{"slug":"railguard","title":"railguard","description":"Railguard is a safer, context-aware alternative to --dangerously-skip-permissions for Claude Code.\n\nInstead of choosing between approving every command manually or giving Claude unrestricted access, Railguard sits in the middle. It intercepts every tool call — Bash, Write, Edit, Read — and makes policy-based decisions: allow safe commands instantly, block dangerous ones automatically, and ask for human approval when it's not sure.\n\nOut of the box, Railguard comes with 29 default rules covering destructive operations like terraform destroy, rm -rf, DROP TABLE, and git force-push. It detects evasion attempts (base64 encoding, chr() construction, variable substitution, shell wrapping), restricts file access with path fencing (blocking ~/.ssh, ~/.aws, /etc), snapshots every file write for one-click rollback, and logs every decision to a structured audit trail.\n\nEverything is customizable through a simple railguard.yaml file in your project directory.","developer":"railguard-dev","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-07T00:08:29.147Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/railyard-dev/railguard.git","web_data":{},"github_data":{},"catalog_sources":{"community":[{"name":"railguard","source":{"sha":"41eb9272f62eafd6fe968f381807154a16b0c71c","url":"https://github.com/railyard-dev/railguard.git","source":"url"},"homepage":"https://railguard.tech","description":"Railguard is a safer, context-aware alternative to --dangerously-skip-permissions for Claude Code.\n\nInstead of choosing between approving every command manually or giving Claude unrestricted access, Railguard sits in the middle. It intercepts every tool call — Bash, Write, Edit, Read — and makes policy-based decisions: allow safe commands instantly, block dangerous ones automatically, and ask for human approval when it's not sure.\n\nOut of the box, Railguard comes with 29 default rules covering destructive operations like terraform destroy, rm -rf, DROP TABLE, and git force-push. It detects evasion attempts (base64 encoding, chr() construction, variable substitution, shell wrapping), restricts file access with path fencing (blocking ~/.ssh, ~/.aws, /etc), snapshots every file write for one-click rollback, and logs every decision to a structured audit trail.\n\nEverything is customizable through a simple railguard.yaml file in your project directory."}]},"manifest":{"url":"https://raw.githubusercontent.com/railyard-dev/railguard/41eb9272f62eafd6fe968f381807154a16b0c71c/.claude-plugin/plugin.json","payload":{"name":"railguard","author":{"name":"railguard-dev"},"license":"MIT","version":"0.5.1","homepage":"https://github.com/railguard-dev/railguard","keywords":["security","guardrails","safety","runtime","hooks"],"repository":"https://github.com/railguard-dev/railguard","description":"A secure runtime for Claude Code. Intercepts every tool call with policy-based allow/block/ask decisions, evasion detection, path fencing, file snapshots, and audit logging."},"observed_at":"2026-11-06T10:48:14Z"}}