What is stream-studio?

A workflow for turning a livestream or recorded video into organised files such as a transcript, clips, subtitles, chapters, thumbnails, and summary videos. It uses a standard folder layout so related files stay linked.

Use it to process a stream, find and cut topic clips, make short videos or a highlight reel, create subtitles and chapters, and prepare YouTube copy.

It removes the repeated manual work of finding topics, cutting clips, naming files, and keeping captions and chapter timings together. The organised files also make the video work easier to rebuild later.

stream-studio — Skill for Claude Code by donvito/skillsbento

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.

Any agent

npx skills add donvito/skillsbento --skill stream-studio

Clone the repo

git clone --depth 1 https://github.com/donvito/skillsbento

Made for: Claude Code.

Or install stream-shorts, the plugin that ships this one along with the rest of its 1 skill, 2 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/donvito/skillsbento/stream-studio/github.svg)](https://agentmods.dev/skills/donvito/skillsbento/stream-studio)

Your own site

<a href="https://agentmods.dev/skills/donvito/skillsbento/stream-studio"><img src="https://agentmods.dev/badge/skills/donvito/skillsbento/stream-studio/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/donvito/skillsbento/stream-studio"><img src="https://agentmods.dev/badge/skills/donvito/skillsbento/stream-studio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 174 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,193 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.

Model	Per session	Once invoked
Fable 5.1	$0.00174	$0.01193
Opus 5.5	$0.00070	$0.00477
Sonnet 5.5	$0.00035	$0.00239
Haiku 4.5	$0.00017	$0.00119

Measured 10d ago against content hash 0a7a7967027f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stream-studio 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 10d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (assets/kit.js, engine/assets/engine.js, engine/scripts/build.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/stream-shorts/skills/stream-studio/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stream Studio

One skill for the whole pipeline: raw stream → transcript + chapters + clips → summary reel / shorts → YouTube copy. All files follow one folder layout and naming scheme so a clip, its transcript, subtitles, chapters and thumbnail always link together, and every video is rebuildable from its version folder.

SKILL=<this skill's base directory>
$SKILL/scripts/stream.py     doctor · init · transcribe · clips · reel · short-new · short-build · migrate
$SKILL/scripts/short.py      shorts engine front end: doctor · brand · transcribe · frame · cut · scaffold · balance
$SKILL/engine/  assets/      motion-reel renderer, kit.js, fonts
$SKILL/references/           folders.md · process-stream.md · make-shorts.md · style.md · kit-api.md · youtube.md

Which workflow?

the user says	do	read
`/process-stream video.mp4`, "clip my stream", "transcript", "chapters", "subtitles"	process the stream	`references/folders.md`, then `references/process-stream.md`
"summary video of all features", recap, highlight reel	summary reel (longform)	`references/process-stream.md` → Summary reel
`/make-shorts <topic or file>`, "make a short", "vertical", "reel"	make shorts	`references/folders.md`, then `references/make-shorts.md` (+ `style.md`, `kit-api.md`, `youtube.md`)
"chapter timings I can paste in X/YouTube"	chapters	`references/process-stream.md` → Chapters
"title and description"	YouTube copy	`references/youtube.md`

A request often chains them ("process this stream and make a short on dots"): do /process-stream first, then shorts from the clips.

Works in Claude Code and Codex

The skill is the same in both. /process-stream and /make-shorts are Claude Code commands only; in Codex ask in plain words or mention the skill ($stream-studio process my stream video.mp4, $stream-studio make a 30s short about <topic>).
Tool names in these docs are generic: "run in the background" = Claude Code's Bash run_in_background, or in any agent nohup <cmd> > .work/job.log 2>&1 & and poll the log; "ask the user" = a question tool if you have one, otherwise a short numbered list in chat; "look at a frame" = open the PNG with your image-viewing tool.
Python scripts locate themselves ($SKILL = the folder holding this file), so the skill works from any install location.

Read the full file on GitHub · 47 lines

Files

What ships with it

27 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

10d ago First seen · 47 lines · 174 tokens per session scan A 0a7a7967027f

Subscribe to this mod's changes

stream-studio is a skill published in the GitHub repository donvito/skillsbento (9 stars, last pushed 10d ago), licensed Apache-2.0. It adds 174 tokens to every session and 1,193 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-01.

Creative and media

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.