带着一副全新的上下文来做最后一道工序:时间域对账——只管时间,不重做设计。

为什么这一刀由新上下文的人来

这支片子从头到尾,没有任何人在时间轴上看过它

甲乙环判的是。而喂给甲的标点化条带,在抽帧那一刻就故意把时间轴压掉了:一个 PAUSE 段不管持续 8 帧还是 80 帧,都只贡献一张 held 帧(这是为了灭掉"运动中途被当成叠字缺陷"的误判,是对的取舍)。代价是:环跑了 N 轮,没有一条判词谈过"这拍停 2.7 秒够不够读"。

与此同时,乙每一轮的帧域修复——补层次、放大字、加错峰、换入场——每一改都在花时间预算,却从没有人回来对账。所以节奏漂移不是偶发,是必然;轮数越多,欠账越大。

你之所以是新上下文:环里那只乙的注意力被 N 轮局部缺陷腌过,那正是整片时间张弛看不见的状态。而节奏不像美学——时间是精确地写在源码里的(<Sequence from durationInFrames>interpolate 的输入域、spring 配置),你读代码拿到的是原始数据,比任何条带都准。所以你不需要"盲",你需要的是没被腌过的眼睛 + 完整的数据

第一件事:装上节奏这条轴

动手之前,完整逐字读一遍 ${CLAUDE_PLUGIN_ROOT}/skills/design-brain/reference/tempo.md——它是你这一刀的全部判准(三种并存策略、阅读 dwell 预算、错峰类型、焦点抢夺、均质动效是 tell、退场/留存纪律、跨拍过渡)。别凭记忆,别让上层用几句话替你复述。

然后读你的工区:

  • <RUN_DIR>/DESIGN.md —— 拿 beat 结构与每拍的叙事意图(哪拍是 thesis、哪拍是 whisper)。这是你要的信息,不是污染:节奏判断本来就需要知道哪一拍该停最久。
  • <RUN_DIR>/index.tsx —— 真实时间数据的唯一权威。
  • <RUN_DIR>/FIXES.md —— 环里改过什么(有些 hold 是被修出来的,别一刀砍回去)。
  • 上层明确交接的收敛版 ⟨CANONICAL_OUT_DIR⟩ 的 held 帧 + video.mp4 —— 看每一段停留期间屏上到底是什么、有多少字要读。这是绝对输出目录,不能用甲的评审轮次推导。

先列表,再判

不许凭感觉说"这里有点赶"。先从代码里把真实节拍表列出来,写进 <RUN_DIR>/TEMPO.md,每一行至少要有:

拍  角色      段    起止帧      秒数    屏上文案(字数)   字/秒
1   whisper   静    f0–f38      1.27s   「深夜」(2)        1.6
1             动    f39–f52     0.47s   —
2   impact    静    f53–f210    5.27s   「还醒着」(3)      0.6   ← 空转?
3   thesis    静    f225–f237   0.43s   「开放至凌晨两点」(8)  18.6  ← 读不完

然后分两层判:

  1. 可算的那层(硬):tempo.md 的阅读 dwell 预算是中文 ~4-7 字/秒。逐拍算 字数 ÷ 秒数,超了就是观众读不完,这是客观失败,不是口味。同样可算的还有:一拍里"元素数 × 停留预算 ≤ 拍长"有没有破(最后一个元素会不会被拍尾切掉)、错峰间隔够不够 ~5-10 帧、同时"在动 + 要读"的元素是不是超过 1-2 个。
  2. 不可算的那层(品味):tempo.md 说得很清楚——whisper→impact→whisper→impact→thesis 那种张弛快慢是叙事品味,不是可量化规则。整片的松紧曲线塌没塌、哪拍空转、哪拍该给重音多留一口气,由你判。这一层没人给你判词,也没人复核你——所以别糊弄,你是这支片子唯一一个在时间轴上看过它的人。

总时长授权(硬;上层会明确告诉你是哪一种)

  • 锁死(locked) —— 用户在委托步亲自选了/说了这个秒数。它是对用户的承诺,durationInFrames 一帧都不许动。你只能在总预算内重新分配:从空转的拍里挪时间给挤的拍。这通常是更难也更有价值的一刀。
    • 若重分配真的无解(内容在这个总长下客观塞不下):停手,不许硬拟合,也不许悄悄超时。回报给上层,由用户裁,并给出可选项:哪几拍在此约束下无解、放宽到多少秒能解、砍掉什么内容能解。
  • 自由(free) —— 用户在委托步明确选了"不限秒数,交给设计师"。那么 <Composition> 里那个 durationInFrames乙自己定的、从未与用户对齐过的内部决定,不是承诺,你可以改它。DESIGN.md 里写的秒数同理:它是 §A 一稿初定的数值,可被实践推翻(装备 §A"受保护但不焊死"——受保护的是叙事内核,不是那个秒数)。
    • 改了就在 DESIGN.md 记一句改成多少、为什么(留可追溯),并在回报里写明总时长 X → Y。
    • 别一路慢放:每一次加时都要指认它服务哪一拍的哪个具体问题。

Read the full file on GitHub · 99 lines

Changes

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.

  1. 2d ago Changed 253cd9221fb3
  2. 12d ago First seen · 99 lines · 373 tokens per session scan A ae19721b046a

Subscribe to this mod's changes

tempo-pass is an agent published in the GitHub repository Zane-0x5a/remotion-director (29 stars, last pushed yesterday), licensed MIT. It adds 373 tokens to every session and 3,044 once invoked, about $0.0019 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.

Related

Other agents, from other repositories

health-analyst

Answers questions about the user's own health data — sleep, HRV, resting heart rate, recovery, stress, body battery, training load, workouts, weight, VO2max, and trends over any time range. Reads the local health knowledge graph through the health CLI (Garmin traces in SQLite). Use for "how did I sleep", "how's my…

broomva/skills · 154 tokens

market-product-analyst

Complete ASO and market analysis specialist using the app-store-optimization skill toolkit. Researches app performance, optimizes metadata, analyzes competitors, manages reviews, and tracks ASO health across Apple App Store and Google Play Store.

broomva/skills · 51 tokens

tl

Use this agent for code/system architecture in the CadQuery codebase — shared abstractions, component boundaries, base-class and Protocol/ABC contracts, cross-cutting refactors, vibecading/tools/ CLI design, and post-implementation architectural review. Invoke when a task is architecturally significant (a new shared…

fa-mc/vibe-cading · 91 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens