parallel-agents

parallel-agents is a skill for Claude Code, Codex from ariana-dot-dev/cloud-sandbox-vm-skills. It costs 91 tokens per session (551 once invoked), scanned C, original, MIT.

A setup for running many coding agents in separate cloud virtual machines, created by copying one already-configured machine.

In plain words
What is it for?
Use it to split work across multiple isolated agents, run configuration variations, or divide a larger workload among persistent machines.
Why use it?
It avoids repeating environment setup for every worker while keeping each agent's files and machine separate.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to split work across multiple isolated agents, run configuration variations, or divide a larger workload among persistent machines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ariana-dot-dev/cloud-sandbox-vm-skills/parallel-agents
Install

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.

Any agent
npx skills add ariana-dot-dev/cloud-sandbox-vm-skills --skill parallel-agents
Clone the repo
git clone --depth 1 https://github.com/ariana-dot-dev/cloud-sandbox-vm-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for parallel-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/ariana-dot-dev/cloud-sandbox-vm-skills/parallel-agents.svg)](https://agentmods.dev/skills/ariana-dot-dev/cloud-sandbox-vm-skills/parallel-agents)
Your own site
<a href="https://agentmods.dev/skills/ariana-dot-dev/cloud-sandbox-vm-skills/parallel-agents"><img src="https://agentmods.dev/badge/skills/ariana-dot-dev/cloud-sandbox-vm-skills/parallel-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 551 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.00551
Opus 5 $0.00046 $0.00275
Sonnet 5 $0.00018 $0.00110
Haiku 4.5 $0.00009 $0.00055

Measured 7d ago against content hash 06236033b22f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

parallel-agents 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`.
skills/parallel-agents/SKILL.md · 37 lines

What it actually says

Parallel agents / agent factory (Box)

Use this when work should be fanned out across many isolated environments: N agents on N tasks, a config sweep, or sharding a workload — and each worker needs a real machine, not a coroutine. Box move: configure one box (clone, install, secrets), then fork it; each fork is an independent VM from that snapshot, so you skip re-provisioning every machine.

Why Box

  • Fork = a configured template — one setup, N identical machines (disk-level, no re-clone per VM).
  • True isolation per agent — separate filesystem, dedicated IPv4, SSH; agents can even talk over the network.
  • Fleet economics — 50 VMs × 240 h/mo ≈ $432 (Box) vs ~$4,124 (E2B) / ~$7,160 (Modal).

Honest scoping

Box forks at the disk level, not memory — a fork does not keep the parent's running processes; re-run your start command after fork. For running-process fork or routinely 1000+ concurrent VMs with <500 ms boot, E2B/Modal are built for that. Box's sweet spot: tens of persistent, cheap, fully-isolated machines. EU-only; 100 active VMs soft cap (raising).

Prereqs

curl -fsSL https://box.ascii.dev/install | sh, then box login "$BOX_API_KEY" --json.

Recipe

base="$(box new --json | jq -r 'select(.event == "ready") | .id')"
box ssh "$base" -- bash -s < ./setup.sh                 # configure once
for i in $(seq 1 10); do
  fork="$(box fork "$base" --json | jq -r 'select(.event == "ready") | .id')"
  box ssh "$fork" -- "cd /project && ./run-task.sh $i" &
done
wait

Keep setup.sh and the start command idempotent so every fork bootstraps reliably.

Changes

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.

  1. 7d ago First seen · 37 lines · 91 tokens per session scan C 06236033b22f

Subscribe to this mod's changes

parallel-agents 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 91 tokens to every session and 551 once invoked, about $0.0005 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.

Related

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…

K-Dense-AI/scientific-agent-skills · 76 tokens

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…

Jeffallan/claude-skills · 71 tokens

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…

Jeffallan/claude-skills · 138 tokens

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.

itsmostafa/aws-agent-skills · 41 tokens

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.

itsmostafa/aws-agent-skills · 32 tokens

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.

itsmostafa/aws-agent-skills · 42 tokens