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 ariana-dot-dev/cloud-sandbox-vm-skills --skill background-workergit clone --depth 1 https://github.com/ariana-dot-dev/cloud-sandbox-vm-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/ariana-dot-dev/cloud-sandbox-vm-skills/background-worker)<a href="https://agentmods.dev/skills/ariana-dot-dev/cloud-sandbox-vm-skills/background-worker"><img src="https://agentmods.dev/badge/skills/ariana-dot-dev/cloud-sandbox-vm-skills/background-worker.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.00470 |
| Opus 5 | $0.00042 | $0.00235 |
| Sonnet 5 | $0.00017 | $0.00094 |
| Haiku 4.5 | $0.00008 | $0.00047 |
Grade C, and why
background-worker scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
`curl -fsSL https://box.ascii.dev/install | sh`, then `box login "$BOX_API_KEY" --json`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -fsSL https://box.ascii.dev/install | sh`, then `box login "$BOX_API_KEY" --json`. What it actually says
Background / 24-7 worker (Box)
Use this when work must keep running unattended: a queue worker, a Telegram/Discord bot, a polling agent, a scheduled scraper, or any always-on service. Ephemeral sandboxes (E2B microVMs, Codespaces) auto-die on a timer — wrong tool. A Box can be told to never auto-stop, persists its disk, and keeps a dedicated IPv4.
Why Box
- No session cap — runs hours/days/indefinitely.
- Persistent + resumable — disk survives stop;
box resumebrings it back. - Cheap steady-state — flat per-second pricing beats ephemeral providers (50 always-on VMs ≈ $432/mo vs ~$4k+).
Prereqs
curl -fsSL https://box.ascii.dev/install | sh, then box login "$BOX_API_KEY" --json.
Recipe
box_id="$(box new --no-auto-stop --json | jq -r 'select(.event == "ready") | .id')"
box ssh "$box_id" -- bash -s < ./setup.sh
box ssh "$box_id" -- "cd /app && nohup ./worker.sh > /var/log/worker.log 2>&1 &"
box extend "$box_id" --ttl 2592000 # optional: 30-day deadline
Survival rules
Running processes do not survive stop/resume or fork — only the disk does. Make startup idempotent and relaunch after resume; use a process manager (systemd, pm2, nohup).
Limits
EU-only; disk-level snapshots; 100 active VMs soft cap; max 30-day TTL per extension (re-extend as needed).
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.
- 7d ago First seen · 36 lines · 84 tokens per session scan C 19a6e26034f8
background-worker is a skill published in the GitHub repository ariana-dot-dev/cloud-sandbox-vm-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 470 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
latchbio-integration
Build, register, debug, and operate bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, and Latch MCP. Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and…
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…
django-storages-s3
Use when configuring Django to store static and media files on AWS S3 with django-storages. Invoke when working with the STORAGES setting, S3 buckets, presigned URLs, CloudFront, or boto3-backed file storage in settings.py. Configures the Django 4.2+ STORAGES dict, public/private custom backends, presigned GET/POST…
eventbridge
AWS EventBridge serverless event bus for event-driven architectures. Use when creating rules, configuring event patterns, setting up scheduled events, integrating with SaaS, or building cross-account event routing.
sns
AWS SNS notification service for pub/sub messaging. Use when creating topics, managing subscriptions, configuring message filtering, sending notifications, or setting up mobile push.
iam
AWS Identity and Access Management for users, roles, policies, and permissions. Use when creating IAM policies, configuring cross-account access, setting up service roles, troubleshooting permission errors, or managing access control.