537 security Claude Code mods, most popular first. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| claw-memory Claw mod: injects your SOUL.md, MEMORY.md and open tasks into every session automatically, gives Claude rememb | – | High risk |
| claw-telegram Claw mod: talk to Claw from your phone. Messages from your own Telegram chat start a turn, the answer is sent | – | High risk |
| masque-secrets Masks the values from ~/.claude/secrets/*.env in everything the model reads | – | Low risk |
| delete-guard Holds recursive deletes (rm -rf, Remove-Item -Recurse, rmdir /s, git clean -f), shows what would go, and offer | – | Low risk |
| eol-guard Keeps files' git line endings (CRLF/LF) after Claude's edits and shell commands, and stops prettier checks fai | – | Review before installing |
| secret-guard Blocks git commit and git push from Claude when the change carries a secret file or a credential-shaped line, | – | Review before installing |
| klyth A model extension router for Claude Code: keep your Claude subscription connected while routing selected model | – | High risk |
| ask-on-auto-deny When auto mode's classifier blocks a tool call, asks you above the prompt and lets you allow that exact call o | – | Low risk |
| guardrail Blocks hook-skipping git commands and live data operations that have no successful dry run first; you can allo | – | Low risk |
| security-guard Checks git commit and PR commands against the rules in your own and the project's CLAUDE.md files | – | Low risk |
| vibe-guard Companion to vibe-wise: offers learning mode once per project, holds Claude's edits while a checkpoint waits o | – | Review before installing |
| act-now-guard 計画フェーズの要らない依頼で EnterPlanMode や Plan エージェントに入ろうとしたら止め、すぐ実装に着手させる function hook | – | Review before installing |
| approval-guard AskUserQuestion で得た承認と gh の不可逆コマンド（レビュー投稿・close・merge）の宛先を照合し、force push の確認と PR 本文の Closes キーワードの確認も行う functi | – | Low risk |
| session-guard 同じ作業ディレクトリで動く別の Claude Code セッションを検出し、workspace への移行を促す function hook | – | Low risk |
| blast-radius-plus Hält riskante Shell-Befehle an (rm -rf, git reset --hard, Force-Push, Migrationen) und zeigt dir vorher, was s | – | Low risk |
| branch-guard Asks the user before Edit/Write/NotebookEdit changes a file of a git repo whose current branch is main or mast | – | Low risk |
| commit-size-guard Asks before a git commit or git add includes large files, big binaries or build/release artifacts (dmg, zip, a | – | Low risk |
| doc-sync-guard Warns above the prompt when a turn did not update COMMANDS.md, or changed code without updating CHANGES.md | – | Review before installing |
| env-protect Asks the user before Claude reads secret files (.env, private keys, .netrc, .npmrc, .aws/credentials, keychain | – | Low risk |
| french-guard Toasts when the last answer looks English or is French written without accents; /french-guard off|on|status | – | Low risk |
| main-guard Refuses git pushes to main/master, force pushes, tag creation and GitHub releases unless the person allows the | – | Low risk |
| rm-guard Asks the user before destructive Bash commands run: rm -rf, git reset --hard, git clean -f, discarding all cha | – | Low risk |
| secret-shield Refuses Write, Edit and Bash calls that contain secret-looking values (API keys, tokens, private keys) | – | Low risk |
| sparkle-guard Protects the Sparkle EdDSA signing key: denies deleting it from the keychain, asks before generate_keys may cr | – | Low risk |
| detector-secretos Revisa lo que Claude escribe y lo que va a commitear, y se detiene si encuentra API keys, tokens, llaves priva | – | Review before installing |
| guardia-produccion Detiene comandos riesgosos (deploys, migraciones, borrados, force push, kubectl en prod) y pide confirmación; | – | Review before installing |
| roclaude Roblox Studio safety layer for Claude Code (Studio MCP): RemoteEvent security audit, undo, Team Create protect | – | Review before installing |
| guard Holds shell commands that delete folders or overwrite work | – | Low risk |
| guard-first-try Holds a shell command that deletes a whole folder (first try, has a hole) | – | Low risk |
| clef-guard Has Cloudflare's Clef decision model judge each Bash, Write, Edit and WebFetch call (risk, kind of risk, wheth | – | Review before installing |
| code-modernization Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, th | – | Review before installing |
| hover-reveal Desktop app: masks API keys, tokens and passwords in replies and tool output; hover to show them | – | Low risk |
| blast-radius Holds risky Bash (migrations, force-push, DROP, hard reset, rm -rf, deleting .env) and shows a dry-run pane wi | – | Low risk |
| shell-guard Windows shell guard: fixes backslash drive paths in Bash, blocks quote-eating node -e / heredoc patterns, and | – | Low risk |
| repo-guard Blocks destructive git commands and asks before Claude first edits a repo other than the session's own | – | Low risk |
| sdk-sync After an SDK release (v* tag): /release-check gathers what changed and asks Claude for a read-only audit of th | – | Review before installing |
| command-guard Safety net for dangerous commands: before rm -r, git push --force, reset --hard and the like, shows what would | – | Review before installing |