What is dedalus-machines?

Documentation for persistent Linux environments called Agent Machines, including their providers, agent runtimes, tools, storage locations, and lifecycle operations.

Use it when working with Dedalus, E2B, or Sprites machines; selecting Hermes, OpenClaw, Claude Code, or Codex; or checking runtime, scaling, and configuration details.

It explains where the environment lives and how its parts fit together, reducing confusion when starting, inspecting, sleeping, waking, or removing a machine.

dedalus-machines — Skill for Codex by Kevin-Liu-01

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 Kevin-Liu-01/Agent-Machines --skill dedalus-machines

Clone the repo

git clone --depth 1 https://github.com/Kevin-Liu-01/Agent-Machines

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/dedalus-machines/github.svg)](https://agentmods.dev/skills/kevin-liu-01/agent-machines/dedalus-machines)

Your own site

<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/dedalus-machines"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/dedalus-machines/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/dedalus-machines"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/dedalus-machines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 712 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00069	$0.00712
Opus 5	$0.00034	$0.00356
Sonnet 5	$0.00014	$0.00142
Haiku 4.5	$0.00007	$0.00071

Measured 11d ago against content hash 90e5b67e0497, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dedalus-machines scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **CLIs:** agent-browser, playwright, httpx, curl, jq, sqlite3

knowledge/skills/dedalus-machines/SKILL.md · 78 lines

What it actually says

Agent Machines Runtime

Persistent Linux rig provisioned by the Agent Machines control plane. Runtime root: ~/.agent-machines (not ~/.hermes).

Providers

Provider	Home path	Notes
dedalus	`/home/machine`	Firecracker microVM, sleep/wake
e2b	`/home/user`	Sandbox, public URL per port
sprites	`/home/sprite`	Sprites.dev compute

Agent runtimes (pick one per machine)

Kind	Gateway	State	Role
hermes	:8642	`~/.agent-machines`	Default: memory, cron, MCP, skills
openclaw	:18789	`~/.openclaw`	Computer-use runtime
claude-code	n/a	`~/.claude`	Anthropic API
codex	n/a	`~/.codex`	OpenAI API

When Hermes is the runtime, HERMES_HOME=~/.agent-machines.

Layout

/home/machine/
├── .agent-machines/       # CANONICAL runtime root
│   ├── skills/            # 161 SKILL.md files
│   ├── mcps/catalog.json
│   ├── config.yaml        # mcp_servers, model
│   ├── scripts/reload-from-git.sh
│   └── logs/
├── .openclaw/             # when OpenClaw runtime selected
├── agent-machines/        # git checkout for Reload
├── cursor-bridge/         # optional MCP build
└── .cache/ms-playwright/

Legacy ~/.hermes is symlinked to ~/.agent-machines after migration.

Tools

22 built-ins (terminal, files, browser, search, vision, cron, memory, ...)
MCP core: playwright, cursor-bridge
MCP bundled: see ~/.agent-machines/mcps/catalog.json
CLIs: agent-browser, playwright, httpx, curl, jq, sqlite3

Reload

~/.agent-machines/scripts/reload-from-git.sh

Inspect this VM

/.agent/docs/agent-context.md
tail ~/.agent-machines/logs/gateway.log
ss -tlnp

Dedalus SDK

import Dedalus from "dedalus";
const client = new Dedalus({ xAPIKey: process.env.DEDALUS_API_KEY });

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.

11d ago First seen · 78 lines · 69 tokens per session scan A 90e5b67e0497

Subscribe to this mod's changes

dedalus-machines is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (29 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 712 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Claude Code Cloud DevOps and cloud ai-agent cron hermes-agent mcp microvm model-context-protocol

api-workers

Cloudflare Workers deployment using createWorkerHandler from @cyanheads/mcp-ts-core/worker. Covers the full handler signature, binding types, CloudflareBindings extensibility, runtime compatibility guards, and wrangler.toml requirements.

cyanheads/obsidian-mcp-server · 51 tokens

coolify

Operate a Coolify self-hosted PaaS through the @masonator/coolify-mcp server. Use this skill whenever the user asks Claude to inspect, deploy, restart, debug, or manage anything on Coolify — including applications, databases, services, servers, projects, environments, deployments, environment variables, private keys…

StuMason/coolify-mcp · 156 tokens

cloud-iam-deep

GCP/AWS/Azure cloud exploitation -- Cloud Functions, Firestore, Cloud Run, S3, MinIO, Blob Storage, SA keys.

uphiago/recon-skills · 35 tokens

modal

Use when running Python or GPU workloads serverlessly on Modal — modal.App, inline container Images, gpu= on @app.function, Volumes for weight caching, Cron schedules, ASGI endpoints, modal run vs serve vs deploy. NOT managed prediction APIs with no container of your own (that is replicate); NOT SSH-able GPU boxes…

ericrisco/rsc-harness · 78 tokens

render

Use when deploying or fixing an app on Render — web services, background workers, cron jobs, private services, managed Postgres and Key-Value, and especially the render.yaml Blueprint. Covers deploys that fail with no open ports detected, 502s on first deploy, free-tier cold starts, and a free Postgres about to expire…

ericrisco/rsc-harness · 105 tokens

discovery-patterns

Configure ServiceNow Discovery — schedules, IP ranges, credential affinities, MID Server assignment, custom probes/sensors, identification rules, and run-status monitoring on discovery tables.

serac-labs/serac · 40 tokens

dedalus-machines