Borrowing it
Nothing to install: this file belongs to orka-agents/orka. 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/orka-agents/orka/main/.agents/skills/agent-sandbox-deploy/SKILL.mdgit clone --depth 1 https://github.com/orka-agents/orkaWrote 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/orka-agents/orka/agent-sandbox-deploy)<a href="https://agentmods.dev/skills/orka-agents/orka/agent-sandbox-deploy"><img src="https://agentmods.dev/badge/skills/orka-agents/orka/agent-sandbox-deploy/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/orka-agents/orka/agent-sandbox-deploy"><img src="https://agentmods.dev/badge/skills/orka-agents/orka/agent-sandbox-deploy.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 | $0.00091 | $0.02720 |
| Opus 5.5 | $0.00036 | $0.01088 |
| Sonnet 5.5 | $0.00018 | $0.00544 |
| Haiku 4.5 | $0.00009 | $0.00272 |
Grade C, and why
agent-sandbox-deploy scanned grade C 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 10d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
touches `~/.kube/config`. Resolve the binary first: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
wget -qO- http://127.0.0.1:1337/readyz How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Sandbox Deploy
Stand up the experimental kubernetes-sigs/agent-sandbox
backend and the external orka-workspace-sandbox provider against an Orka
controller on a local kind cluster. Orka core has no Agent Sandbox flag or
in-tree provider. The provider, its CRDs, and its proof harnesses live in the
orka-workspace repository at
the revision pinned in this repository's go.mod.
This skill is for local/kind evaluation and validation, not production.
Orka does not install or manage upstream agent-sandbox CRDs, controllers,
templates, or warm pools. See website/docs/concepts/agent-sandbox.md for the
design and website/docs/reference/configuration.md#workspace-providers for the
controller flags.
What this skill orchestrates (do not retype)
- Backend:
hack/demos/cluster/install-agent-sandbox.shinstalls the pinned agent-sandbox release (ORKA_AGENT_SANDBOX_VERSION, defaultv1.0.3) and theorka-live-templateSandboxTemplate. WithAGENTIC=1(default) it also builds the archived demo runtime and router images and prepares vekil, the model Secret, the Git Secret, and the API client ServiceAccount. It does not change Orka controller flags and does not install the provider or a class. - Provider: the orka-workspace shared bundle (
config/) and Sandbox bundle (providers/sandbox/config), installed as described in itsdocs/external-providers.mdandproviders/sandbox/README.md. - Proofs: orka-workspace
scripts/external-sandbox-e2e.sh(installed backend persistence) andscripts/external-workspace-e2e.sh core(real Core RuntimeSession through an external provider). Drive these in place.
Existing v0.5 installations must complete the upstream storage migration before applying v1. The installer does not run or preflight that migration. After a v1 install it removes only the four obsolete namespaced conversion-webhook resources documented by upstream.
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.
- 10d ago Changed · -162 lines · +6 tokens per session 67cbbd8e5b26
- 1mo ago Changed · +6 lines 678b87ba6a1e
- 1mo ago Changed 16251337f9b6
- 1mo ago Changed · +7 lines a033a211d747
- 1mo ago Changed e45b129dd192
- 1mo ago First seen · 375 lines · 85 tokens per session scan C f926883016c8
agent-sandbox-deploy is a skill published in the GitHub repository orka-agents/orka (36 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 2,720 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cdf-orchestration-setup
Use when the user asks to deploy, install, reinstall, redeploy, upgrade, or connect to the CDF Orchestration Airflow controller. Owns the end-to-end deploy sequence and runs the cdf-orchestration-preflight audit first. Covers make setup, controller image builds, Helm installation, controller connection…
aiq-deploy
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
dynamo-recipe-runner
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".
remote-crew-microvm
Drive the AWS Lambda MicroVM remote-crew lane: check whether it is configured, hand the operator the cloud.json block when it is not, launch a crew, reach it, and tear it down. Use for microvm, lambda microvm, remote crew, cheap cloud crew.
wrangler
Run or troubleshoot Wrangler CLI commands in projects that have a wrangler.jsonc, wrangler.json, or wrangler.toml file, including local development, Previews, deployment, and resource management. For new projects and projects without a Wrangler configuration file, use the cf CLI instead.