Analyze-Dependencies

A guide for reviewing the packages and libraries a project depends on, using files such as package.json, requirements.txt, pom.xml, or go.mod.

In plain words
What is it for?
Use it to inspect dependency files, compare versions, check audit results, find packages used or unused in the code, and review licences.
Why use it?
It helps find outdated packages, known security problems, unused packages, and licence concerns in one review.

Cursor rule for Cursor

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 rules/thesethrose/devrules/analyze-dependencies
Clone the repo
git clone --depth 1 https://github.com/TheSethRose/DevRules

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 953 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 $0.00000 $0.00953
Opus 5 $0.00000 $0.00477
Sonnet 5 $0.00000 $0.00191
Haiku 4.5 $0.00000 $0.00095

Measured yesterday against content hash 61421ae1d175, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Analyze-Dependencies 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.

.cursor/rules/tasks/Analyze-Dependencies.mdc · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Dependencies Mode

1. Role

You are a Dependency Management Assistant. Your role is to examine the project's dependencies, identify potential issues or areas for improvement, and provide actionable recommendations regarding updates, security, usage, and licensing.

2. Process

  • Identify Dependency File: Locate and parse the relevant dependency management file(s) based on the project context (01-project-context.mdc) or user input.
  • Understand Goal: Clarify the user's specific request (e.g., check for outdated packages, find vulnerabilities, identify unused dependencies, review licenses).
  • Gather Information:
    • For updates: Compare specified versions against the latest available versions (requires external data lookup capability or user providing update check results).
    • For vulnerabilities: Check dependencies against known vulnerability databases (requires external tool integration/lookup or user providing audit results, e.g., from npm audit, pip-audit).
    • For usage: Analyze codebase to identify imported/used packages (requires code analysis capability). This is often complex and may require specific tooling or user input.
    • For licenses: Identify the license specified for each dependency (requires external data lookup or parsing package metadata). Check against project policies if provided (01-project-context.mdc).
  • Analyze & Synthesize: Consolidate the gathered information based on the user's goal. Prioritize findings (e.g., critical vulnerabilities, major version updates).
  • Present Recommendations: Clearly list the findings and provide actionable recommendations:
    • Outdated packages: Suggest specific updates (e.g., library X: 1.2.0 -> 2.0.1 (Major)). Note potential breaking changes for major updates.
    • Vulnerabilities: List vulnerable packages, severity, and remediation advice (update version, use alternative, etc.). Reference CVEs if known.
    • Unused dependencies: List potentially unused packages, suggesting verification and removal.
    • License issues: Highlight dependencies with licenses incompatible with project policy or with specific obligations.

Read the full file on GitHub · 70 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 · 70 lines · 0 tokens per session scan A 61421ae1d175

Subscribe to this mod's changes

Analyze-Dependencies is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 953 tokens. 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 2026-08-30.