bootstrap

bootstrap is a command for coding agents from vinnie357/claude-skills. It costs 44 tokens per session (1,372 once invoked), scanned A, original, MIT.

A command that prepares a Kubernetes cluster to run Claude Code workloads in isolated microVM-based sandboxes. Kubernetes is a system for managing containers and related workloads across a cluster.

In plain words
What is it for?
Use it to set up a local kind cluster, a GKE cluster, or a macOS Apple Silicon environment through kina, depending on the available host.
Why use it?
It brings together substrate selection, prerequisite checks, the agent-sandbox controller, and an initial SandboxTemplate so the cluster can host sessions.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the agent-sandboxing plugin — 7 skills, 6 commands shipped together

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/vinnie357/claude-skills/bootstrap
Clone the repo
git clone --depth 1 https://github.com/vinnie357/claude-skills

Or install agent-sandboxing, the plugin that ships this one along with the rest of its 7 skills, 6 commands.

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 bootstrap

README.md
[![agentmods](https://agentmods.dev/badge/commands/vinnie357/claude-skills/bootstrap.svg)](https://agentmods.dev/commands/vinnie357/claude-skills/bootstrap)
Your own site
<a href="https://agentmods.dev/commands/vinnie357/claude-skills/bootstrap"><img src="https://agentmods.dev/badge/commands/vinnie357/claude-skills/bootstrap.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,372 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 $0.00044 $0.01372
Opus 5 $0.00022 $0.00686
Sonnet 5 $0.00009 $0.00274
Haiku 4.5 $0.00004 $0.00137

Measured 2d ago against content hash 0943baba828d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bootstrap 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.

plugins/tools/agent-sandboxing/commands/bootstrap.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bring up a Kubernetes cluster ready to host Claude Code workloads in microVM-isolated pods.

Skills to load (explicit, no globs)

  • /agent-sandboxing:k8s-agent-sandbox
  • /agent-sandboxing:kata-on-kind
  • /agent-sandboxing:kata-on-gke
  • /agent-sandboxing:kina-microvm
  • /agent-sandboxing:claude-code-on-sandbox
  • /core:nushell
  • /core:mise
  • /core:anti-fabrication

Steps

1. Pick the substrate

If --substrate=<value> is not in arguments, ask the user which path:

  • kind-kata — Linux host with /dev/kvm; local microVM dev loop via kind + kata-deploy. See /agent-sandboxing:kata-on-kind.
  • gke-kata — GKE Standard with Ubuntu N2 nodes + nested virt + upstream examples/kata-gke-sandbox/setup.sh. See /agent-sandboxing:kata-on-gke.
  • kina — macOS Apple Silicon via kina (Kubernetes-in-Apple-Containers). See /agent-sandboxing:kina-microvm.

Detect the host's OS via uname -s. Steer the user away from kind-kata on macOS (won't work without nested KVM) and toward kina instead.

2. Verify prerequisites

For the chosen substrate, run the skill's prerequisites checklist verbatim. Do not skip this. If a prereq fails, stop and report; the user fixes it before continuing.

  • kind-katareferences/verify-kvm.md checks (ls /dev/kvm, KVM group, nested-virt CPU flags).
  • gke-kata → confirm gcloud auth, project, nested-virt org policy, N2 quota.
  • kinacontainer --version and kina --help both succeed; verify Apple Container version drift caveat documented in the skill.

3. Create the cluster

Follow the relevant skill's "Step 1" commands verbatim. Examples:

  • kind-kata: render and apply the kind-kata.yaml cluster config with /dev/kvm extraMounts, then kind create cluster ....
  • gke-kata: gcloud container clusters create + node-pools create --enable-nested-virtualization.
  • kina: kina create agent-sandbox && kina export ... && export KUBECONFIG=....

4. Install the agent-sandbox controller

VERSION=v0.4.6
kubectl apply -f https://github.com/kubernetes-sigs/agent-sandbox/releases/download/${VERSION}/manifest.yaml
kubectl apply -f https://github.com/kubernetes-sigs/agent-sandbox/releases/download/${VERSION}/extensions.yaml
kubectl wait --for=condition=Available deploy/agent-sandbox-controller -n agent-sandbox-system --timeout=5m

Read the full file on GitHub · 118 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 · 118 lines · 44 tokens per session scan A 0943baba828d

Subscribe to this mod's changes

bootstrap is a command published in the GitHub repository vinnie357/claude-skills (24 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,372 once invoked, about $0.0002 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 2026-09-03.