Claude Code mod
quarantine
Wraps web, MCP and third-party tool output as untrusted data and defangs prompt-injection lines before the model reads them
Install
git clone https://github.com/ccdwyer/quarantine.git
claude --plugin-dir ./quarantine/.The repo has no marketplace file, so load the plugin folder directly with --plugin-dir.
What it can access
- Reach
- L1Reads: reads env vars, reads mod state, draws
- Sees
- every tool call
- Hooks
session.startcommand.runtool.callsession.append
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
- ccdwyer/quarantine
- Folder
.- Author
- Chris Dwyer
- License
- MIT
- Last updated
- 2 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is quarantine?
Wraps web, MCP and third-party tool output as untrusted data and defangs prompt-injection lines before the model reads them It is a mod for Claude Code, from ccdwyer/quarantine on GitHub.
What can the quarantine mod access?
Its widest reach is "reads" (reads env vars, reads mod state, draws). It sees every tool call. Like any mod, it runs with your permissions.
How do I install quarantine?
Clone ccdwyer/quarantine and start Claude Code with --plugin-dir pointing at the mod's folder (.).
More guard & safety mods
push-guard
kk5190/claude-code-mods
Blocks git push and gh pr create until you confirm the commits, their authors and the diff size, with a side pane of the last check
query-guard
nu0ma/query-guard
Asks before Claude runs destructive or slow-looking SQL through a DB CLI: DELETE, UPDATE without WHERE, DROP, TRUNCATE, full scans and cartesian joins.
publish-guard
seanyyoo/claude-code-mods
Stops Claude from typing private terms into the browser or writing them into your publishing files, and keeps a log of what it blocked
quick-reply
ivanzoid/cc-quick-reply-mod
Reply to parts of an answer: comment on blocks inline, or quote a selection with > on an empty prompt line
protocol-guard
Mar5929/claude-toolkit
Required workflow checks with Claude Code function hooks. Refuses a knowledge-file write, or a memory-service save in external memory mode, until knowledge-save is open, refuses hand edits to generated indexes, refuses a pull request, close or merge until knowledge-save (and the work or merge-and-clean-up skill) is open, and holds a final reply once when working memory or the index rebuild and checker did not follow the change. Fact checks only: no model call and no reading of the agent's words. Runs only when CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1.
roclaude
vinkdc/roclaude
Roblox Studio safety layer for Claude Code (Studio MCP): RemoteEvent security audit, undo, Team Create protection, a confirmation before destructive Luau, and a live activity view that replays every change.
Browse the most popular Claude Code mods, all guard & safety mods, or the skills and MCP server directories.