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 agentmods add skills/defanglabs/defang/deploynpx skills add DefangLabs/defang --skill deploygit clone --depth 1 https://github.com/DefangLabs/defangWhat 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 | $0.00031 | $0.00902 |
| Opus 5 | $0.00015 | $0.00451 |
| Sonnet 5 | $0.00006 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
deploy scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl: `eval "$(curl -fsSL s.defang.io/install)"` How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy the current project using the Defang CLI by following these steps:
Step 1: Validate the CLI
Run defang --version to confirm the CLI is installed. If it is not found, install it:
- npm:
npm install -g @defang-io/defang - Homebrew:
brew install DefangLabs/defang/defang - curl:
eval "$(curl -fsSL s.defang.io/install)"
If you installed defang for the first time, run /reload-plugins to activate the Defang MCP server.
Step 2: Authenticate
Run defang whoami to check if the user is already logged in. If not, run defang login and wait for authentication to complete.
Step 3: Find or Create a compose.yaml file
Look for any compose.yaml files in the current directory or parent directories. If multiple are found, ask the user to select one. If none are found, ask the user if they want to create a new one. If yes, ask them about the services they want to deploy and generate a compose.yaml based on their answers. You will need to know which command each service should run, any environment variables they require, whether or not they should listen on a port, and if so, which one, and so on.
Step 4: Select or create a stack
A stack is a single deployed instance of the project in a specific cloud account and region, for example: production is deployed to aws in us-east-1. Additional configuration associated with a stack can be specified in the stack file (e.g., .defang/production). Note that stack variables are read at deployment time, and are not available at runtime in your application services.
List existing stacks:
defang stack list
- If one or more stacks exist, ask the user whether to use an existing one or create a new one.
- If no stacks exist, create a new one.
To create a stack interactively:
defang stack new
Required parameters:
- Name: alphanumeric, cannot start with a number (e.g.,
production) - Provider:
aws,gcp, ordigitalocean - Region: e.g.,
us-east-1(AWS),us-central1(GCP) - Deployment Mode: controls cost and resiliency
affordable— lowest cost, for dev/test (default)balanced— general production workloadshigh_availability— critical services- See https://docs.defang.io/docs/concepts/deployment-modes
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.
- 2d ago First seen · 112 lines · 31 tokens per session scan A cbe9c51908fb
deploy is a skill published in the GitHub repository DefangLabs/defang (164 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 902 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.
ecs
AWS ECS container orchestration for running Docker containers. Use when deploying containerized applications, configuring task definitions, setting up services, managing clusters, or troubleshooting container issues.
eks
AWS EKS Kubernetes management for clusters, node groups, and workloads. Use when creating clusters, configuring IRSA, managing node groups, deploying applications, or integrating with AWS services.
k8s-dev-deploy
Build, push, and deploy Kurtosis dev images to a Kubernetes cluster without creating a release. Rebuilds engine, core, and files-artifacts-expander as multi-arch Docker images with a unique tag, pushes to the logged-in user's Docker Hub, and restarts the engine. Use when testing local code changes on a k8s cluster.
k8s-clean-cluster
Force-clean all Kurtosis resources from a Kubernetes cluster when kurtosis clean hangs or fails. Removes all kurtosis namespaces, pods, daemonsets, cluster roles, and cluster role bindings. Use when kurtosis clean -a hangs or leaves behind orphaned resources.
ovh
OVHcloud infrastructure integration for managing instances, Kubernetes clusters, networks, and object storage via CLI and Terraform.