reels-factory: Agent for Claude Code

.claude/agents/transcribe-agent.md

transcribe-agent is an agent for Claude Code from aslanzubairaev/reels-factory. It costs 0 tokens per session (851 once invoked), scanned A, original, MIT.

An agent that turns a recorded video into corrected text and timestamped segments; timestamps show when each passage occurs.

In plain words
What is it for?
Processing recording_full.mp4 files with Whisper, correcting the text, and producing transcript, timestamp, word-timing, and correction files.
Why use it?
It provides both a raw transcription and a reviewed version, making the recording easier to search and use for subtitles.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is aslanzubairaev/reels-factory's own configuration. It tells Claude Code how to work on reels-factory itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything reels-factory configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python .claude/skills/transcribe/transcribe.py "projects/{name}/output/recording_full.mp4".

Reuse

Borrowing it

Nothing to install: this file belongs to aslanzubairaev/reels-factory. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aslanzubairaev/reels-factory/master/.claude/agents/transcribe-agent.md
Clone the repo
git clone --depth 1 https://github.com/aslanzubairaev/reels-factory

Made for: Claude Code.

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 transcribe-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/aslanzubairaev/reels-factory/transcribe-agent/github.svg)](https://agentmods.dev/agents/aslanzubairaev/reels-factory/transcribe-agent)
Your own site
<a href="https://agentmods.dev/agents/aslanzubairaev/reels-factory/transcribe-agent"><img src="https://agentmods.dev/badge/agents/aslanzubairaev/reels-factory/transcribe-agent/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 transcribe-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/aslanzubairaev/reels-factory/transcribe-agent"><img src="https://agentmods.dev/badge/agents/aslanzubairaev/reels-factory/transcribe-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 851 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 $0.00000 $0.00851
Opus 5 $0.00000 $0.00426
Sonnet 5 $0.00000 $0.00170
Haiku 4.5 $0.00000 $0.00085

Measured 11d ago against content hash cb24a5806fae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

transcribe-agent 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 11d 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/agents/transcribe-agent.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Агент 6: Транскрибатор

Роль

Транскрибирует записанное видео в текст с таймкодами, затем исправляет ошибки распознавания.

Когда вызывать

После записи видео в Studio (после получения recording_full.mp4).

Вход

  • projects/{name}/output/recording_full.mp4 — записанное видео

Выход (в projects/{name}/output/)

  • transcript_raw.txt — сырой текст от Whisper (до правок)
  • transcript.txt — исправленный текст (после правок Claude)
  • transcript.json — сегменты с таймкодами [{start, end, text}]
  • words_raw.json — пословные таймкоды (для субтитров)
  • transcript_corrections.md — таблица исправлений

Пошаговая инструкция

Шаг 1: Проверка входного файла

  1. Убедись что projects/{name}/output/recording_full.mp4 существует
  2. Если файла нет — выведи ошибку: "Файл recording_full.mp4 не найден. Сначала запиши видео в Studio."
  3. Не угадывай, не ищи другие файлы, не пропускай этот шаг.

Шаг 2: Транскрипция через Whisper

Запусти скилл транскрипции:

python .claude/skills/transcribe/transcribe.py "projects/{name}/output/recording_full.mp4"

Скилл создаст:

  • transcript_raw.txt — сырой текст
  • transcript.json — сегменты с таймкодами
  • words_raw.json — пословные таймкоды

Шаг 3: Исправление текста (Claude)

  1. Прочитай transcript_raw.txt
  2. Исправь:
    • Технические термины (Python, JavaScript, React, API, и т.д. — правильное написание)
    • Бренды (Instagram, YouTube, GitHub — правильный регистр)
    • Пунктуацию (точки, запятые, тире)
    • Слова-паразиты (убрать "ну", "типа", "вот" если они не несут смысл)
    • Повторы слов (заикания)
  3. НЕ меняй смысл, НЕ добавляй новые мысли, НЕ переписывай предложения
  4. Сохрани исправленный текст в transcript.txt
  5. Обнови тексты сегментов в transcript.json (таймкоды НЕ трогай!)

Шаг 4: Таблица исправлений

Создай transcript_corrections.md:

# Исправления транскрипции

| # | Было | Стало | Причина |
|---|------|-------|---------|
| 1 | питон | Python | Техн. термин |
| 2 | гитхаб | GitHub | Бренд |

Read the full file on GitHub · 84 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. 11d ago First seen · 84 lines · 0 tokens per session scan A cb24a5806fae

Subscribe to this mod's changes

transcribe-agent is an agent published in the GitHub repository aslanzubairaev/reels-factory (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 851 tokens. 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.

Related

Other agents, from other repositories

visual-critic

Independently inspect generated or edited image files against a frozen brief. Use after generation for high-value, branded, text-heavy, edited, or multi-candidate work. Never generate, edit, or rewrite files.

AgriciDaniel/banana-claude · 47 tokens

encoder

Executes video/audio encodes with the right codec, container, and flags for the target. Use after the architect has produced a plan, or when the user has a clear target ("re-encode this to H.265 10-bit under 5 Mbps", "transcode to ProRes 422 HQ for Premiere"). Owns rate-control math, preset selection, pixel format…

damionrashford/media-os · 83 tokens

hdr

Handles HDR color workflows end-to-end — HDR10 static metadata, HDR10+ dynamic metadata, Dolby Vision profiles, PQ↔HLG conversion, SDR↔HDR tone mapping, and ACES/OCIO color management. Use when the user mentions Dolby Vision, HDR10, HDR10+, HLG, PQ, tone mapping, or anything about color pipelines that must survive…

damionrashford/media-os · 80 tokens

architect

Designs end-to-end media pipelines before a single command runs. Use when the user describes an unfamiliar workflow ("how do I deliver a Dolby Vision MP4 for Apple TV", "stream 4K HDR to HLS + DASH with DRM") and needs a plan that picks the right skills and ordering. Produces a staged recipe with exact tools, not just…

damionrashford/media-os · 76 tokens

gemini-image-gen

Image generation and editing agent. Creates photos, illustrations, icons, website visuals, placeholders, banners, thumbnails, and any graphic asset. Edits, retouches, and applies style transfer to existing images. Use for any task requiring image creation or manipulation.

Ibrahim-3d/nano-banana-claude-plugin · 56 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens