70 mods for Claude Code security tools, ordered by the votes people give them on ClaudeMods. A good place to start: sec-default,ruflo-market-data or ruflo-migrations.
Each entry links to its original repository or post, and shows how to install it.
70
Claude Code mod that shows live WHOOP heart rate in the status line and blocks risky Bash commands while your heart rate is over a configurable limit.
Anthropic introduces Mods for Claude Code: packaged as TypeScript modules within plugins, they can hook into events such as tool calls, prompts, turns, slash commands, and UI rendering to rewrite or intercept them; installed via /plugin, requires version 2.1.287+. Official examples include
A Claude Code mod that makes Claude ask before it touches your database migrations.
Masks secrets (API keys, tokens, passwords, private keys) in the Claude Code transcript; hover a masked value to reveal it.
Claude Code 2.1.287 is released, including 106 CLI changes, adding Claude Mods plugin deep behavior modifications, a caretaker plugin, and multiple fixes and improvements.
A Claude Code plugin that scans every text entering a conversation — prompts, tool results, subagent rows — and replaces detected API keys, cloud credentials and other secrets with meaningful placeholders before they reach the model.
One key for 140+ AI models
bazaarlink.aiVisit sponsor ↗
Prevent delegated agents from changing the repository's Claude settings files.
Track what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗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.
A look-only mode for someone else at your PC: Claude can read and answer, but cannot change anything until you unlock it.
The author released the Jev Permission Gate extension, replacing Claude Code's auto mode classifier with Jev. In testing, permission checks were about 2x faster, with median latency dropping from 329ms to 164ms.
Holds a risky shell command before Claude runs it, works out what it would change, and opens a pane with **Proceed** and **Cancel**. Cancel refuses the command and tells Claude why, so it knows nothing ran.
Side-effects ledger (/ledger) with a hold on production SQL writes, and a waiting-on tracker for background work
