Repository · MIT
jmanico/grim-prompter
Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT.
★ 362
Stars
31 forks · 1 open issues
+37/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
52.1
Momentum / 100
see the breakdown below
10d ago
Created
last push 9d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 30.2 | +37/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 14.5 | last push 9d ago; decays to zero at 180 days |
| Scale | 15 | 7.4 | 362 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 52.1 | sum of the above |
Detail
| Topics | ai-agentsappsecclaude-codecodexlinddunllmpastaprompt-engineeringsecuritystridethreat-modeling |
| Matched on | AI Agents (ai-agents) LLM & Inference (llm) Security (security) |
| Short window | +259 stars over 7 days = 37.0/day |
| Long window | no snapshot 14–45 days old yet |
| Lifetime average | 45.24 stars/day over 8 days |
| First seen here | 2026-10-29 |
| Last read | 2d ago |