Process for safely adding or updating npm dependencies
Scanned 9/12/2026
Install to Claude Code
npx -y skills add albinotonnina/echos --skill dependency-update --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Dependency Update?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/albinotonnina-dependency-update)More formats (shields.io, HTML) on the badges page.
---
name: dependency-update
description: Process for safely adding or updating npm dependencies
disable-model-invocation: true
---
## Adding a new dependency
1. Check bundle impact — justify packages >50 KB
2. Verify licence: must be MIT, Apache-2.0, BSD-2-Clause, or BSD-3-Clause
3. Check maintainer activity: last publish within 12 months, >1 maintainer for critical packages
4. Pin to exact version for CLI tools; use `^` for library dependencies
5. Add to `package.json` in the correct section (`dependencies` vs `devDependencies`)
6. Run `npm install` and commit the updated lockfile
## Updating an existing dependency
1. Read the changelog between current and target version — note any breaking changes
2. Run the full test suite after the update: `npm test`
3. Run `npm audit` and resolve any new advisories before committing
4. Update in a separate commit from feature work: `chore(deps): bump express from 4.18 to 4.19`
## Never do
- Do not use `npm install --legacy-peer-deps` without a comment explaining why
- Do not add a dependency to solve a problem that already has a solution in the codebase
- Do not add polyfills for browser APIs if target environments already support them
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling