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-agents/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-agents)<a href="https://agentmods.dev/skills/thurbeen/thurbox/thurbox-agents"><img src="https://agentmods.dev/badge/skills/thurbeen/thurbox/thurbox-agents/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-agents"><img src="https://agentmods.dev/badge/skills/thurbeen/thurbox/thurbox-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Rogue Agent · line 24 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.04084 |
| Opus 5.5 | $0.00000 | $0.01634 |
| Sonnet 5.5 | $0.00000 | $0.00817 |
| Haiku 4.5 | $0.00000 | $0.00408 |
Grade A, and why
thurbox-agents 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 yesterday.
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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thurbox agent definitions
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.
Agent Definitions
Per-agent reference + the "adding a new built-in" checklist:
docs/AGENTS.md(each built-in's exact config, ID model, and status-hook mechanism, plus every file to update when promoting a CLI to a built-in).
The set of launchable coding agents is declared as data in
~/.config/thurbox/agents.toml, seeded with built-ins
(claude, codex, antigravity, opencode, aider, copilot, vibe, pi, omp)
plus shell on first run.
shell is the one seeded entry that is not a coding agent: the platform's own
interactive shell (bash -i, or powershell -NoLogo on native Windows, where
the multiplexer is psmux). The platform is the session's host: while the entry (or its inherited variant)
is still a stock command/args pair, session_ops::resolve_agent_def swaps in
the host's own
(shell::shell_agent_def); an edited shell is launched as written. It exists so a session can be anything, and it is
the ready-made form of session create --command. Because it declares no
resume_args/fork_args, it also documents the rule by example: those groups
are the conversation address, and an entry without them can be restarted but
never resumed. A raw --command session behaves identically — thurbox builds it
a synthetic AgentDef with empty arg groups and persists the recipe on the
session row, since there is no agents.toml entry to re-resolve at restart.
Each [[agents]] entry is an AgentDef:
default = "claude"
[[agents]]
name = "claude"
command = "claude"
args = [] # always passed; bake a model here if you want one
resume_args = ["--resume", "{id}"] # emitted when resuming
fork_args = ["--resume", "{id}", "--fork-session"]
new_session_args = ["--session-id", "{id}"] # emitted on a fresh spawn
additional_dir_args = ["--add-dir", "{dir}"] # repeated per multi-repo member
[[agents]]
name = "codex"
command = "codex"
resume_args = ["resume", "{id}"]
fork_args = ["fork", "{id}"]
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.
- yesterday Changed · +4 lines f5251d875fee
- 2d ago Changed · +28 lines 70d9008201c1
- 4d ago Changed · +2 lines 2c439e488507
- 5d ago Changed · +17 lines cd23a4007163
- 7d ago Changed · +17 lines d420384d3ec7
- 11d ago Changed · +4 lines 6739a8fe31a0
- 12d ago Changed · +13 lines c181d5bad0a1
- 15d ago Changed · +2 lines 989139a381d0
- 17d ago Changed · +6 lines ef032b734ea9
- 1mo ago First seen · 161 lines · 0 tokens per session scan A 0dea28232314
thurbox-agents 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 4,084 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.