- Home
- Skills
- APIs & Backend
- Dependency Update Planner
Works with the AI Agents you already use
Dependency Update Planner
Analyze npm and Python dependencies to generate risk-aware, batched upgrade plans with live registry data.
$2.99
Dependency Update Planner
Example session with this skill installed
Analyze my package.json for pending updates and flag anything that hasn't been updated in over two years.
- Read your context and instructions
- Compiled the dependency update planner
I have analyzed your package.json against the npm registry. I found 12 pending updates, including one abandoned package and two high-risk major version jumps.
Dependency Upgrade Plan
| Package | Current | Latest | Type | Age Drift | Risk / Status |
|---|---|---|---|---|---|
lodash | 4.17.15 | 4.17.21 | Patch | 840 days | Stable |
axios | 0.21.1 | 1.6.7 | Major | 1,120 days | Breaking (0.x to 1.x) |
moment | 2.24.0 | 2.30.1 | Minor | 1,500 days | Deprecated (Use date-fns) |
left-pad | 1.3.0 | 1.3.0 | - | 2,200 days | Abandoned (No release >2yr) |
next | 13.0.0 | 14.1.0 | Major | 95 days | Breaking |
Batch 1: Low Risk (Patches)
npm install lodash@4.17.21
Batch 2: Significant Updates (Requires Testing)
# Note: axios 1.x introduces breaking changes to error handling
npm install axios@1.6.7 next@14.1.0
Batch 3: Replacement Required
- moment: Project is in maintenance mode. Plan migration to
dayjsordate-fns. - left-pad: No updates since 2018. Evaluate if this utility is still necessary.
Next steps
- Review the
axiosmigration guide for changes to theerror.responseobject. - Run Batch 1 and execute your unit test suite.
- Schedule a refactor for the
momentlibrary to reduce bundle size and improve maintainability.
Connects securely to your tools. The creator never sees your data.
About this skill
Outdated dependencies introduce technical debt and subtle bugs. Blindly running update commands often breaks builds due to unexpected breaking changes. This skill analyzes your project to build a risk-aware upgrade roadmap.
What it does
- Version Analysis identifies patch, minor, and major updates for npm and Python ecosystems.
- Risk Assessment flags abandoned packages (2+ years stagnant) and bleeding-edge releases (under 7 days old).
- Update Classification treats 0.x minor bumps as breaking changes to prevent semver accidents.
- Drift Measurement calculates exactly how many days and versions each package trails the latest release.
- Batched Execution generates ordered install commands to manage complex dependency chains.
How it works
- Source Scan reads
package.json,package-lock.json,requirements.txt, orpyproject.toml(Poetry/PEP 621). - Registry Lookup queries npm and PyPI APIs for current version metadata and deprecation notices.
- Logic Application filters updates based on age, stability, and version delta.
- Plan Generation outputs a Markdown report with links to changelogs and exact shell commands.
Frameworks & tools
Supports Node.js (npm, yarn, pnpm) and Python (pip, Poetry). Uses public JSON APIs for registry.npmjs.org and pypi.org.
Why this beats prompting it yourself
Generic LLMs lack real-time registry data and often ignore the nuances of 0.x versioning. This skill integrates live API lookups to distinguish between a safe patch and a risky, unproven release.
Use cases
- Quarterly Maintenance to systematically reduce version drift across a monorepo.
- Pre-release Hardening by identifying and replacing abandoned or deprecated libraries.
- Incident Response to check if a local bug exists in a more recent, stable version.
Known limitations
Requires outbound network access to npm and PyPI registries. Does not perform local build testing or automated regression checks.
Requires outbound network access to npm and PyPI. Does not execute local builds or run test suites to verify compatibility.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Requires
Permissions
Allowed Hosts