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 agentmods add skills/thurbeen/thurbox/thurbox-kernelnpx skills add Thurbeen/thurbox --skill thurbox-kernelgit clone --depth 1 https://github.com/Thurbeen/thurboxWhat 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 | $0.00095 | $0.05398 |
| Opus 5 | $0.00048 | $0.02699 |
| Sonnet 5 | $0.00019 | $0.01080 |
| Haiku 4.5 | $0.00010 | $0.00540 |
Grade A, and why
thurbox-kernel 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 2d 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 — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thurbox plugin kernel and plugin authoring
Working reference extracted from CLAUDE.md, which indexes it. 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.
Architecture (plugin kernel)
The interface is Lua running on a Rust kernel. thurbox boots the kernel,
which reads ui/ and renders whatever plugins it finds; there is no built-in
pane. v1's src/app (TEA model/update/view) and src/ui (35 render modules) were
deleted when the kernel took the binary name — v1 lives on the v1.x branch.
The five rules
- Four node kinds, forever —
text,box,input,surface. Everything else composes inui/lib/widgets.lua.tests/kernel_mvp.rsasserts the count. - Layout resolves before render — rects are computed first, then each plugin is called with its own. Plugins declare size statically, in their declaration table, which is what breaks the circularity.
- Snapshot-read, command-write — reads come from an in-memory snapshot and return instantly; writes are commands accepted now and surfaced later. Lua never blocks, so no plugin can stall the loop on SQLite, git or an unreachable host.
- Capabilities by absence — an ungranted capability is not in the
environment.
io,os,debug,packageand the loaders are withheld, andthurbox.ymlmakes selene enforce that statically. One capability cannot be expressed that way: a program pane is asked for throughcommand, which every plugin has, sothurbox.grantedreports the grant instead — a boolean about a decision already made, which withholds nothing. - Anything touching the world runs on a worker — terminal attach, commands, diffs, metrics, git stats, repository reads, update checks, and programs a plugin asked for.
Module Dependency Rules (enforced by tests/architecture_rules.rs)
session ← pure data types, no crate-internal references
agent ← session (+ paths/shell utils; NEVER git)
kernel ← session + storage + sync + paths + session_ops + git
(+ agent/usage by fully-qualified path only)
main ← the coordinator: the loop, the workers, the chrome
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.
- 2d ago First seen · 322 lines · 0 tokens per session scan A 0d5477f99b46
thurbox-kernel is a skill published in the GitHub repository Thurbeen/thurbox (57 stars, last pushed 2d ago), licensed MIT. It adds 95 tokens to every session and 5,398 once invoked, about $0.0005 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
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…