hosted-agents

hosted-agents is a skill for Claude Code, Codex from guanyang/open-agent-hub. It costs 46 tokens per session (3,401 once invoked), scanned A, a copy of hosted-agents, MIT.

Guidance for building agents that run on remote computers or in the background instead of only during a local session.

In plain words
What is it for?
Use it to design hosted coding environments, background agents, multiplayer sessions, remote sandboxes, and systems where agents start other agents.
Why use it?
It helps address isolation, saved sessions, shared access, and scaling when agents need to run remotely.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions OpenCode.

Part of the open-agent-hub plugin — 102 skills, 3 commands, 5 agents, 6 MCP servers shipped together

Good fit Use it to design hosted coding environments, background agents, multiplayer sessions, remote sandboxes, and systems where agents start other agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/guanyang/open-agent-hub/hosted-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 guanyang/open-agent-hub --skill hosted-agents
Clone the repo
git clone --depth 1 https://github.com/guanyang/open-agent-hub

Made for: Claude Code, Codex.

Or install open-agent-hub, the plugin that ships this one along with the rest of its 102 skills, 3 commands, 5 agents, 6 MCP servers.

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 hosted-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/guanyang/open-agent-hub/hosted-agents.svg)](https://agentmods.dev/skills/guanyang/open-agent-hub/hosted-agents)
Your own site
<a href="https://agentmods.dev/skills/guanyang/open-agent-hub/hosted-agents"><img src="https://agentmods.dev/badge/skills/guanyang/open-agent-hub/hosted-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,401 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00046 $0.03401
Opus 5 $0.00023 $0.01700
Sonnet 5 $0.00009 $0.00680
Haiku 4.5 $0.00005 $0.00340

Measured 4d ago against content hash 4786dad600b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hosted-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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/sandbox_manager.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to hosted-agents — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/hosted-agents/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hosted Agent Infrastructure

Hosted agents run in remote sandboxed environments rather than on local machines. When designed well, they provide unlimited concurrency, consistent execution environments, and multiplayer collaboration. The critical insight is that session speed should be limited only by model provider time-to-first-token, with all infrastructure setup completed before the user starts their session.

When to Activate

Activate this skill when:

  • Building background coding agents that run independently of user devices
  • Designing sandboxed execution environments for agent workloads
  • Implementing multiplayer agent sessions with shared state
  • Creating multi-client agent interfaces (Slack, Web, Chrome extensions)
  • Scaling agent infrastructure beyond local machine constraints
  • Building systems where agents spawn sub-agents for parallel work

Do not activate this skill for adjacent work owned by other skills:

  • Designing the autonomous research loop, novelty gates, rollback policy, or merge boundaries: harness-engineering.
  • Choosing supervisor, swarm, or handoff topology without hosted infrastructure concerns: multi-agent-patterns.
  • Designing the tools used by a hosted agent, such as spawn/status tools or PR tools: tool-design.
  • Managing file-backed state inside a session rather than the hosted runtime itself: filesystem-context.

Core Concepts

Move agent execution to remote sandboxed environments to eliminate the fundamental limits of local execution: resource contention, environment inconsistency, and single-user constraints. Remote sandboxes unlock unlimited concurrency, reproducible environments, and collaborative workflows because each session gets its own isolated compute with a known-good environment image.

Design the architecture in three layers because each layer scales independently. Build sandbox infrastructure for isolated execution, an API layer for state management and client coordination, and client interfaces for user interaction across platforms. Keep these layers cleanly separated so sandbox changes do not ripple into clients.

Read the full file on GitHub · 302 lines

Files

What ships with it

2 files 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.

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. 4d ago First seen · 302 lines · 46 tokens per session scan A 4786dad600b0

Subscribe to this mod's changes

hosted-agents is a skill published in the GitHub repository guanyang/open-agent-hub (961 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 3,401 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to hosted-agents, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

pipedream-workflows

Use when pipedream serverless workflows — triggers, code steps, pre-built actions, data stores, HTTP. Use when working with pipedream workflows.

oyi77/1ai-skills · 38 tokens

neo-azure-pipelines

Use this skill when the user asks to create, review, debug, or modernize Azure Pipelines YAML for CI/CD, especially .NET builds, Azure App Service deploys, or IIS/on-premises deploys. Prefer bundled templates and verify task syntax against Microsoft docs when version-specific accuracy matters.

Benknightdark/neo-skills · 66 tokens

vercel-hygiene

Audit and harden the 4 pivoshenko brand sites on Vercel (pivoshenko.dev, pivoshenko.startpage, pivoshenko.wallpapers, pivoshenko.ai), team pivoshenko. Read-only sweep -> per-site report (ok/attention/action) -> confirmed fixes. Emphasizes security headers and analytics coverage. Use when the user says "audit vercel"…

pivoshenko/pivoshenko.ai · 162 tokens

cloudflare-hygiene

Audit + harden + optimize live Cloudflare zones/domains — read-only sweep of each zone (SSL/TLS mode, HSTS, min TLS, TLS 1.3, Always-Use-HTTPS, Brotli, HTTP/3, 0-RTT, Early Hints, caching, security level, Bot Fight Mode, WAF, DNS proxy/TTL + SPF/DKIM/DMARC hygiene, DNSSEC) -> ok/attention/action report grouped by…

pivoshenko/pivoshenko.ai · 220 tokens

hetzner-create

Provision a new hardened Hetzner VPS end to end. Sets up the local toolchain if missing (hcloud CLI, API context, SSH keypair, sshconfig Include), then creates the server with the firewall attached and cloud-init hardening applied at first boot, verifies SSH comes up on the non-standard port, and registers it in the…

IsaiaScope/ai · 122 tokens

hetzner-update

Align the version of a self-hosted open-source app between your Mac and a Hetzner VPS, upgrading whichever side is behind. Reads the software registry at /.config/hetzner/hetzner.json, compares both halves, classifies every release in between as safe or breaking, and stops for approval before crossing a breaking…

IsaiaScope/ai · 151 tokens