Borrowing it
Nothing to install: this file belongs to claude-world/claude-world-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/claude-world/claude-world-studio/main/.claude/skills/studio/SKILL.mdgit clone --depth 1 https://github.com/claude-world/claude-world-studioWrote 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.
[](https://agentmods.dev/skills/claude-world/claude-world-studio/studio)<a href="https://agentmods.dev/skills/claude-world/claude-world-studio/studio"><img src="https://agentmods.dev/badge/skills/claude-world/claude-world-studio/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.
<a href="https://agentmods.dev/skills/claude-world/claude-world-studio/studio"><img src="https://agentmods.dev/badge/skills/claude-world/claude-world-studio/studio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 32 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 33 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 36 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 39 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00014 | $0.01753 |
| Opus 5 | $0.00007 | $0.00877 |
| Sonnet 5 | $0.00003 | $0.00351 |
| Haiku 4.5 | $0.00001 | $0.00175 |
Grade A, and why
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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude World Studio CLI
Full CLI for Claude World Studio. Maps 1:1 to the REST API + WebSocket.
Install
# Option A: npm global (recommended)
npm install -g @claude-world/studio
studio <command>
# Option B: From source
git clone https://github.com/claude-world/claude-world-studio.git
cd claude-world-studio && npm install
node bin/cli.js <command>
# or: npm link && studio <command>
# Option C: Electron Desktop App
npm run electron:dev # development
npm run electron:build # production (.app + .dmg)
MCP Server Setup
# One-command setup (uvx preferred, auto-cached)
npx @claude-world/studio setup-mcp
# Or legacy venv mode
npx @claude-world/studio setup-mcp --venv
# Update installed servers
npx @claude-world/studio setup-mcp --update
Quick Reference
# Server
studio serve # Start web UI
studio status # Check if running
# Sessions
studio session list
studio session create --title "Research" --workspace /path
studio session get <ID>
studio session rename <ID> --title "New Title"
studio session delete <ID>
studio session messages <ID> --limit 20
# Chat (WebSocket streaming)
studio chat --message "Find trends" --json
studio chat --session <ID> --message "Publish the best"
echo "What's trending?" | studio chat --json
studio interrupt <ID>
# Accounts
studio account list
studio account create --name "Main" --handle "@me" --platform threads --token TOKEN
studio account update <ID> --token NEW_TOKEN
studio account delete <ID>
# Settings
studio settings get
studio settings detect # Scan system for MCP tools
studio settings apply # Apply detected values
studio settings set --language en --default-workspace /path
# Publishing (supports all Threads post types)
studio publish --account <ID> --text "Hello!" --score 85
studio publish --account <ID> --text "Vote!" --poll "Option A|Option B"
studio publish --account <ID> --text "Look!" --image "https://url/img.png"
studio publish --account <ID> --text "Watch" --video "https://url/vid.mp4"
studio publish --account <ID> --text "Slides" --carousel URL1 URL2 URL3
studio publish --account <ID> --text "Mood" --gif-id "GIPHY_ID"
studio publish --account <ID> --text "Read" --link-attachment "https://url"
studio publish --account <ID> --text "TL;DR" --text-attachment article.txt
studio publish --account <ID> --text "Spoiler!" --image URL --spoiler-media
studio publish --account <ID> --text "Secret text" --spoiler-text "7:4"
studio publish --account <ID> --text "24hr only" --ghost
studio publish --account <ID> --text "My take" --quote-post-id "12345"
studio publish --account <ID> --text "Post" --reply-control mentioned_only
studio publish --account <ID> --text "Post" --topic-tag "AI" --alt-text "desc"
studio publish --account <ID> --text "Post" --link-comment "https://url"
studio history --limit 10
# Files
studio file list <SESSION_ID> --depth 2
studio file read <SESSION_ID> src/index.ts
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.
- 9d ago First seen · 192 lines · 14 tokens per session scan A 14fea444f07a
studio is a skill published in the GitHub repository claude-world/claude-world-studio (72 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 1,753 once invoked, about $0.0001 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.
Other skills, from other repositories
notebooklm-research
Automate source-grounded research with Google NotebookLM. Create notebooks from URLs, text, or local files; ask cited questions; run fast or deep web research; create articles and social drafts; and generate or download audio, video, cinematic video, slides, reports, study guides, quizzes, flashcards, mind maps…
cf-cowork-setup
One-shot setup that wires ContentForge for team usage in Anthropic Cowork — verifies the Cowork sandbox environment, checks a Google Drive MCP is connected, creates the canonical Drive folder layout (brands/, runs/), and persists the team's routing config so .docx outputs, brand profiles, and checkpoints land in…
google-tasks
Manage Google Tasks via the gtasks CLI. Use when the user asks to view, add, update, complete, or delete tasks. Supports multiple task lists.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.