agent-kernel: Skill for Claude Code

.agents/skills/ak-dev-new-sandbox-provider/SKILL.md

ak-dev-new-sandbox-provider is a skill for Claude Code, Codex from yaalalabs/agent-kernel. It costs 92 tokens per session (3,385 once invoked), scanned A, original, Apache-2.0.

A development guide for adding a new service that runs code for Agent Kernel agents. It explains how to connect a code-execution backend while accurately describing its isolation and supported abilities.

In plain words
What is it for?
Use it to implement a sandbox and provider, register a new backend, and add its package, configuration, and capability details.
Why use it?
It gives contributors the interfaces and registration steps needed to add a sandbox provider without overstating its safety or capabilities.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is yaalalabs/agent-kernel's own configuration. It tells Claude Code and Codex how to work on agent-kernel itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-kernel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yaalalabs/agent-kernel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/yaalalabs/agent-kernel/develop/.agents/skills/ak-dev-new-sandbox-provider/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/yaalalabs/agent-kernel

Made for: Claude Code, 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.

agentmods badge for ak-dev-new-sandbox-provider

README.md
[![agentmods](https://agentmods.dev/badge/skills/yaalalabs/agent-kernel/ak-dev-new-sandbox-provider/github.svg)](https://agentmods.dev/skills/yaalalabs/agent-kernel/ak-dev-new-sandbox-provider)
Your own site
<a href="https://agentmods.dev/skills/yaalalabs/agent-kernel/ak-dev-new-sandbox-provider"><img src="https://agentmods.dev/badge/skills/yaalalabs/agent-kernel/ak-dev-new-sandbox-provider/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.

agentmods 80×15 button for ak-dev-new-sandbox-provider

Your own site · 80×15
<a href="https://agentmods.dev/skills/yaalalabs/agent-kernel/ak-dev-new-sandbox-provider"><img src="https://agentmods.dev/badge/skills/yaalalabs/agent-kernel/ak-dev-new-sandbox-provider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,385 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. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.03385
Opus 5 $0.00046 $0.01692
Sonnet 5 $0.00018 $0.00677
Haiku 4.5 $0.00009 $0.00338

Measured today against content hash b4c4ce8208c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ak-dev-new-sandbox-provider 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 today.

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.

.agents/skills/ak-dev-new-sandbox-provider/SKILL.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adding a New Sandbox Provider

This guide walks through adding a new sandbox provider to Agent Kernel. Use the shipped local_subprocess (ak-py/src/agentkernel/sandbox/providers/local_subprocess.py) and docker (ak-py/src/agentkernel/sandbox/providers/docker.py) implementations as reference.

Existing Providers

Provider type value Isolation Extra
Local subprocess local_subprocess none (no isolation; dev/test) — (stdlib)
Docker docker container agentkernel[sandbox-docker]
E2B e2b micro_vm agentkernel[e2b]
Daytona daytona container agentkernel[daytona]
EC2 via SSM ec2_ssm none (attach-only to an existing instance) agentkernel[aws]
Kubernetes kubernetes container agentkernel[kubernetes]

Planned in later iterations: bedrock_agentcore.

Reference implementations by pattern: docker.py (sync SDK via to_thread), e2b.py (native async SDK + native idle timeout passthrough), daytona.py (sync SDK + native auto-stop + configurable base image/snapshot/env_vars + resource mapping), ec2_ssm.py (attach-only provider with user-identity mapping: sts:AssumeRole + run_as), kubernetes.py (sync SDK via to_thread with plain dict manifests, exec over the WebSocket stream API (the caller's RBAC needs BOTH create and get on pods/exec), user identity via cached per-subject RBAC-impersonation clients, and the instance-level capability override, below). Providers with a native auto-stop take the profile's idle_timeout as a second constructor argument, passed by their factory branch; kubernetes takes it too, sizing the pod's activeDeadlineSeconds orphan ceiling.

Attach-only backends (environments the framework connects to but never owns) subclass AttachedEnvironmentProvider instead of SandboxProvider: it fixes create (binds to the config's attach_to, never provisions) and destroy (no-op) once, so only attach is implemented. The handle subclasses AttachedEnvironment (not Sandbox directly), which fixes close() as a no-op and keeps the class name honest (e.g. EC2SSMEnvironment). Declare provisions=False, attaches_external=True — the factory validates the profile's environment: managed | attached mode against these flags at startup (attach-only providers are rejected under managed, and attached requires attaches_external plus an attach_to target), and the worker never self-heal-provisions or disposes an attached environment.

Read the full file on GitHub · 272 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. today Changed · +7 lines b4c4ce8208c5
  2. 5d ago Changed · +13 lines · +4 tokens per session 92c43acfa85a
  3. 9d ago First seen · 252 lines · 88 tokens per session scan A 09b08ff314a4

Subscribe to this mod's changes

ak-dev-new-sandbox-provider is a skill published in the GitHub repository yaalalabs/agent-kernel (166 stars, last pushed yesterday), licensed Apache-2.0. It adds 92 tokens to every session and 3,385 once invoked, about $0.0005 per session on Opus 5. 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.