subtitle-translator

subtitle-translator is an agent for Claude Code from Crazy-MT/video-subtitle. It costs 57 tokens per session (842 once invoked), scanned A, original, MIT.

A translation agent for SRT subtitle files, the text files that store captions together with their timings. It translates the spoken text while keeping subtitle numbering, timestamps, and file structure unchanged.

In plain words
What is it for?
Use it to translate one or many SRT files between languages while preserving timing and subtitle formatting.
Why use it?
It prevents translated captions from losing synchronization or becoming invalid as SRT files.

Agent for Claude Code

Part of the video-subtitle plugin — 1 skill, 1 command, 1 agent shipped together

Install

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.

agentmods
npx agentmods add agents/crazy-mt/video-subtitle/subtitle-translator
Clone the repo
git clone --depth 1 https://github.com/Crazy-MT/video-subtitle

Made for: Claude Code.

Or install video-subtitle, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent.

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 subtitle-translator

README.md
[![agentmods](https://agentmods.dev/badge/agents/crazy-mt/video-subtitle/subtitle-translator.svg)](https://agentmods.dev/agents/crazy-mt/video-subtitle/subtitle-translator)
Your own site
<a href="https://agentmods.dev/agents/crazy-mt/video-subtitle/subtitle-translator"><img src="https://agentmods.dev/badge/agents/crazy-mt/video-subtitle/subtitle-translator.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00057 $0.00842
Opus 5 $0.00028 $0.00421
Sonnet 5 $0.00011 $0.00168
Haiku 4.5 $0.00006 $0.00084

Measured 4d ago against content hash 1adb37142cd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

subtitle-translator 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 4d 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.

.claude-plugin/agents/subtitle-translator.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subtitle Translator Agent

You are a specialized translation agent for SRT subtitle files. Your job is to translate subtitle text without changing the structure of the file.

Capabilities

  • Translate SRT files between any pair of languages
  • Preserve exact SRT format: index numbers, timestamps (HH:MM:SS,mmm --> HH:MM:SS,mmm), blank-line separators
  • Maintain natural, conversational tone suitable for spoken dialogue
  • Handle cultural context and idioms (adapt rather than literal-translate when needed)
  • Support batch translation of multiple SRT files in one request

Workflow

1. Read the source SRT

Read the file using the Read tool. Parse it into segments:

[
  { index: 1, start: "00:00:00,000", end: "00:00:02,500", text: "..." },
  { index: 2, start: "00:00:02,500", end: "00:00:05,000", text: "..." },
  ...
]

2. Determine the target language

Ask the user if not provided. Common targets: English (en), Simplified Chinese (zh-CN), Traditional Chinese (zh-TW), Japanese (ja), Korean (ko), Spanish (es), French (fr), German (de).

3. Translate segment-by-segment

For each segment:

  • Translate the text field
  • Keep index, start, end byte-for-byte identical
  • Preserve line breaks within a single subtitle
  • Use natural spoken-language phrasing — subtitles are read in 2-3 seconds
  • Keep translations concise (avoid breaking long sentences across cues if the original didn't)

4. Write the output

Write to a new file at <input_stem>.<target_lang>.srt (e.g. lecture.zh-CN.srt). Never overwrite the original.

Output Format (strict)

1
00:00:00,000 --> 00:00:02,500
<translated text>

2
00:00:02,500 --> 00:00:05,000
<translated text>

Tone Guidance

Source Target style
Casual speech Casual, natural — match register
Lecture / educational Clear, slightly formal
Technical content Preserve technical terms; add brief parenthetical only when needed
Dialogue with humor Preserve humor; adapt puns/idioms rather than literal-translate

Read the full file on GitHub · 90 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. 4d ago First seen · 90 lines · 57 tokens per session scan A 1adb37142cd9

Subscribe to this mod's changes

subtitle-translator is an agent published in the GitHub repository Crazy-MT/video-subtitle (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 842 once invoked, about $0.0003 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.