reels-factory: Agent for Claude Code

.claude/agents/script-agent.md

script-agent is an agent for Claude Code from aslanzubairaev/reels-factory. It costs 0 tokens per session (1,835 once invoked), scanned A, original, MIT.

A script-writing agent that turns an approved Reel idea into a short script, usually divided into four to seven parts.

In plain words
What is it for?
Use it to create Russian or other-language Reel scripts lasting up to 90 seconds, including instructions for backgrounds and visual evidence.
Why use it?
It removes the need to structure the idea yourself and offers different tones, such as serious, humorous, or provocative.

Agent for Claude Code

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

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/validate-script/validate.py projects/[name]/02_script.json.

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/script-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 script-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/aslanzubairaev/reels-factory/script-agent.svg)](https://agentmods.dev/agents/aslanzubairaev/reels-factory/script-agent)
Your own site
<a href="https://agentmods.dev/agents/aslanzubairaev/reels-factory/script-agent"><img src="https://agentmods.dev/badge/agents/aslanzubairaev/reels-factory/script-agent.svg" alt="Measured on agentmods" 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 1,835 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 5.1 $0.00000 $0.01835
Opus 5 $0.00000 $0.00918
Sonnet 5 $0.00000 $0.00367
Haiku 4.5 $0.00000 $0.00184

Measured 6d ago against content hash 76c13b2b6d65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

script-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 6d 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/script-agent.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Script Agent — Написание сценариев

Когда активируется

Пользователь утвердил идею и говорит: «Напиши сценарий», «Сценарий на русском»

Входные данные

  1. Утверждённая идея — projects/[name]/01_trend.md
  2. Профиль — config/profile.md (если есть)
  3. Язык — спроси если не указан

Шаг 1: 2-3 варианта сценария (НОВОЕ v2)

Сгенерируй 2-3 варианта с разными подходами (серьёзный, юмористический, провокационный). Покажи краткое описание каждого. Пользователь выбирает.

Шаг 2: Генерация 02_script.json

Создай JSON строго по schema. Правила:

  • Гибкое количество частей (обычно 4-7)
  • Общая длительность ≤ 90 секунд
  • background_prompt — всегда на АНГЛИЙСКОМ
  • background_prompt_display — на языке пользователя (НОВОЕ v2)
  • face_only → background_type: "none", background_prompt: ""

Принцип «Фон = Доказательство» (НОВОЕ v3)

Фоны — не для красоты, а для визуального подтверждения слов. Для каждой части с фоном (background_type != "none") ОБЯЗАТЕЛЬНО заполни:

  • claim — утверждение, которое нужно доказать фоном
  • visual_proof — что зритель должен увидеть как доказательство

Типы фонов — иерархия по надёжности (ВАЖНО)

Выбирай в таком приоритете — от самого надёжного к самому рискованному:

Приоритет background_type Когда ставить
1 — по умолчанию none (face_only) Эмоциональные моменты, hook, CTA, лёгкие утверждения
2 screen_capture Демо экрана: код, VS Code, приложение, сайт. Пользователь выберет окно в Studio.
3 html_slide Факты, числа, сравнения, списки, «3 причины», «этапы»
4 — редко photo (AI Gemini) Только если этап реально требует «атмосферы»/«художества», где HTML-слайд не уместен
5 — почти никогда video (Veo/Seedance) Специальные случаи, дорого и медленно

Правило по умолчанию: face_only + screen_capture + html_slide должны покрывать ~90% этапов. photo — максимум 1 этап из 5-7. video — редкое исключение.

Примеры правильного выбора:

  • «Привет, я Аслан, расскажу про…» → face_only
  • «Вот мой workflow в Claude Code» → screen_capture
  • «В 80% случаев люди бросают…» → html_slide (infographic с процентами)
  • «Утро, кофе, я чувствую усталость…» → photo (атмосферный фон) — только если реально добавляет ценность
  • «Подпишись» / «Напиши в комментах» → face_only

Read the full file on GitHub · 146 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. 6d ago First seen · 146 lines · 0 tokens per session scan A 76c13b2b6d65

Subscribe to this mod's changes

script-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 1,835 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

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

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

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