Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add vinnie357/claude-skills/plugin install agent-sandboxingWrote 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.
[](https://agentmods.dev/skills/vinnie357/claude-skills/claude-code-on-sandbox)<a href="https://agentmods.dev/skills/vinnie357/claude-skills/claude-code-on-sandbox"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/claude-code-on-sandbox/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.
<a href="https://agentmods.dev/skills/vinnie357/claude-skills/claude-code-on-sandbox"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/claude-code-on-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.01987 |
| Opus 5 | $0.00049 | $0.00993 |
| Sonnet 5 | $0.00020 | $0.00397 |
| Haiku 4.5 | $0.00010 | $0.00199 |
Grade B, and why
claude-code-on-sandbox scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
ca-certificates curl git jq iproute2 iptables sudo gnupg Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
ca-certificates curl git jq iproute2 iptables sudo gnupg How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-code-on-sandbox
Claude Code does not ship an officially maintained standalone OCI image. The supported path is the @anthropic-ai/claude-code npm CLI plus the Anthropic-published Dev Container Feature (ghcr.io/anthropics/devcontainer-features/claude-code:1.0). For sandboxed Kubernetes deployment, the pattern is: build a Dockerfile that installs Claude Code via mise (using the registry short name), wire it into a SandboxTemplate that pins a runtimeClassName, and let agent-sandbox provision per-session pods from that template.
Mise-based Dockerfile
The plugin ships templates/Dockerfile.claude-code and templates/mise.toml.claude-code. Use them verbatim or adapt.
Dockerfile.claude-code:
# syntax=docker/dockerfile:1.7
FROM debian:13-slim AS base
ARG MISE_VERSION=v2026.5.0
ENV MISE_DATA_DIR=/opt/mise \
CLAUDE_CONFIG_DIR=/home/agent/.claude \
PATH=/opt/mise/shims:/home/agent/.local/bin:$PATH
RUN --mount=type=cache,target=/var/cache/apt \
--mount=type=cache,target=/var/lib/apt/lists \
apt-get update && apt-get install -y --no-install-recommends \
ca-certificates curl git jq iproute2 iptables sudo gnupg
RUN useradd -m -u 1000 -s /bin/bash agent
USER agent
WORKDIR /home/agent
RUN curl -fsSL https://mise.run | MISE_VERSION=${MISE_VERSION} sh
COPY --chown=agent:agent mise.toml /home/agent/mise.toml
RUN --mount=type=cache,uid=1000,target=/home/agent/.cache/mise \
/home/agent/.local/bin/mise install
ENTRYPOINT ["/home/agent/.local/bin/mise", "exec", "--", "claude"]
CMD ["--print", "--output-format", "json"]
mise.toml.claude-code:
[tools]
node = "lts"
claude-code = "latest"
Use the mise registry short name claude-code — not npm:@anthropic-ai/claude-code. mise's registry maps the short name to the npm package internally, and the short form keeps the template clean.
BuildKit cache mounts
The Dockerfile uses two BuildKit cache mounts:
/var/cache/apt+/var/lib/apt/lists— apt package cache, so repeated builds don't re-download./home/agent/.cache/mise— mise's per-tool download cache. Theuid=1000is critical; mise runs as theagentuser so the cache must be owned by UID 1000.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 166 lines · 99 tokens per session scan B 02aefb109c44
claude-code-on-sandbox is a skill published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 1,987 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.