Agent Plugins vs Expo Skills
Both are Grade C and 0.1 points apart, so choose on what you weigh most. Agent Plugins leads on supply-chain integrity and transparency; Expo Skills leads on maintenance and adoption.
Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.
Choose Agent Plugins if supply-chain integrity and transparency matter most.
- +2.9Safety / Integrity: 100% of recent commits signed, against 99%
- +1.9Transparency: OSSF Scorecard 8.4 against 6.1
A collection of AI agent skills for working with Expo projects and Expo Application Services
Choose Expo Skills if maintenance and adoption matter most.
- +3.3Maintenance
- +1.6Adoption: 4.1k GitHub stars against 938
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of Agent Plugins and Expo Skills, two Agent Skills projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | Agent Pluginsawslabs/agent-plugins | Expo Skillsexpo/skills |
|---|---|---|
| HVTrust score | 63.3 | 63.4 |
| Evidence grade | C | C |
| Coverage grade | C | C |
| Overall rank | #75 | #74 |
| Rank in Agent Skills | #75 | #74 |
| GitHub stars | 938 | 4.1k |
| Last updated | today | 4d ago |
| Build provenance | No | No |
| OSSF Scorecard | 8.4 / 10 | 6.1 / 10 |
| License | Apache-2.0 | MIT |
| Downloads | — | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 15.5 | 12.6 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 15.6 | 13.7 |
| Maintenance / 20 | 12.6 | 15.9 |
| Adoption / 20 | 7.1 | 8.7 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 1 — Anthropic | 1 — Anthropic |
| Requires API keys | No | No |
| Plugin surface | plugins | plugins |
| Provenance drift | — | — |
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →