nimbalyst/lib-updater
skills/dev/lib-updater/SKILL.md
Update dependencies with changelog review. Use when updating npm packages or libraries.
$ install --global
skillsauthnpx skillsauth add nimbalyst/skills lib-updaterInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 6, 2026, 6:51 AM126.0s1 file scanned
SKILL.md
- name:
- lib-updater
- description:
- Update dependencies with changelog review. Use when updating npm packages or libraries.
Update the Anthropic Agent SDK, MCP library, and OpenAI Codex SDK to their latest versions, showing changelogs.
Libraries to Update
- @anthropic-ai/claude-agent-sdk - Located in root
package.json - @modelcontextprotocol/sdk - Located in
packages/electron/package.json - @openai/codex-sdk - Located in
packages/runtime/package.json
Steps
- Check current versions by reading the package.json files
- Fetch latest versions from npm:
- Run
npm view @anthropic-ai/claude-agent-sdk versionto get latest - Run
npm view @modelcontextprotocol/sdk versionto get latest - Run
npm view @openai/codex-sdk versionto get latest
- Get changelogs for all packages:
- For claude-agent-sdk: Fetch https://github.com/anthropics/claude-code/releases to find changes between current and latest. Important: The SDK changelog often just says "brought up to CLI version X.Y.Z" - in these cases, also fetch the Claude Code CLI changelog at https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md to get the actual feature/fix details for those CLI versions.
- For MCP SDK: Fetch https://github.com/modelcontextprotocol/typescript-sdk/releases to find changes between current and latest
- For Codex SDK: Fetch https://github.com/openai/openai-codex-sdk/releases or https://www.npmjs.com/package/@openai/codex-sdk to find changes between current and latest
- Report the changes - Show what changed between the current version and latest for each library. For the Agent SDK, include relevant CLI changes that affect the SDK.
- Update the versions in the respective package.json files:
- Update
@anthropic-ai/claude-agent-sdkversion in rootpackage.json(use exact version, no caret) - Update
@modelcontextprotocol/sdkversion inpackages/electron/package.json(use caret prefix) - Update
@openai/codex-sdkversion inpackages/runtime/package.json(use caret prefix)
- Run npm install at the repository root to update package-lock.json
- Verify the updates were successful by checking the installed versions
- Commit the changes - Create a git commit with the updated dependencies. The commit message should summarize which packages were updated and their version changes (e.g., "deps: update claude-agent-sdk 1.0.0 -> 1.1.0, mcp-sdk 2.0.0 -> 2.1.0"). Stage only the relevant files:
package.json,packages/electron/package.json,packages/runtime/package.json, andpackage-lock.json.
Output Format
Present the findings in this format:
@anthropic-ai/claude-agent-sdk
- Current: [version]
- Latest: [version]
- Changes:
- [List notable changes from release notes]
@modelcontextprotocol/sdk
- Current: [version]
- Latest: [version]
- Changes:
- [List notable changes from release notes]
@openai/codex-sdk
- Current: [version]
- Latest: [version]
- Changes:
- [List notable changes from release notes]
If any package is already at the latest version, note that no update is needed.
Related Skills
nimbalyst/user-research-doc
testing
VerifiedTrustedCommunity
Structure user research findings and insights. Use when documenting user research, interview synthesis, or usability testing results.
20SKILL.mdUpdated Jun 6, 2026
nimbalyst/deep-researcher
testing
VerifiedTrustedCommunity
Parallel multi-agent research with citations. Use when conducting deep research, competitive analysis, or investigating complex topics.
20SKILL.mdUpdated Jun 6, 2026
nimbalyst/customer-interview-sim
testing
VerifiedTrustedCommunity
Simulate customer interviews for practice. Use when preparing for user interviews or testing interview scripts.
20SKILL.mdUpdated Jun 6, 2026
nimbalyst/competitive-analyst
research
VerifiedTrustedCommunity
Competitive analysis with SWOT and feature comparisons. Use when analyzing competitors, comparing products, or evaluating market positioning.
20SKILL.mdUpdated Jun 6, 2026