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.
npx skills add mpfaffenberger/code_puppy --skill sandbox-basicsgit clone --depth 1 https://github.com/mpfaffenberger/code_puppyWrote 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/mpfaffenberger/code_puppy/sandbox-basics)<a href="https://agentmods.dev/skills/mpfaffenberger/code_puppy/sandbox-basics"><img src="https://agentmods.dev/badge/skills/mpfaffenberger/code_puppy/sandbox-basics/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/mpfaffenberger/code_puppy/sandbox-basics"><img src="https://agentmods.dev/badge/skills/mpfaffenberger/code_puppy/sandbox-basics.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 | $0.00045 | $0.00328 |
| Opus 5.5 | $0.00018 | $0.00131 |
| Sonnet 5.5 | $0.00009 | $0.00066 |
| Haiku 4.5 | $0.00005 | $0.00033 |
Grade A, and why
sandbox-basics 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 4d 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.
What it actually says
Sandbox basics
- You are the
agentuser in a Docker sandbox. Your Code Puppy config is in~/.code_puppy/; the project workspace is a separate mount. - Egress is allow-list based. A blocked host fails fast: report the
exact hostname and why you need it so the user can extend the policy
(
sbx policy), instead of working around it. - Provider keys (
META_API_KEY,ANTHROPIC_API_KEY,OPENAI_API_KEY,GEMINI_API_KEY,OPENROUTER_API_KEY) contain placeholders. The host proxy swaps in the real key only for that provider's API domain. Code that sends a key anywhere else will fail authentication by design.meta-*models come from themeta_oauthplugin;/meta-statusshows which credential source is active. - Install Python tools with
uvx <tool>(ephemeral) oruv tool install <tool>(persistent). PyPI egress is allowed. - Sandbox config is seeded at creation from the
code-puppy-configkit. Edits you make under~/.code_puppy/last for this sandbox's lifetime; durable changes belong in the kit on the host.
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.
- 4d ago First seen · 24 lines · 45 tokens per session scan A b781bef2ff69
sandbox-basics is a skill published in the GitHub repository mpfaffenberger/code_puppy (870 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 328 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-18.
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…
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.
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.
polar-local-environment
This skill should be used when setting up or managing Polar local development environment with Docker.