audit-upgrade

audit-upgrade is a command for Claude Code from spree/agent-skills. It costs 24 tokens per session (777 once invoked), scanned A, original, MIT.

A read-only report that checks whether a Spree online store is ready for a version upgrade. Spree is a Ruby on Rails ecommerce platform, and the report examines the change from the installed version to a target version.

In plain words
What is it for?
Finding the installed Spree version, reading the relevant official upgrade notes, checking the app's code and package manifests, and producing an upgrade-readiness plan for the developer to carry out.
Why use it?
It shows likely breaking changes, dependency or SDK mismatches, and the upgrade steps before anything is changed. The audit itself does not run the upgrade, database migrations, or dependency updates.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the spree plugin — 26 skills, 2 commands, 1 agent, 2 hooks shipped together

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/spree/agent-skills/audit-upgrade
Clone the repo
git clone --depth 1 https://github.com/spree/agent-skills

Made for: Claude Code.

Or install spree, the plugin that ships this one along with the rest of its 26 skills, 2 commands, 1 agent, 2 hooks.

Wrote 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.

agentmods badge for audit-upgrade

README.md
[![agentmods](https://agentmods.dev/badge/commands/spree/agent-skills/audit-upgrade.svg)](https://agentmods.dev/commands/spree/agent-skills/audit-upgrade)
Your own site
<a href="https://agentmods.dev/commands/spree/agent-skills/audit-upgrade"><img src="https://agentmods.dev/badge/commands/spree/agent-skills/audit-upgrade.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 777 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 5.1 $0.00024 $0.00777
Opus 5 $0.00012 $0.00388
Sonnet 5 $0.00005 $0.00155
Haiku 4.5 $0.00002 $0.00078

Measured 6d ago against content hash 7a706c28f39c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

audit-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 6d 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.

commands/audit-upgrade.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spree upgrade-readiness audit

Target version: $ARGUMENTS — if blank, detect the installed version (step 1) and target the next minor.

This command is read-only/advisory: never run spree upgrade, bundle update, or migrations from here. The output is a readiness report; the user runs the upgrade.

Flavor note: on a classic Rails app (Spree gems at the repo root, no Docker/CLI), read Gemfile.lock instead of backend/Gemfile.lock, get the plan with DRY_RUN=1 bundle exec rake spree:upgrade instead of spree upgrade --plan, and the closing recommendation becomes the native sequence: bundle update <spree gems>, bin/rake spree:install:migrations && bin/rails db:migrate, bin/rake spree:upgrade.

Steps

  1. Determine the version hop. Installed: the spree_core entry in backend/Gemfile.lock (monorepo edge projects resolve gems via path — read the version from the monorepo's gemspec instead). Target: $ARGUMENTS or the next minor.

  2. Read the official upgrade doc for that hop. Local first: node_modules/@spree/docs/dist/developer/upgrades/<from>-to-<to>.md; fall back to https://spreecommerce.org/docs/developer/upgrades/<from>-to-<to>. Extract three lists: (a) the data-backfill steps the rake manifest automates, (b) required post-upgrade configuration the manifest does NOT cover (cron jobs, env), (c) breaking changes that may require code edits.

  3. Spawn the spree-expert agent (Task tool, subagent_type: spree-expert) with a charter built from the breaking-changes list, for example:

    Audit this codebase for the Spree → upgrade. For each breaking change below, find concrete usages with file:line evidence — or state it's not used: . Check specifically: decorators in backend/app/ referencing renamed or removed Spree classes/methods; storefront code (apps/storefront/) string-matching wire formats that changed; custom subscribers/services touching changed models. Also report the @spree/sdk version declared in apps/storefront/package.json and whether it matches the target Spree version's compatibility row. Return findings only — no fixes.

Read the full file on GitHub · 33 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. 6d ago First seen · 33 lines · 24 tokens per session scan A 7a706c28f39c

Subscribe to this mod's changes

audit-upgrade is a command published in the GitHub repository spree/agent-skills (4 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 777 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.