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.
git clone --depth 1 https://github.com/massdriver-cloud/claude-pluginsWrote 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/commands/massdriver-cloud/claude-plugins/architect)<a href="https://agentmods.dev/commands/massdriver-cloud/claude-plugins/architect"><img src="https://agentmods.dev/badge/commands/massdriver-cloud/claude-plugins/architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/massdriver-cloud/claude-plugins/architect"><img src="https://agentmods.dev/badge/commands/massdriver-cloud/claude-plugins/architect.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00016 | $0.00902 |
| Opus 5.5 | $0.00006 | $0.00361 |
| Sonnet 5.5 | $0.00003 | $0.00180 |
| Haiku 4.5 | $0.00002 | $0.00090 |
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 19d 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect — App Idea → Governed Infrastructure
Placeholder / demo command. Citizen developers — non-infra folks vibe-coding an app with an LLM — shouldn't end up with an unreviewed pile of infrastructure on a laptop. This command routes that work through Massdriver's self-service portal instead: it lands in the org's cloud account, on secure/compliant/correct bundles, inside a visual, audit-filled environment with a full deployment history.
Start the architect agent to take an app idea and turn it into a real Massdriver project:
the right project layout, the right bundles, the right runtime, and a permission-gated path
from dev up through production.
What This Does
- Setup — asks which environment and which credentials/profile to work in.
- Understand the use case — what the citizen developer is actually trying to ship.
- Recommend a project layout — one project vs. sharded projects, environment defaults, and remote references for shared/cross-project resources.
- Recommend bundles — reuse existing org bundles where they fit; identify where a custom application bundle is needed. If the app needs a capability with no bundle in the (grant-filtered) catalog, the agent won't improvise infrastructure — it tells the user exactly what to request from their DevOps team, and keeps building the rest.
- Pick a runtime — examines the use case against the org's available bundles, environments, and standards, then picks the best runtime and proceeds. It states its reasoning; it doesn't make the citizen developer choose. See below.
- Build + publish the app bundle directly to the platform (
--development) so the citizen developer never needs a git remote or a PR to get moving. Source is committed to a local git repo automatically; a remote is opt-in (the agent asks if one already exists). - Progress through environments — dev → staging → prod, gated by the user's permissions.
The whole flow is meant to be as frictionless as: install Claude → install the Massdriver
plugin → set access keys → /massdriver:architect. No git hosting, CI, or repo permissions
required.
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.
- 19d ago Changed 66c5ade76f3a
- 1mo ago First seen · 83 lines · 16 tokens per session scan A d9672830f52c
architect is a command published in the GitHub repository massdriver-cloud/claude-plugins (2 stars, last pushed 19d ago), licensed Apache-2.0. It adds 16 tokens to every session and 902 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other commands, from other repositories
cost-optimize
Reduce cloud costs across AWS, Azure, and GCP through rightsizing, reserved and spot capacity, storage tuning, and cost monitoring.
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
env
Manage Vercel environment variables. Commands include list, pull, add, remove, and diff. Use to sync environment variables between Vercel and your local development environment.
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.
scan
Scan AWS account for cost optimization.
finops-status
Orientation — say where an opportunity or assignment sits in the five-step FinOps lifecycle and what unlocks next. Useful when a record has no active stage: an opportunity while its assignments do the work, an assignment whose plan has not been approved yet, or a rejected or archived assignment. Read-only; mutates…