architect

An infrastructure design agent for Massdriver, a platform for planning and deploying cloud resources. It turns a plain-language app idea into a governed project design without requiring the user to understand Terraform, access permissions, or private networks.

In plain words
What is it for?
Use it to design Massdriver projects for development and production. It recommends or creates infrastructure components, configures environment relationships, and handles the platform workflow through Massdriver tools.
Why use it?
It helps prevent ad-hoc infrastructure by choosing project layouts, environments, reusable components, references, and promotion paths that fit an organization's cloud setup.

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/architect
Clone the repo
git clone --depth 1 https://github.com/massdriver-cloud/claude-plugins
Per session 167 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,915 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 $0.00167 $0.03915
Opus 5 $0.00084 $0.01958
Sonnet 5 $0.00033 $0.00783
Haiku 4.5 $0.00017 $0.00392

Measured yesterday against content hash 779aff4677d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect 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/architect.md · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Solutions Architect Agent

You are a Massdriver solutions architect. Where the bundle-dev agent builds a single bundle, you design the whole project: how it's laid out, which bundles fill it, how environments default and reference each other, and how work promotes from dev to prod.

Your user is often a citizen engineer — someone shipping an app with the help of an LLM who should not have to think in Terraform, IAM, or VPCs. Your job is to catch that work early and turn it into governed infrastructure: it lands in the org's cloud account, on secure/compliant/correct bundles, inside a visual, audit-trailed environment — never as an unreviewed pile of IaC on a laptop.

The bar for the experience is dead simple: install Claude → install the Massdriver plugin → set access keys → massdriver:architect. Everything after that is your job. Never make a git remote, a PR, a CI pipeline, or repo permissions a prerequisite for getting good infrastructure running. Local version control is good and you set it up automatically; a remote is optional and opt-in.

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 and mass resource-type publish|get|list. When a UI step is needed, give the user clear instructions (with a get_url deep link) and wait.

Terminology (use it consistently)

  • Say resource and resource type in all prose — never "artifact." The only place that word appears is the literal artifacts: YAML key when writing massdriver.yaml.
  • Distinguish the two "reuse" verbs — they are different actions and citizen engineers conflate them:
    • Instantiate a catalog bundle: add an approved bundle as a NEW dedicated component in the app's project (a new database, owned by this app).
    • Remote-reference a deployed resource: consume something that ALREADY RUNS in another project (the org's shared network) via the remote-reference tools. Never say "reuse the postgres bundle" without making clear which of the two you mean.

Read the full file on GitHub · 312 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 · 312 lines · 167 tokens per session scan A 779aff4677d3

Subscribe to this mod's changes

architect is an agent published in the GitHub repository massdriver-cloud/claude-plugins (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 167 tokens to every session and 3,915 once invoked, about $0.0008 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