templates

Commands for managing sandbox templates, which are reusable configurations for creating or running isolated environments.

In plain words
What is it for?
Use them to list built-in templates, save a sandbox configuration, add GitHub templates, or remove custom templates.
Why use it?
They avoid repeating the same environment setup for similar projects.

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/templates
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 1,327 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 $0.01327
Opus 5 $0.00000 $0.00664
Sonnet 5 $0.00000 $0.00265
Haiku 4.5 $0.00000 $0.00133

Measured 2d ago against content hash 50125984fcb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

templates 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 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.

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/templates.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentkernel template

Manage sandbox templates. Templates are pre-configured agentkernel.toml configs that can be used with sandbox create --template or run --template.

Subcommands

Command Description
template list List available templates
template save --from <SANDBOX> <NAME> Save a sandbox's config as a template
template add <SPECIFIER> Fetch and cache a GitHub template
template remove <NAME> Remove a custom template

Built-in Templates

agentkernel ships with 26 built-in templates:

Language Runtimes

Template Image Use Case
python python:3.12-alpine Python development
python-ml python:3.12 Python ML/data science
node node:22-alpine Node.js development
node-fullstack node:22 Full-stack Node.js
typescript node:22-alpine TypeScript projects
rust rust:1.85-alpine Rust development
rust-ci rust:1.85-alpine Rust CI (restrictive)
go golang:1.23-alpine Go development
ruby ruby:3.3-alpine Ruby development
java eclipse-temurin:21-alpine Java development
dotnet mcr.microsoft.com/dotnet/sdk:8.0 .NET development
bash alpine:3.24 Shell scripting
c gcc:14-bookworm C/C++ development
secure alpine:3.24 Restrictive (no network)

AI Agent Sandboxes

Template Image Use Case
amp-sandbox node:24-bookworm-slim Amp agent
claude-sandbox node:24-alpine3.24 Claude Code agent
codex-sandbox node:24-alpine3.24 Codex agent
copilot-sandbox node:24-bookworm-slim GitHub Copilot CLI agent
gemini-sandbox node:24-alpine3.24 Gemini CLI agent
opencode-sandbox node:24-alpine3.24 OpenCode agent
pi-sandbox node:24-alpine3.24 Pi coding agent
symphony-sandbox elixir:1.19-otp-28-slim Symphony orchestration agent

Read the full file on GitHub · 156 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 · 156 lines · 0 tokens per session scan A 50125984fcb6

Subscribe to this mod's changes

templates 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 1,327 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.