review-dep-update

review-dep-update is a skill for Claude Code from marinahaugen/polymorph-mindset-plugins. It costs 48 tokens per session (2,410 once invoked), scanned A, original, MIT.

A review guide for pull requests that update software dependencies. Dependencies are libraries, services, or tools that a project relies on.

In plain words
What is it for?
Use it to review npm, Maven or Kotlin, GitHub Actions, and infrastructure-as-code dependency changes, using sources such as Context7 and GitHub.
Why use it?
It helps identify breaking changes, required code updates, and important release notes before approving an update.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the polymorph-mindset plugin — 6 skills shipped together

Good fit Use it to review npm, Maven or Kotlin, GitHub Actions, and infrastructure-as-code dependency changes, using sources such as Context7 and GitHub.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marinahaugen/polymorph-mindset-plugins/review-dep-update
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.

Any agent
npx skills add marinahaugen/polymorph-mindset-plugins --skill review-dep-update
Clone the repo
git clone --depth 1 https://github.com/marinahaugen/polymorph-mindset-plugins

Made for: Claude Code.

Or install polymorph-mindset, the plugin that ships this one along with the rest of its 6 skills.

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 review-dep-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/marinahaugen/polymorph-mindset-plugins/review-dep-update/github.svg)](https://agentmods.dev/skills/marinahaugen/polymorph-mindset-plugins/review-dep-update)
Your own site
<a href="https://agentmods.dev/skills/marinahaugen/polymorph-mindset-plugins/review-dep-update"><img src="https://agentmods.dev/badge/skills/marinahaugen/polymorph-mindset-plugins/review-dep-update/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.

agentmods 80×15 button for review-dep-update

Your own site · 80×15
<a href="https://agentmods.dev/skills/marinahaugen/polymorph-mindset-plugins/review-dep-update"><img src="https://agentmods.dev/badge/skills/marinahaugen/polymorph-mindset-plugins/review-dep-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,410 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00048 $0.02410
Opus 5 $0.00024 $0.01205
Sonnet 5 $0.00010 $0.00482
Haiku 4.5 $0.00005 $0.00241

Measured 9d ago against content hash 2f2ff1a6d7e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-dep-update 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 9d 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.

plugins/polymorph-mindset/skills/review-dep-update/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dependency Update PR Review

Review a pull request that updates dependencies by systematically researching each changed dependency for breaking changes, required migration steps, and changelog highlights.

Arguments

  • PR number or URL (required)
  • Repository (optional — defaults to current repo, use --repo org/name for cross-repo)

Stack Context Template (fill this in for your project)

Anchor the review in your stack so the AI doesn't reinvent context every PR. Replace this template with a real table that lists your repos, what they do, and which dependencies are load-bearing.

Repo Purpose Stack Key Dependencies
<repo-1> Infrastructure as code (e.g. AWS CDK, Terraform, Pulumi) TypeScript / IaC aws-cdk-lib, constructs, ...
<repo-2> Customer-facing frontend (SPA, SSR app) TypeScript, React, Vite/Next, ... UI lib, state lib, routing, http client, ...
<repo-3> Backend / BFF / API server Kotlin / Node / Go / Python framework, ORM, auth client, AWS SDK, ...

How they connect

Sketch the layers. Example:

Frontend SPA
    ↓ HTTP/REST
Backend API
    ↓ AWS SDK / JDBC / DB driver
Cloud services / database (deployed by IaC repo)

What this means for dependency reviews

  • Infrastructure dep updates can change deployed resources — verify CDK/Terraform diffs show only expected changes (asset hashes, not structural).
  • Frontend dep updates affect the user-facing UI — watch for framework version compatibility, CSS/styling breaking changes in component libraries, and bundle size regressions.
  • Backend dep updates affect the API layer — watch for language/runtime changes, serialization changes, and SDK API changes that could break integrations.
  • A dependency updated in one repo may need a coordinated update in another (e.g., shared OpenAPI codegen versions must match between frontend and backend).

Why this template exists: project-specific context shouldn't live in generic Claude knowledge — it lives next to the team that owns it. Filling in this table for your stack is part of the value of having a custom skill.

Read the full file on GitHub · 255 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 255 lines · 48 tokens per session scan A 2f2ff1a6d7e0

Subscribe to this mod's changes

review-dep-update is a skill published in the GitHub repository marinahaugen/polymorph-mindset-plugins (4 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 2,410 once invoked, about $0.0002 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.