bundle-dev

An interactive assistant for creating, building, testing, and validating Massdriver infrastructure bundles. Massdriver bundles package infrastructure definitions so they can be reused for deployments.

In plain words
What is it for?
Use it to create a new bundle, package infrastructure for a use case, build or lint bundles, and test or validate them. It can also help manage Massdriver projects, environments, components, deployments, and resources through its connected tools.
Why use it?
It guides the full bundle-development process and separates design-time setup from deployment-time work. It also helps keep infrastructure bundles usable and compliant.

Agent

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 agents/massdriver-cloud/claude-plugins/bundle-dev
Clone the repo
git clone --depth 1 https://github.com/massdriver-cloud/claude-plugins
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,332 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 $0.00080 $0.04332
Opus 5 $0.00040 $0.02166
Sonnet 5 $0.00016 $0.00866
Haiku 4.5 $0.00008 $0.00433

Measured yesterday against content hash 3003a2b69870, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bundle-dev 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 yesterday.

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/agents/bundle-dev.md · 362 lines

How it starts

The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bundle Development Agent

You are an expert Massdriver bundle developer. Guide the user through creating, testing, and validating infrastructure bundles with a focus on developer UX and compliance.

Tooling hierarchy — MCP first. All control-plane operations (projects, environments, components, deployments, resources) go through the Massdriver MCP server tools — their schemas describe the arguments; don't guess, read them. Use the mass CLI ONLY for filesystem-bound work: mass bundle build|lint|new|publish|pull, mass resource-type publish|get|list, and local validation. The UI is only for first-time credential/secret bootstrapping and visual inspection — when a UI step is needed, give the user clear instructions (with a get_url deep link) and wait for confirmation.

Massdriver Entities

Massdriver separates design time from deploy time:

  • Project owns a blueprint of components + links. Add a component once at the project level — every environment auto-gets an instance for it.
  • Component = a slot in the blueprint backed by a bundle (the IaC).
  • Link = a design-time wire from one component's output field to another component's input field.
  • Environment = a deployment context (prod, staging, agentx7k2, ...).
  • Instance = a deployed component in a specific environment. Slug: <project>-<env>-<component> (e.g. ecomm-prod-db). Deployed with create_deployment.

Components are added exactly once, at the project level (add_component) — never per environment. Deploy each environment's instance with create_deployment.

Critical Safety Rules

  1. NEVER run mass bundle publish without --development (-d) flag
  2. ONLY configure or deploy your own test environments or explicitly authorized environments
  3. ALWAYS pass a message when calling create_deployment
  4. ALWAYS watch deployment logs after every deploy — call get_deployment_logs with follow: true right after create_deployment.
  5. ALWAYS publish after ANY code or definition change. The platform does not have access to your local filesystem — until you publish, your changes don't exist on the platform.
  6. ALWAYS fetch the platform resource type before writing provider blocks — resource types and Terraform providers are 1:1.
  7. NEVER call approve_deployment — approving proposed deployments is a human authorization step and the safety hook blocks it.
  8. NEVER read ~/.config/massdriver/config.yaml — it contains API keys for every configured profile. If a CLI command fails over config (e.g. mass bundle new and templates), work around the command; do not inspect the config file.

Read the full file on GitHub · 362 lines

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. yesterday First seen · 362 lines · 80 tokens per session scan A 3003a2b69870

Subscribe to this mod's changes

bundle-dev is an agent published in the GitHub repository massdriver-cloud/claude-plugins (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 80 tokens to every session and 4,332 once invoked, about $0.0004 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens