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 vosslab/vosslab-skills --skill hang-checkgit clone --depth 1 https://github.com/vosslab/vosslab-skillsWrote 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/vosslab/vosslab-skills/hang-check)<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/hang-check"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/hang-check/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/vosslab/vosslab-skills/hang-check"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/hang-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00040 | $0.00916 |
| Opus 5 | $0.00020 | $0.00458 |
| Sonnet 5 | $0.00008 | $0.00183 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
hang-check 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 9d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hang check
Purpose
A dispatched subagent can hang: it stops making progress but never returns. This skill installs a recurring check that catches a real hang while leaving a slow-but-working agent alone. Judge on evidence, not the clock: elapsed time alone is never proof of a hang, because a long compile, model load, or remote wait looks identical to a stuck agent if you only watch the timer.
When to use
- One or more background subagents are running and may run long.
- The user asks for a watchdog, hang check, or "tell me if an agent gets stuck."
Skip it when no background subagents are active, when driving a single
foreground task turn by turn, or when the user wants live per-event log
streaming (use the Monitor tool for that).
Timer
Use CronCreate for the recurring check and CronDelete to remove it.
- Arm exactly one recurring job when the first watched subagent starts. One watchdog covers all active agents; do not arm a second.
- Every 10-15 minutes fits most work; shorten only if agents finish fast.
- The job prompt re-enters this skill: "Run hang-check: review each active subagent's status, recent output, and file activity; investigate any agent that looks stuck; remove the timer if no subagents remain active."
- Record the returned job ID for cleanup.
CronCreatejobs auto-expire after 7 days; tell the user if the watched work could run longer.
Evidence and decision
Each check, read up to three signals per active agent:
| Signal | How to read it |
|---|---|
| Agent status | TaskList / agent status: running, completed, or errored |
| Recent output | Latest lines (TaskOutput or output file) -- is it advancing? |
| File activity | New or changed files / mtimes in the work area, when relevant |
File activity is evidence only when the agent is expected to touch files. An agent that is researching, reading, or waiting on a remote call may make no file changes while healthy; do not treat missing file changes as a hang.
What ships with it
1 file 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.
- 9d ago First seen · 92 lines · 40 tokens per session scan A a670349012f3
hang-check is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 13d ago), licensed MIT. It adds 40 tokens to every session and 916 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…