Claude Code mod
prime-guard
Helps reduce personal data sent to Claude: redacts detected Thai and international personal data before sending and masks it on screen. Detection runs locally and the mod makes no network calls of its own; the redacted conversation is still sent to your configured model provider (Anthropic by default). Also keeps secret files (.env, keys) closed to the file tools and shell, and refuses a tool call that would send a credential or personal data off the machine. It also hides who and where: the user's account and machine names (learned from the machine), profile paths, host and ssh-config names, LAN URLs, MAC addresses, SIDs, SSH key lines and private key blocks. Before a git push, gh release or package publish it reads the commits that would go out and refuses when they hold personal data or secrets (it names the file and the kind, never the value). `/prime-guard git on` adds global git hooks that scan every push on the machine, inside or outside Claude Code. Images and files are not read: it warns, or blocks in block mode. Best effort, not legal advice.
Install
/plugin marketplace add settanun-prime/prime-studio-mods
/plugin install prime-guard@prime-studio-modsMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: runs processes, reads files, reads mod state, draws
- Sees
- every prompt, the system prompt, every tool call
- Draws in
AssistantMessageUserMessage- Hooks
session.startcommand.runprompt.submitsession.appendprompt.attachmentprompt.contexttool.callui.render
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
- settanun-prime/prime-studio-mods
- Folder
prime-guard- Marketplace
prime-studio-mods- Author
- settanun-prime (Prime Studio)
- License
- MIT
- Last updated
- 29 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is prime-guard?
Helps reduce personal data sent to Claude: redacts detected Thai and international personal data before sending and masks it on screen. Detection runs locally and the mod makes no network calls of its own; the redacted conversation is still sent to your configured model provider (Anthropic by default). Also keeps secret files (.env, keys) closed to the file tools and shell, and refuses a tool call that would send a credential or personal data off the machine. It also hides who and where: the user's account and machine names (learned from the machine), profile paths, host and ssh-config names, LAN URLs, MAC addresses, SIDs, SSH key lines and private key blocks. Before a git push, gh release or package publish it reads the commits that would go out and refuses when they hold personal data or secrets (it names the file and the kind, never the value). `/prime-guard git on` adds global git hooks that scan every push on the machine, inside or outside Claude Code. Images and files are not read: it warns, or blocks in block mode. Best effort, not legal advice. It is a mod for Claude Code, from settanun-prime/prime-studio-mods on GitHub.
What can the prime-guard mod access?
Its widest reach is "writes or runs" (runs processes, reads files, reads mod state, draws). It sees every prompt, the system prompt, every tool call. It draws in AssistantMessage, UserMessage. Like any mod, it runs with your permissions.
How do I install prime-guard?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add settanun-prime/prime-studio-mods and then /plugin install prime-guard@prime-studio-mods.
More guard & safety mods
port-guard
colorfield/claude-port-guard
Stops Claude from killing, or running E2E tests against, another project's local dev server
prod-guard
blackironj/claude-mods
Confirm production kubectl/helm/IAM mutations before they run (also inside aws-vault exec), require an explicit kube context, and hand interactive aws-vault commands to you
polish
HuliLulu46/cc-prompt-polish
/polish <text>: rewrites it into a clearer prompt and leaves the result in the input box for you to confirm
prompt-pilot
Fox1304/FT_Claude_PromptUpgrader
Picks the model and effort for each prompt (you confirm), and upgrades substantial prompts through a short question panel before they run
pkexec-guard
joshkerr/claude-mods
Routes `sudo` in Bash calls to a password prompt the person can answer: pkexec on a Linux desktop, an osascript administrator dialog on macOS, and Windows sudo's UAC prompt on Windows.
prompt-redact
ezoushen/claude-mods
Replaces secrets and credentials with stable placeholders inside Claude Code before the model or the session file ever sees them — prompts, tool results and replies, plus attachments and compaction summaries where the platform lets this mod see them — and restores real values only in Edit/Write/NotebookEdit arguments. 220-rule corpus plus checksum detectors, a benign-shape allowlist, fail-closed scanning, a /redact pane and a redacted-values skill. No network, no subprocess, no model call.
Browse the most popular Claude Code mods, all guard & safety mods, or the skills and MCP server directories.