massdriver

A workflow for developing and testing Massdriver infrastructure bundles. These bundles are reusable packages that describe how cloud infrastructure is configured and deployed.

In plain words
What is it for?
Use it to scaffold bundles, run interactive development or upgrade tests, and work with Massdriver infrastructure components through its control plane.
Why use it?
It provides a defined way to build bundles, test upgrades, and manage Massdriver projects, environments, and deployments.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/massdriver-cloud/claude-plugins/massdriver
Any agent
npx skills add massdriver-cloud/claude-plugins --skill massdriver
Clone the repo
git clone --depth 1 https://github.com/massdriver-cloud/claude-plugins

Made for: Claude Code, Codex.

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,387 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00104 $0.07387
Opus 5 $0.00052 $0.03694
Sonnet 5 $0.00021 $0.01477
Haiku 4.5 $0.00010 $0.00739

Measured 2d ago against content hash c3505258e29d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

massdriver 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 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.

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.

massdriver/skills/massdriver/SKILL.md · 738 lines

How it starts

The opening of the file, as written. The whole thing — 738 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Massdriver Bundle Development

You are helping develop infrastructure bundles for Massdriver. This skill provides patterns, workflows, and reference material for bundle development against the platform.

Tooling hierarchy — MCP first. Every control-plane operation (projects, environments, components, instances, deployments, resources) is a tool on the massdriver MCP server — the server's tool list and schemas are the reference; don't guess arguments, read them. The mass CLI is used ONLY for filesystem-bound work the MCP server can't touch (see CLI Reference at the bottom). The UI is only for first-time credential/secret bootstrapping and visual canvas inspection — hand the user a deep link with get_url. GraphQL is optional, for multi-entity queries only (references/graphql.md).

Mental Model (read first)

Massdriver separates design time from deploy time:

  • Project — owns a blueprint: a graph of components connected by links. The blueprint is the architecture.
  • Component — a slot in the blueprint backed by a bundle (the IaC). Add a component once at the project level — every environment gets it automatically.
  • Link — a design-time wire from one component's output field to another component's input field. Becomes a connection at deploy time.
  • Environment — a deployment context (e.g. prod, staging, agentx7k2). Environments materialize the blueprint into instances.
  • Instance — a deployed component in a specific environment. Slug is <project>-<env>-<component> (e.g. ecomm-prod-db).
  • Resource — the runtime output of an instance, conforming to a resource type (the schema contract). Bundles author "artifacts" in massdriver.yaml; those become resources at deploy time.

Components are added exactly once, at the project level (add_component) — never per environment. Every environment automatically gets an instance for every component.

Quick Start

Workflow Command Use When
Full Development /massdriver:develop <use-case> Creating/updating bundles with full test loop
Upgrade Testing /massdriver:test-upgrade <bundle> Validating version upgrades against prod config
Quick Generation /massdriver:gen <use-case> Scaffolding a bundle without deploy loop

Read the full file on GitHub · 738 lines

Files

What ships with it

7 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.

Changes

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.

  1. 2d ago First seen · 738 lines · 104 tokens per session scan A c3505258e29d

Subscribe to this mod's changes

massdriver is a skill published in the GitHub repository massdriver-cloud/claude-plugins (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 104 tokens to every session and 7,387 once invoked, about $0.0005 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

application-design-center-design-deploy

Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting…

google/skills · 94 tokens

terraform-skill

Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…

agentscope-ai/QwenPaw · 62 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

huggingface-spaces

Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't…

huggingface/skills · 106 tokens

yandex-cloud

Read Yandex Cloud through its REST API. Applies to any question about VMs, metrics, logs, audit events, Kubernetes, managed databases, serverless, networking or any other Yandex Cloud resource. Never shell out to the yc CLI — it is not how this agent reaches Yandex Cloud and is usually not installed.

Tracer-Cloud/opensre · 71 tokens

cloud-architect

Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…

Jeffallan/claude-skills · 71 tokens