ai-jail
CLAUDE.md1.4k starsChanged 3 months agoGPL-3.0View on GitHub
A Rust CLI tool that wraps bubblewrap (bwrap) to sandbox AI coding agents (Claude Code, GPT Codex, OpenCode, Crush). It replaces a bash script with config persistence (.ai-jail TOML), proper…
- Reads credentials
- Commits and pushes
We split this CLAUDE.md into the rules it gives an agent
8 rules. About 0 are common, 2 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Trending
Less talk lately.thin dataabout the whole repository
Who's talking about akitaonrails/ai-jail
- Amit-Roy/agent-console“Analyzer runs commands in a bwrap jail so compromise shows as attempts”GitHub · Oct 24, 2026
- Alexandre-Tortoza/ai-skills“[Security] Implement trust policy for repository-requested and third-party skills”GitHub · Aug 24, 2026
- Alexandre-Tortoza/ai-skills“[Epic] Build ai-skills v0: central skill and knowledge manager for AI agents”GitHub · Aug 24, 2026
- craftzdog/dotfiles“feat(tmux): run claude via ai-jail in popup”GitHub · May 23, 2026
The biggest 4 of 4 mentions linking to the repository that our crawl found. Each line is their own headline.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.