npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

modelbound-cursor-plugin

v0.3.3

Published

Official ModelBound plugin for Cursor — slash commands for skill pipeline, trust & safety, versions, and MCP-backed context sync.

Downloads

160

Readme

ModelBound — Cursor plugin

Audit Agent Skills for trust, token budget, duplicates, and tool-surface risk — without leaving Cursor. Run the Skill Development Pipeline, Trust & Safety findings, and manage skill versions directly from your editor.

Built and maintained by ModelBound, the unified knowledge index and MCP tool proxy for AI agents.

All slash commands shell out to the ModelBound CLI via node .modelbound/mb.mjs (installed by this plugin). The launcher uses a global modelbound binary if present, otherwise npx modelbound from npm. Same semantics as the Cursor extension and MCP. You never need skill UUIDs: pass a file path or slug and the CLI syncs + resolves internally.

What's in the box

| Component | Purpose | | --- | --- | | Skill · skill-health-lens | Invoke with /skill-health-lens to run the four core checks | | Rule · skill-authoring | Inline authoring standards on all watched skill paths | | Trust & Optimize · /mb-findings, /mb-suggest, /mb-compare, /mb-benchmark | Test & Optimize phase (extension v1.9.16 parity) | | Pipeline · /mb-pipeline, /mb-test, /mb-sync, /mb-context | Skill Development Pipeline with auto sync | | Versions · /mb-versions, /mb-restore, /mb-diff | Checkpoint history and restore | | Auth · /mb-login, /mb-logout, /mb-whoami, /mb-health | Device login + MCP connectivity | | Hook · beforeFileEdit + afterFileEdit on skill files | Pre-edit backup to .mb-backup/ and token-budget hint on save | | MCP server · modelbound | Hosted at https://mcp.modelbound.co (requires MODELBOUND_API_KEY) |

Test & Optimize workflow (Brian's case)

/mb-context set --repo org/repo
/mb-sync .modelbound/prompt-pr-contributor.md
/mb-findings .modelbound/prompt-pr-contributor.md
/mb-findings ignore ... --key "escalation:critical:..."
/mb-pipeline .modelbound/prompt-pr-contributor.md --stage test_optimize

Skill file paths (auto-detected)

  • .modelbound/**/*.md|.json
  • .kiro/skills/**/*.md
  • .cursor/rules/**/*.md|.mdc
  • .claude/**/*.md
  • .agents/skills/**/SKILL.md

Install

npx modelbound-cursor-plugin@latest install

Requires Node ≥ 20. Auth via MODELBOUND_API_KEY or run /mb-login once.

Slash commands

| Command | CLI equivalent | |---|---| | /mb-findings <skill> | findings list --skill … | | /mb-suggest <skill> | suggest --skill … | | /mb-compare <skill> | compare --skill … --from latest --to current | | /mb-benchmark <skill> | benchmark --skill … | | /mb-pipeline <skill> | pipeline run --skill … --watch | | /mb-test <skill> | test --skill … | | /mb-sync <file> | sync --file … | | /mb-context set | context set [--repo org/repo] | | /mb-optimize <file\|slug> | optimize … | | /mb-versions <skill> | versions --skill … | | /mb-restore <skill> <ver> | version restore --skill … --version … | | /mb-diff <skill> <from> [to] | version diff --skill … | | /mb-health | health | | /mb-login / /mb-logout / /mb-whoami | auth login / auth logout / auth status |

Known backend blockers

Pipeline, findings ignore, benchmark, compare, and suggest may hit hosted-backend bugs until Lovable deploys fixes. The CLI surfaces these errors explicitly (Pipeline failed:, [MCP_ERROR], etc.). See docs/BACKEND-BLOCKERS.md in modelbound-cli.

Pre-skill-write Git hook

scripts/pre-skill-write.mjs snapshots staged skill files (same paths as above) to .modelbound/backups/ before commit and blocks empty files or dropped YAML frontmatter. Opt out with MODELBOUND_SKIP_HOOK=1 or --no-verify.

Edit hooks in hooks/hooks.json back up to .mb-backup/ and print a token-budget hint on save for the same skill paths.

Related projects

| Project | Description | | --- | --- | | ModelBound CLI · npm | Terminal + CI for token optimization, skill pipeline, and version management | | ModelBound MCP Server · npm | Local-first MCP server for skill lint, convert, and cloud sync | | Cursor Extension · Marketplace | VS Code/Cursor extension for rules sync and MCP bridge | | Claude Code Plugin | Claude Code plugin for pipeline, hooks, and skill sync | | Dev Packs | Open-source curated AI context packs for engineering teams |

Install hub: modelbound.co/connect

License

MIT