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.
npx skills add Thurbeen/thurbox --skill ui-skillgit 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/ui-skill)<a href="https://agentmods.dev/skills/thurbeen/thurbox/ui-skill"><img src="https://agentmods.dev/badge/skills/thurbeen/thurbox/ui-skill/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/ui-skill"><img src="https://agentmods.dev/badge/skills/thurbeen/thurbox/ui-skill.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 | $0.00122 | $0.03507 |
| Opus 5.5 | $0.00049 | $0.01403 |
| Sonnet 5.5 | $0.00024 | $0.00701 |
| Haiku 4.5 | $0.00012 | $0.00351 |
Grade A, and why
thurbox-ui 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 1mo 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editing the thurbox interface
Managed by thurbox
extension install— see Updating this skill at the bottom before editing it.
thurbox's interface has no built-in screen underneath. Every pane is a Lua file in one directory, the kernel reads that directory at startup, and saving a file reloads it. Changing the TUI means editing Lua there — never Rust, and never the repository this session happens to be sitting in.
First: find the directory
The interface is not in the current repo. It is a config directory of the user's, so it is almost always outside this session's worktree:
thurbox-cli plugin dir # the directory in force, and which rule chose it
Two rules pick it: THURBOX_UI_DIR if set, otherwise the user's own copy —
~/.config/thurbox/ui, or ~/.config/thurbox-dev/ui for a dev build. Run the
command; do not assume which. If you cannot write outside this session's
worktree, say so and ask for that path to be allowed — do not edit something
else instead and report it as done.
A thurbox checkout's ui/ is not the live interface. Editing ui/ inside a
clone of the thurbox repository changes nothing on screen unless
THURBOX_UI_DIR points at it (just tui-ui in that repo does exactly that). If
the user wants their running thurbox changed, the destination is plugin dir's
answer. If they want the shipped interface changed, it is the checkout, and
that is a code change with a pull request behind it — ask which they mean when
both are plausible.
Then: read the directory's own docs
The directory ships the reference, and it is versioned with the binary the user is running, so it is more current than anything you remember:
UI="$(thurbox-cli plugin dir --text | head -1)" # or: plugin dir --json | jq -r .dir
cat "$UI/AGENTS.md" # the operational half — what is easy to get wrong
cat "$UI/README.md" # the reference — node kinds, the API, the traps
cat "$UI/layout.lua" # the arrangement — which slots exist and where
ls "$UI/plugins" "$UI/lib"
What ships with it
2 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.
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.
- 1mo ago Changed bd772e8525f9
- 1mo ago Changed · +1 lines 03071fd152f7
- 2mo ago First seen · 258 lines · 122 tokens per session scan A e782557cf7de
thurbox-ui is a skill published in the GitHub repository Thurbeen/thurbox (115 stars, last pushed today), licensed MIT. It adds 122 tokens to every session and 3,507 once invoked, about $0.0005 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 2026-08-30.
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.