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-session-status/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-session-status)<a href="https://agentmods.dev/skills/thurbeen/thurbox/thurbox-session-status"><img src="https://agentmods.dev/badge/skills/thurbeen/thurbox/thurbox-session-status/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-session-status"><img src="https://agentmods.dev/badge/skills/thurbeen/thurbox/thurbox-session-status.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 | $0.08756 |
| Opus 5.5 | $0.00000 | $0.03502 |
| Sonnet 5.5 | $0.00000 | $0.01751 |
| Haiku 4.5 | $0.00000 | $0.00876 |
Grade A, and why
thurbox-session-status 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 — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thurbox session status and notifications
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.
Session status (hooks-driven)
The session list shows, at a glance, which agents are blocked, working,
or done. SessionState (src/session/hook_status.rs) is the whole
vocabulary — one enum, every surface. Five of its words are the agent's own
hook report; the rest are thurbox's own, and each is spelled apart from idle
on purpose, because collapsing "nothing here is wired to report" or "the host
is gone" into "the agent says it is at rest" is exactly the conflation the
module exists to prevent:
| State | Colour | Glyph | Meaning |
|---|---|---|---|
working |
yellow | animated braille spinner (⠋⠙⠹…; static ◐) |
agent is actively running (hook) |
blocked |
red | ◆ |
agent needs input or approval (hook) |
done |
blue | ● (filled) |
a turn just finished; shown until you switch away (hook) |
background |
status_background (a purple per preset) |
◎ |
the turn is at rest and sub-work it started is still running — claude's background subagents (hook, issue #1510) |
idle |
green | ○ (hollow) |
acknowledged (you moved off a Done), never active, or at rest |
unreachable |
muted grey | ⊘ |
remote host down/offline; the ordinary row, derived from a live attach failure, awaiting reconnect |
running |
status_running (accent) |
◉, animated while its pane prints |
an agent holds the pane and nothing has signalled — an observation, never a claim about what it is doing |
uncovered |
status_unknown (muted) |
◌ |
this agent is wired to report nothing, so its silence means nothing |
unreported |
status_unknown (muted) |
◌ |
the agent can report and has not yet |
failed |
status_error |
✗ |
the launch died before the agent reported anything: a failed agents.toml setup step, or a hook-covered agent whose pane died with no report. Recorded once (thurbox.launch_failure meta + a changed/launch_failed event) by session_ops::launch_failure — the reconcile tick, session get, list --verify, wait, watch, and session exited on psmux — and published as launch_failure (reason, exit_code, output, pane, at). Outranks everything but stopped; the next launch clears it, and a record naming a pane the row has left is ignored. See docs/ORCHESTRATION.md → Launch failures |
stopped |
— | — | parked by session stop: no process at all, which is why it outranks whatever the hook columns still hold |
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 Changed · +1 lines e678dce26c1f
- 4d ago Changed · +8 lines 883be546d0cc
- 9d ago Changed · +76 lines f1f7163c3a52
- 10d ago Changed · +7 lines 25287b080151
- 12d ago Changed · +4 lines e5601fa97b10
- 15d ago Changed · +5 lines d2a7c9f20846
- 1mo ago Changed · +1 lines db0731873f44
- 1mo ago Changed 8933a1f72750
- 1mo ago Changed · +9 lines 5dbbf792fe92
- 1mo ago First seen · 377 lines · 0 tokens per session scan A 76ecde1e7073
thurbox-session-status 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 8,756 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.