JavaScript · MIT
leepokai/jev-guard
Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.
★ 140
Stars
22 forks · 3 open issues
—
Growth · stale
We stopped seeing this repository in its topic's top results, so its star count is frozen at the date it was last read. Subtracting from a frozen number would read as zero growth, which would be false, so no rate is shown.
18.4
Momentum / 100
see the breakdown below
51d ago
Created
last push 37d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | — — no measurable rate |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 12.1 | last push 37d ago; decays to zero at 180 days |
| Scale | 15 | 6.2 | 140 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 18.4 | capped at 35 because growth is unmeasured |
Detail
| Topics | ai-agentsclaude-codecodexcursorgemini-clihooksjevopencodeprompt-injectionsecurity |
| Matched on | Security (security) |
| Short window | +9 stars over 7 days = 1.3/day |
| Long window | +77 stars over 26 days = 3.0/day |
| Lifetime average | 2.86 stars/day over 49 days |
| First seen here | 2026-10-11 |
| Last read | 7d ago |