create

A command for creating a persistent sandbox, which is an isolated environment for running an agent and project commands. The sandbox remains available until you explicitly remove it.

In plain words
What is it for?
Use it to create sandboxes from Docker or development-container settings, mount a project, select an agent, or create an isolated Git worktree.
Why use it?
It gives coding work a repeatable environment with a chosen project directory, image, template, agent, backend, or Git worktree.

Command

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.

agentmods
npx agentmods add commands/thrashr888/agentkernel/create
Clone the repo
git clone --depth 1 https://github.com/thrashr888/agentkernel
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,770 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01770
Opus 5 $0.00000 $0.00885
Sonnet 5 $0.00000 $0.00354
Haiku 4.5 $0.00000 $0.00177

Measured yesterday against content hash 919682724ded, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create 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 yesterday.

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.

docs/commands/create.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentkernel sandbox create

Create a new persistent sandbox. The sandbox remains available until explicitly removed.

Usage

agentkernel sandbox create [OPTIONS] [NAME]

Arguments

Argument Description
[NAME] Name for the sandbox (alphanumeric, hyphens, underscores). Optional when --branch is used.

Options

Option Description
--config <FILE> Path to agentkernel.toml config file
--devcontainer <FILE> Path to a JSONC Development Container file
--auto-devcontainer Detect .devcontainer/devcontainer.json in the project
-i, --image <IMAGE> Docker image override (takes precedence over the devcontainer)
--template <NAME> Use a built-in or custom template
--agent <AGENT> Agent type: claude, codex, gemini, opencode
--dir <PATH> Project directory to mount
--git-worktree Create an isolated host-side Git worktree and mount it at /workspace
-B, --backend <BACKEND> Backend: docker, podman, firecracker, apple
--branch Auto-name from git project and branch
--ttl <DURATION> Auto-expire after duration (e.g. 1h, 30m, 3d)
-p, --publish <PORT> Port mapping (e.g. 8080:80, 3000, 5353:53/udp). Repeatable.
--network-name <NAME> Use an AgentKernel-managed Docker/Podman bridge.
--network-subnet <CIDR> Managed bridge subnet (default 172.30.0.0/24).
--network-gateway <IP> Managed bridge gateway IPv4 address.
--network-dns <IP> Managed bridge DNS IPv4 address. Repeatable.
--network-ip <IP> Fixed sandbox IPv4 address on the managed bridge.
--ssh Enable SSH access to the sandbox
-S, --secret <BINDING> Bind a secret to a host via proxy. Repeatable. See Secrets.
--secret-file <KEY> Inject a vault secret as a file. Repeatable. See Secrets.
--placeholder-secrets Use placeholder tokens for --secret-file (real values stay on host).

Read the full file on GitHub · 222 lines

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. yesterday First seen · 222 lines · 0 tokens per session scan A 919682724ded

Subscribe to this mod's changes

create is a command published in the GitHub repository thrashr888/agentkernel (58 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,770 tokens. 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 2026-08-30.