Claude Code mod
guardian
GUARDIAN: executable policy that protects lab/demos/protected/** from Write/Edit/Bash, whatever CLAUDE.md says
Install
git clone https://github.com/ucsandman/Agnostic-AI.git
claude --plugin-dir ./Agnostic-AI/labs/claude-mods/lab/demos/guardianThe repo has no marketplace file, so load the plugin folder directly with --plugin-dir.
What it can access
- Reach
- L0Draws and remembers: draws
- Sees
- Write|Edit|NotebookEdit|Bash calls
- Hooks
session.starttool.calltool.check
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
- ucsandman/Agnostic-AI
- Folder
labs/claude-mods/lab/demos/guardian- License
- MIT
- Last updated
- 2 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is guardian?
GUARDIAN: executable policy that protects lab/demos/protected/** from Write/Edit/Bash, whatever CLAUDE.md says It is a mod for Claude Code, from ucsandman/Agnostic-AI on GitHub.
What can the guardian mod access?
Its widest reach is "draws and remembers" (draws). It sees Write|Edit|NotebookEdit|Bash calls. Like any mod, it runs with your permissions.
How do I install guardian?
Clone ucsandman/Agnostic-AI and start Claude Code with --plugin-dir pointing at the mod's folder (labs/claude-mods/lab/demos/guardian).
Is guardian popular?
ucsandman/Agnostic-AI has 24 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 2 October 2026.
More guard & safety mods
shared-file-guard
6mutlumehmet/claude-plugins
Refuses a shell write to a shared file (STATUS.md, CLAUDE.md, MEMORY.md, or the files you name) that this session has not read, or that another session changed since
reminder-log
3schreibse/claude-code-mods
Tallies the reminders Claude Code injects for the model, per session; drops the token counter and repeated attribution blocks; /reminders prints the last 30 days
rehearsal-widget
4oMaN-Rod/claude-code-widgets
Which of the commands and edits Claude has made in this project would stop for permission or be refused right now, asked of the engine's own permission check without running anything
blast-guard
RobGruhl/claude-mods
DURING the turn: refuses destructive shell commands, tidies the rest, and pins Explore subagents to Haiku
injection-guard
4Singh-AP/awesome-claude-mods
Defuses prompt injection in tool output: strips invisible Unicode that hides text from you but not from the model, and flags web pages, files and command output that carry instructions aimed at Claude.
claw-guard
threesil/claude-mods
Claw mod: asks for your OK before any connector action that sends, deletes, pays, publishes or shares (fails closed, also when nobody is there to answer), and flags prompt-injection text inside emails, pages and files.
Browse the most popular Claude Code mods, all guard & safety mods, or the skills and MCP server directories.