Borrowing it
Nothing to install: this file belongs to cardstack/boxel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cardstack/boxel/main/.claude/skills/claude-web-no-docker-stack/SKILL.mdgit clone --depth 1 https://github.com/cardstack/boxelWrote 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/cardstack/boxel/claude-web-no-docker-stack)<a href="https://agentmods.dev/skills/cardstack/boxel/claude-web-no-docker-stack"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/claude-web-no-docker-stack/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/cardstack/boxel/claude-web-no-docker-stack"><img src="https://agentmods.dev/badge/skills/cardstack/boxel/claude-web-no-docker-stack.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 | $0.00174 | $0.02848 |
| Opus 5.5 | $0.00070 | $0.01139 |
| Sonnet 5.5 | $0.00035 | $0.00570 |
| Haiku 4.5 | $0.00017 | $0.00285 |
Grade A, and why
claude-web-no-docker-stack 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 5d 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.
description: Bring up the boxel stack and run the host / realm-server browser test suites inside a Claude Code web session whose egress policy blocks every container-registry blob CDN, so `docker pull` cannot fetch postg How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running the stack when no container image can be pulled
.devcontainer/claude-web-start.sh assumes the session snapshot already holds
the images and the toolchain. In a session provisioned without them — a fresh
container, or one whose setup script failed — three separate egress denials
land at once, and each one looks like a different problem:
| Symptom | Blocked host |
|---|---|
curl https://mise.run → CONNECT tunnel failed, response 403 |
mise.run |
docker pull postgres:16.3 → failed to copy: … Forbidden |
production.cloudfront.docker.com |
docker pull ghcr.io/cardstack/boxel/postgres:16.3 |
pkg-containers.githubusercontent.com |
docker pull public.ecr.aws/docker/library/postgres:16.3 |
d2glxqk2uabbnd.cloudfront.net |
Fetching the boxel-index-cache artifact from a CI run |
productionresultssa*.blob.core.windows.net |
Registry manifests resolve — the pull gets as far as the layers and then 403s — so a failure reads like a corrupt image rather than a policy denial. Confirm before working around anything:
curl -sS "$HTTPS_PROXY/__agentproxy/status" | head -40 # recentRelayFailures names the host
Per the proxy's own README, a 403/407 is an organization policy denial: report it, don't retry it, and don't look for another mirror — every mirror's blobs live behind one of the CDNs above.
What is reachable, and is what this skill builds on: nodejs.org,
registry.npmjs.org (in the proxy's no-proxy list), the Ubuntu archive over
apt, and github.com over git.
When to use
- A web session is asked to run host tests (or realm-server tests) and Docker is unusable.
- You need the stack up — a realm server, a prerender, the host app — to reproduce something, and the usual start script won't boot.
- Deciding whether a test failure you are seeing is real or an artifact of this environment (see What this environment cannot run).
What ships with it
3 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.
- 5d ago First seen · 198 lines · 174 tokens per session scan A f2c3c1445496
claude-web-no-docker-stack is a skill published in the GitHub repository cardstack/boxel (27 stars, last pushed today), licensed MIT. It adds 174 tokens to every session and 2,848 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-21.
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…
bdd-container-update
Update the BDD test container image when its dependencies or runtime change. Determines version bump (major vs minor vs patch), rebuilds the Docker image, pushes to GitLab registry, and updates the image tag in starttest.sh. Test source (tests/, features/, scripts/, data/, conftest.py) is bind-mounted from the host…
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…
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.
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.
k8s-networking
Kubernetes networking management for services, ingresses, endpoints, and network policies. Use when configuring connectivity, load balancing, or network isolation.