Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for teams deploying Claude Code, Codex, or Cursor who need deterministic guardrails before letting agents touch secrets, package managers, or production-adjacent repos.
Who should use it
Who should skip it
Pass on LuD1161/agentjail if its scope or audience does not match what your team is building right now.
About this signal
LuD1161/agentjail is tracked by RepoRadar as an AI project in the AI Infrastructure section. First seen 2026-06-30; the source record was last checked on 2026-06-30. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. LuD1161/agentjail leads on workflow potential (9.7) and practical usefulness (9.0); its lowest signal is setup ease (6.4), so factor that in before investing setup time. This page summarizes the public evidence on the linked source page and states where additional review is still needed.
How this item is evaluated
The LuD1161/agentjail record combines a 8.6/10 composite score with separate popularity (1.0), risk (conditional), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
Hooks into live Claude Code, Codex, or Cursor tool calls and can block or log file, shell, and MCP actions, so first rollout should stay on non-production repos while policy scope is tuned; Install path starts a local policy daemon and hook chain on developer machines, so teams should review the default rules and audit-log location before wider deployment.