Claude Code mod
leaks
Notices personal identifiers and secrets that reach the model, lists them per project, and can redact or block them, with modes and ignore lists per folder
Install
/plugin marketplace add devsomelife/somelife-claude-mods
/plugin install leaks@somelife-claude-modsMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: changes config, writes the prompt box, reads files, reads env vars, reads settings, reads mod state, persists state, draws
- Sees
- every tool call, every prompt
- Draws in
Pane- Hooks
session.startsession.endconfig.setcommand.runtool.callprompt.submitsession.appendmodel.completemodel.forkui.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
- devsomelife/somelife-claude-mods
- Folder
plugins/leaks- Marketplace
somelife-claude-mods- Author
- Greg
- Last updated
- 23 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is leaks?
Notices personal identifiers and secrets that reach the model, lists them per project, and can redact or block them, with modes and ignore lists per folder It is a mod for Claude Code, from devsomelife/somelife-claude-mods on GitHub.
What can the leaks mod access?
Its widest reach is "writes or runs" (changes config, writes the prompt box, reads files, reads env vars, reads settings, reads mod state, persists state, draws). It sees every tool call, every prompt. It draws in Pane. Like any mod, it runs with your permissions.
How do I install leaks?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add devsomelife/somelife-claude-mods and then /plugin install leaks@somelife-claude-mods.
More guard & safety mods
keepwarm
luwux/keepwarm
Idle-session guard for Claude Code's 1-hour prompt cache (macOS): about 50 idle minutes after the last turn of a large session it notifies you, optionally after a cache-read fork judges whether to compact, keep warm or leave it; every request and change it makes is audited. Derived from cache-tax (MIT, Karan Bansal).
mask-that-pass
myveroai/mask-that-pass
Masks credentials in tool output (URL passwords, *_TOKEN / *_SECRET / *_PASSWORD values, API keys, bearer tokens, private keys) before Claude or the transcript sees them. No network, files or processes.
jev-guard
klefix/claude-code-mods
Asks Jev whether a prompt leaves a choice open and whether each edit stays within what the user approved
mellu
kotaraa09/easyClaude
A stack-agnostic harness that makes Claude Code work well on any project: persistent state, an enforced verify gate, guardrails, and a token-frugal escape hatch.
jev
yinjs/claude-jev
Jev answers clear permission prompts, flags prompt injection in fetched content, checks done claims, nudges large or vague requests, and routes effort and models without trading away the prompt cache.
merge-watch
b00y0h/merge-watch
A panel that groups every open merge request or pull request by whether it can merge, shows failing jobs, and can retry or merge after you confirm. Refreshed once a minute.
Browse the most popular Claude Code mods, all guard & safety mods, or the skills and MCP server directories.