Claude Code mod
guard
Blocks destructive shell commands and access to secret files before they run, in Bash and PowerShell, anywhere in a compound command
Install
git clone https://github.com/StanislavKozachenko/claude-mods.git
claude --plugin-dir ./claude-mods/plugins/guardThe repo has no marketplace file, so load the plugin folder directly with --plugin-dir.
What it can access
- Reach
- L1Reads: reads files, reads mod state, draws
- Sees
- Bash calls, Read calls, Edit calls, Write calls, NotebookEdit calls, every tool call
- Hooks
session.starttool.callcommand.run
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- StanislavKozachenko/claude-mods
- Folder
plugins/guard- Author
- Stanislav Kozachenko
- License
- MIT
- Last updated
- 29 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is guard?
Blocks destructive shell commands and access to secret files before they run, in Bash and PowerShell, anywhere in a compound command It is a mod for Claude Code, from StanislavKozachenko/claude-mods on GitHub.
What can the guard mod access?
Its widest reach is "reads" (reads files, reads mod state, draws). It sees Bash calls, Read calls, Edit calls, Write calls, NotebookEdit calls, every tool call. Like any mod, it runs with your permissions.
How do I install guard?
Clone StanislavKozachenko/claude-mods and start Claude Code with --plugin-dir pointing at the mod's folder (plugins/guard).
More guard & safety mods
guard
carlvellotti/mods-starter
Pauses risky shell commands (rm -rf, force push, DROP TABLE) and asks you Proceed or Cancel first
guard-actions
hernandezsanti/claude-code-mods
Saves GitHub Actions minutes: blocks gh run watch/rerun and gh pr checks --watch, and warns when a second PR is opened in the session.
gcloud-guard
davidho27941/cockpit
Holds gcloud and gsutil commands that would create, change or delete cloud resources, shows the account, project, location and the current state of the targets, and asks you to Proceed or Cancel.
guardrails-challenge
scaso01/claude-risk-guardrails
Effective challenge: hold answers to evidence under pushback, and check agents' commit claims against git.
clef-guard
williamchen0606/claude-mods
Has Cloudflare's Clef decision model judge each Bash, Write, Edit and WebFetch call (risk, kind of risk, whether it is read-only, whether it fits your request), asks you itself before risky or always-ask operations, and can approve plain reads for you.
jev-tool-gate
m2ai-portfolio/claude-mods
Log-only Jev judgment of risky tool calls (destructive? requested by fetched content?). Never changes a decision; hosted calls off by default.
Browse the most popular Claude Code mods, all guard & safety mods, or the skills and MCP server directories.