test-upgrade

A command that tests upgrading a deployed software bundle by copying its production-like setup into an isolated test environment.

In plain words
What is it for?
Use it to clone a deployment, compare the test copy with production, optionally reduce its size, deploy a baseline, apply a target version, inspect logs, and compare results.
Why use it?
It lets you check an upgrade without changing the live deployment and helps reveal configuration or deployment problems before release.

Command

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 commands/massdriver-cloud/claude-plugins/test-upgrade
Clone the repo
git clone --depth 1 https://github.com/massdriver-cloud/claude-plugins
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 425 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 $0.00018 $0.00425
Opus 5 $0.00009 $0.00212
Sonnet 5 $0.00004 $0.00085
Haiku 4.5 $0.00002 $0.00042

Measured 2d ago against content hash 47dc4ad6eff6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-upgrade 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/commands/test-upgrade.md · 50 lines

What it actually says

Upgrade Testing

Start the upgrade-tester agent to validate a bundle version upgrade against production-like configuration.

What This Does

  1. Identify instance - Instance slug specifies exactly which bundle deployment to clone (e.g., api-prod-database)
  2. Fork environment - fork_environment creates an isolated test environment carrying prod's component config (secrets/refs/defaults opt-in)
  3. Verify the mirror - compare_environments between prod and the fork
  4. Adjust scale - Optionally copy_instance with overrides to reduce non-critical dependency sizes
  5. Baseline deploy (MCP) - create_deployment + get_deployment_logs follow:true
  6. Upgrade (MCP) - update_instance to the target version, redeploy, then audit with compare_deployments
  7. Report results - Summary of upgrade success/failure with recommendations

Usage

Specify the instance slug and target version:

/massdriver:test-upgrade api-prod-database 1.3.0
/massdriver:test-upgrade ecomm-production-redis 2.0.0

Instance slugs follow the format: {project}-{environment}-{component} (e.g., api-prod-database).

If the slug or version aren't specified, the agent will ask.

Instructions

Use the Task tool to spawn the upgrade-tester agent with the upgrade details. The agent will handle the interactive workflow.

Parse the arguments to extract:

  • Instance slug (first argument) - identifies the specific instance to clone
  • Target version (second argument) - the version to upgrade to

If arguments weren't provided, ask the user for the instance slug and target version.

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 · 50 lines · 18 tokens per session scan A 47dc4ad6eff6

Subscribe to this mod's changes

test-upgrade is a command published in the GitHub repository massdriver-cloud/claude-plugins (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 18 tokens to every session and 425 once invoked, about $0.0001 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.