Cc Safety Net vs Vercel Skills
Both are Grade A and 3.3 points apart, so choose on what you weigh most. Cc Safety Net leads on maintenance and transparency; Vercel Skills leads on adoption.
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi…
Choose Cc Safety Net if maintenance and transparency matter most.
- +2.0Maintenance: last push 1d ago, against 8d ago
- +0.8Transparency: OSSF Scorecard 6.0 against 5.1
- +0.5Safety / Integrity: OSSF Scorecard 6.0 against 5.1
The open agent skills tool - npx skills
Choose Vercel Skills if adoption matters most.
- +7.1Adoption: 5.0M weekly downloads against 5.9k
Where they differ
1 dimension identical: Identity 18.0 · Full evidence table
An independent, evidence-based trust comparison of Cc Safety Net and Vercel 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 | Cc Safety Netkenryu42/cc-safety-net | Vercel Skillsvercel-labs/skills |
|---|---|---|
| HVTrust score | 86.6 | 89.9 |
| Evidence grade | A | A |
| Coverage grade | B | B |
| Overall rank | #7 | #3 |
| Rank in Agent Skills | #7 | #3 |
| GitHub stars | 1.6k | 32.5k |
| Last updated | 1d ago | 8d ago |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 6.0 / 10 | 5.1 / 10 |
| License | MIT | MIT |
| Downloads | 6k/wk | 5.0M/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 19.4 | 18.9 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 13.6 | 12.8 |
| Maintenance / 20 | 19.9 | 17.9 |
| Adoption / 20 | 12.7 | 19.8 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | — |
| External providers | 1 — Anthropic | — |
| Requires API keys | No | No |
| Plugin surface | plugins | — |
| Provenance drift | Match | Match |
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 v4.3 →