guardrails 1.0.0
Stops risky shell commands before they run: killing ports owned by Docker containers, printing secrets from the environment, rewriting your kubeconfig, and asks before kubectl writes on production contexts.
Install
/plugin marketplace add lucasleandro08/claude-mods /plugin install guardrails@claude-mods
Run both lines inside Claude Code.
Hooks into
- Tool calls
Also in lucasleandro08/claude-mods
- mod-manager 1.1.0 A Dracula-themed pane to install the claude-mods and turn them on and off. Every other mod ships disabled; this one is on and lists them all. 0
- live-diff 1.0.0 A Dracula-themed pane with the diff of every Edit and Write Claude makes in the session, a file navigator and line numbers. 0
- kube-pane 1.0.0 A kubectl context chip above the prompt and a Dracula-themed pods pane: switch context for Claude's session without touching your kubeconfig, filter pods, and open a shell in any container from the app's Terminal. 0
- pr-pane 1.0.0 Your open pull requests in a Dracula-themed pane: CI, Codex review and whether each one already reached your integration branch, plus a chip above the prompt that flags failing CI. 0
- promote-branch 1.0.0 /promote previews merging the current branch into an integration branch (staging, homolog, develop); /promote go does a full merge in a temporary worktree and pushes it, never touching your checkout. 0
- codex-loop 1.0.0 /codex-loop <PR> hands Claude a review loop with the Codex GitHub bot: request a review, weigh each finding, fix or 👎 it, reply, resolve and repeat until 👍. 0
- turn-done 1.0.0 A toast and a chime when a long Claude turn finishes, so you can look away while it works. 0
- aws-profile 1.0.0 Shows the AWS_PROFILE Claude Code runs with above the prompt, in red when it looks like production. 0
More guardrails mods
- blast-radius 0.1.0 See what a risky command would change before it runs. 244.1k
- agents-md 0.1.0 AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working director... 149.5k
- ruflo-rvf 0.3.5 mod + skill RVF format for portable agent memory, session persistence, and cross-platform transfer. As a mod (ADR-445): a write guard that keeps secrets out of memory, sessions and transfers, /rvf-mod, and a status file the console shows 73.9k
- openviking-memory 0.7.1 mod + skill Long-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations. 39.3k
- tool-timing-badge 0.2.0 Times every tool call and wraps the engine's ToolUse rendering with a colored duration badge from the surface's own element table, on the terminal, Desktop and mobile. Hooks tool.call and ui.render using JSX. 32.4k