Borrowing it
Nothing to install: this file belongs to Thurbeen/thurbox. 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/Thurbeen/thurbox/main/.agents/skills/thurbox-demo-media/SKILL.mdgit clone --depth 1 https://github.com/Thurbeen/thurboxWrote 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/thurbeen/thurbox/thurbox-demo-media)<a href="https://agentmods.dev/skills/thurbeen/thurbox/thurbox-demo-media"><img src="https://agentmods.dev/badge/skills/thurbeen/thurbox/thurbox-demo-media/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/thurbeen/thurbox/thurbox-demo-media"><img src="https://agentmods.dev/badge/skills/thurbeen/thurbox/thurbox-demo-media.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.01637 |
| Opus 5.5 | $0.00000 | $0.00655 |
| Sonnet 5.5 | $0.00000 | $0.00327 |
| Haiku 4.5 | $0.00000 | $0.00164 |
Grade A, and why
thurbox-demo-media 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 27d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thurbox demo videos and screenshots
Working reference indexed by AGENTS.md. The rationale behind these decisions is owned by the docs under docs/; a change that invalidates what this says updates it in the same PR.
Demo Video
The hero demo is its own recorder. scripts/demo/record-hero.sh writes
media/thurbox-demo.{gif,mp4} (the README GIF, the website's first video) and
website/assets/thurbox-demo-poster.webp in one run. It is not a tape: thurbox
runs under asciinema inside a private tmux server, tmux send-keys presses the
real chords, and the context menu is opened by sending the SGR mouse report of a
right press, which VHS cannot do. The remote host devbox is declared in the
sandbox's hosts.toml and reached through a stand-in ssh on PATH that runs
the command on this machine under devbox's own HOME and tmux socket directory —
the same stand-in tests/backend_routes.rs uses, so everything past the ssh
binary is the real remote path and nobody needs a second machine to rerun it.
Every socket it creates has a name only it uses (thurbox-hero*), never
thurbox, because its teardown kills them by name. agg needs a Nerd Font and
Noto Sans Symbols 2 in FONT_DIR (the header says why only the first is named).
The README GIF is a second agg pass at a smaller font, not an ffmpeg re-encode,
which turned agg's change-only frames into ~66 MB of full frames.
The VHS recordings are stale. Every clip a tape produces was recorded against v1 and shows panes the interface no longer has — code review, the file viewer, the tasks and automations panels. The tapes themselves drive v1 chords, so they need rewriting before re-recording is worth doing. Until then the website's feature clips and the README's session-creation and interface GIFs show an interface that is gone.
doom-easter-egg.mp4is the exception: it is not a tape, and it was re-recorded against v2 when Doom became a plugin (below).
The media is generated, not hand-recorded. One script drives the real TUI via
VHS (needs vhs + ffmpeg + ttyd +
tmux) and writes GIF and MP4 into media/:
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.
- 27d ago Changed · +19 lines 55e6904200dc
- 1mo ago Changed e8e24b2a40c7
- 2mo ago First seen · 81 lines · 0 tokens per session scan A 29092e4b55b3
thurbox-demo-media is a skill published in the GitHub repository Thurbeen/thurbox (115 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,637 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 2026-08-30.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
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.