Rollcage
ChatGPT pluginCheck agent commands first
Rollcage checks shell commands, file paths and URLs against the rules of the open-source Rollcage Guard before an AI coding agent runs them. It flags secret files like .env and keys, destructive commands like rm -rf and DROP DATABASE, risky ones like force pushes, and paste or tunnel sites data could leak to. Each check returns block, ask or allow with the reason. Read-only, no sign-in.
- Featured
- No
not on the featured shelf
Movement
From our daily snapshots over the last 30 days.
Rank by placement
#10165of 10,70432places down24h—7d
Rank in Developer tools
#808of 8661places down24h—7d
In its category
How this plugin compares with others in the same category. Positions are counted within the category, not across the whole directory.
Developer tools808th of 866 by placement
| # | Plugin | Position | 7d |
|---|---|---|---|
| 806 | #10149 | — | |
| 807 | #10161 | 1,631places down | |
| 808 | #10165 | — | |
| 809 | #10185 | — | |
| 810 | #10189 | 1,652places down |
Also on other marketplaces
Example prompts
- “Is it safe to run git push --force origin main?”
- “Should an agent be allowed to read .env.local?”
- “How do I install the Rollcage guard for Codex CLI?”
- Categories
- Made by
- NICOLAE MATIES · Website
- Sign-in
- On Install
- Availability
- Available
- Version
- 1.0.0
- Created
- October 17, 2026
- More info
- Sponsorship
- Promote this plugin