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.svg" alt="Measured on agentmods" 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 | $0.00085 | $0.04466 |
| Opus 5 | $0.00043 | $0.02233 |
| Sonnet 5 | $0.00017 | $0.00893 |
| Haiku 4.5 | $0.00009 | $0.00447 |
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 3d 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`. Every command below runs against the kindctl 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 — 382 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
workspace provider against an Orka controller on a local kind cluster. Validate
install/config, the direct workspace-adapter lifecycle, and workspace-backed
ACP Tasks. Manual deployments keep --acp-workspace-dispatch-enabled off unless
the operator explicitly enables it; the bundled E2E enables the gate and runs a
real Codex prompt against a local Responses-compatible fixture.
This skill is for local/kind evaluation and validation, not production.
Orka does not install or manage upstream agent-sandbox CRDs, the router,
templates, or warm pools in production — install and operate those separately.
See website/docs/concepts/agent-sandbox.md for the full design and the
production controller flags.
What this skill orchestrates (do not retype)
The repeatable standup already lives in
hack/demos/cluster/install-agent-sandbox.sh. Drive that script in place; do
not copy it into the skill. Orka requires agent-sandbox v1.0.0. The script
defaults ORKA_AGENT_SANDBOX_VERSION to that version, matching go.mod, and
owns the gotchas (kind registry addressing, the SDK sandbox-router build from
the Go module cache, the controller flag patch). Use the version override only
for a coordinated future dependency upgrade with matching adapter validation.
Existing v0.5 installations must complete the upstream storage migration before applying v1.0.0. The script does not run or preflight that migration. After a successful v1 install, it removes only the four obsolete namespaced conversion-webhook resources documented by upstream; it leaves the active cluster-scoped controller RBAC intact.
What the script does:
- Base layer (always): installs agent-sandbox CRDs + controllers, applies
the
orka-live-templateSandboxTemplate, and patches the existing Orka controller Deployment with--agent-sandbox-enabled=true,--agent-sandbox-router-url,--agent-sandbox-default-template,--agent-sandbox-cleanup-policy, and--execution-workspace-default-provider=agent-sandbox. - Agentic layer (
AGENTIC=1, default): builds + pushes thesandbox-runtimeimage (realcodex+git+gh). When the pinnedsandbox-routersource is present in the Go module cache, it also builds, pushes, and deploys the router; otherwise it logs operator guidance. It reuses an existing vekil deployment, otherwise attempts helper-based deployment when available (or logs operator guidance when not), creates the model Secret, creates the Git Secret only when a token is available, and ensures the Orka API client ServiceAccount.
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.
- 3d ago Changed · +7 lines a033a211d747
- 4d ago Changed e45b129dd192
- 8d 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 (22 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 4,466 once invoked, about $0.0004 per session on Opus 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
github-actions-templates
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
cost-optimization
Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.
hybrid-cloud-networking
Configure secure, high-performance connectivity between on-premises infrastructure and cloud platforms using VPN and dedicated connections. Use when building hybrid cloud architectures, connecting data centers to cloud, or implementing secure cross-premises networking.
istio-traffic-management
Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.
multi-cloud-architecture
Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, GCP, and OCI. Use when building multi-cloud systems, avoiding vendor lock-in, or leveraging best-of-breed services from multiple providers.
terraform-module-library
Build reusable Terraform modules for AWS, Azure, GCP, and OCI infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.