run

A command for running another command inside a temporary sandbox, an isolated environment for executing code.

In plain words
What is it for?
Use it to run commands with a selected image, security profile, backend, template, or development-container configuration.
Why use it?
It keeps test or build changes contained and removes the sandbox automatically afterward unless you choose to keep it.

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/run
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 1,401 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.01401
Opus 5 $0.00000 $0.00700
Sonnet 5 $0.00000 $0.00280
Haiku 4.5 $0.00000 $0.00140

Measured 2d ago against content hash 146ba300dbc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run 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 2d 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.

agentkernel run --profile permissive curl https://api.example.com
docs/commands/run.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentkernel run

Run a command in a temporary sandbox. The sandbox is created, the command executed, and then cleaned up automatically.

Usage

agentkernel run [OPTIONS] <COMMAND>...

Options

Option Description
-i, --image <IMAGE> Docker image to use (auto-detected if not specified)
--build Build and use the current project's Dockerfile. Conflicts with --image and --fast.
-p, --profile <PROFILE> Security profile: permissive, moderate, restrictive
-k, --keep Keep the sandbox after execution (for debugging)
-F, --fast Use container pool for faster startup (default: true)
-c, --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
-B, --backend <BACKEND> Backend: docker, podman, firecracker, apple, etc.
--template <NAME> Use a template (built-in, local, github:owner/repo/path, or file)
--ttl <DURATION> TTL for kept sandboxes (e.g. 1h, 30m, 3d; default: 1h)
--branch Use git project+branch as sandbox name (reuses existing sandbox)
--no-network Disable network access
-P, --publish <PORT> Port mapping (e.g. 8080:80, 3000). Repeatable. Requires --fast=false.
--ssh Enable SSH access to the sandbox
-S, --secret <BINDING> Bind a secret to a host via proxy (KEY:host, KEY=value:host, KEY:host:header). Repeatable.
--secret-file <KEY> Inject a vault secret as a file inside the sandbox. Repeatable.
--placeholder-secrets Use placeholder tokens instead of real values for --secret-file. Real values substituted by proxy.
--receipt <FILE> Write a signed execution receipt JSON for this run

Examples

Basic usage

# Auto-detects python image
agentkernel run python3 -c "print('hello')"

# Auto-detects node image
agentkernel run node -e "console.log('hello')"

# Run a script
agentkernel run python3 script.py

Read the full file on GitHub · 166 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. 2d ago First seen · 166 lines · 0 tokens per session scan A 146ba300dbc0

Subscribe to this mod's changes

run is a command published in the GitHub repository thrashr888/agentkernel (58 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,401 tokens. 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.