537 security Claude Code mods, most popular first. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| model-router Routes each subagent to the cheapest Claude model and effort that can do its task, judged by TypeSafe Jev. On | – | Review before installing |
| leakstop Stops secrets from leaking before they are written, printed or committed to git. | – | Review before installing |
| usage-guard Winds sessions and subagents down before the 5-hour or 7-day subscription limit: one wind-down note per band, | – | Review before installing |
| client-mask Mask client names, personal data and secrets before anything leaves this machine; keep the list private and le | – | High risk |
| git-guard Keep Claude out of your git history: no co-author trailer, no PR footer, and no push of a commit that carries | – | Review before installing |
| token-meter This session's token use, Claude vs local LLMs: status line, live spinner count, and a /tokens pane with a Pac | – | Low risk |
| context-guard Context window fill in the status line, with a heads-up before it runs out | – | Low risk |
| ather-automata Ather Automata: what needs you and what is next in every S2 session and web app repository (Plan, Build, Prove | – | High risk |
| workspace-guard Blocks reading .gitignore and creating venvs or heavy media inside the Syncthing-synced claude-code workspace. | – | Low risk |
| migration-guard Makes Claude ask before it touches your database migrations or runs destructive SQL, with the risk and what it | – | Low risk |
| secchain-mask Hides SecChain's secret values in prompts, tool results and instructions before the model reads them, through | – | Review before installing |
| watch-tower Watch Tower: a pane to follow a Claude Code session at a glance (subagents and what they are doing, context, c | – | High risk |
| session-fleet Fleet board of live sessions, a needs-you beacon, and a worktree claim guard, shared across sessions | – | Review before installing |
| airlock Routes supported project edits into a Git worktree for review, accept or reject. Worktree routing is not a fil | – | Review before installing |
| code-modernization Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, th | – | Review before installing |
| plus All claudecode-plus-mod Mods in one install: prompt-shield, cache-guard, human-tone, clear-intent and agent-ch | – | Review before installing |
| cache-guard Stabilize the prompt-cache prefix, audit compaction fidelity, and report real cache hit numbers per turn. | – | Review before installing |
| prompt-shield Strip invisible fingerprint characters from outgoing prompts and audit what the model actually receives. | – | Review before installing |
| native-guard Recusa edição de arquivo por sed -i / heredoc / python no shell e manda usar Edit e Write | – | Low risk |
| rainbow-prompt Colors the prompt box as you type: ticket ids, paths, links, rainbow words, and a red warning on anything that | – | Low risk |
| pii-mask 個資去識別化：把手機、身分證、Email、地址等換成代號再送給模型，對照表只留在本機；/pii 開關與查看 | – | Review before installing |
| secret-guard 金鑰守門：遮蔽 prompt 和工具輸出裡的 API key，並擋下讀寫 .env、私鑰這類檔案；/guard 看狀態 | – | Low risk |
| sand-falling A falling-sand sandbox in a side pane while Claude works | – | Low risk |
| usage-guard Claude の5時間の使用量の上限を status line に出し、しきい値を超えたらツールとプロンプトを止める mod | – | Low risk |
| guard Pauses risky shell commands (rm -rf, force push, DROP TABLE) and asks you Proceed or Cancel first | – | Low risk |
| quota-guard Compacts before the 5-hour/weekly usage limit is hit, pauses until it resets, then resumes the task automatica | – | Low risk |
| diagram-preview Show Obsidian vault diagrams (.canvas, Excalidraw, draw.io, BPMN) as SVG in Claude Desktop side panes, with la | – | Review before installing |
| assertion-guardian Blocks edits that weaken tests to fake a green run: removed or loosened assertions, added skips, deleted cases | – | Low risk |
| secret-sentry Two-way secret scrubbing: redacts credentials before the model sees them and blocks writing them into tracked | – | Review before installing |
| cortex-cockpit The harness cockpit, a viewer: the phase every agent is in (PHASES panel, and main and the running agents in t | – | High risk |
| cortex-guard Two rules no settings hook enforces, refused at the tool call: wiki pages and their generated ADR mirrors are | – | Review before installing |
| zetetic-autopilot Automatic effort and model, and a quota that limits how many agents run, not how well one runs. Every request | – | Review before installing |
| pixlings A tiny pixel creature that lives above your Claude Code prompt. It counts down your prompt cache and guards it | – | Review before installing |
| blast-radius Holds risky shell commands (rm -rf, git reset --hard, git clean, force push, migrations) and shows what they w | – | Low risk |
| cockpit A one-line band above the prompt and a roomy Cockpit panel (prompt-cache countdown, context, plan limits, cost | – | High risk |
| haunted-repo Delete a file and its ghost haunts your prompt, whispering fragments of its lost code until you restore it. Se | – | Low risk |
| yujie 雨姐陪你写代码：像素工位面板、状态栏、提示条，报错会黑脸，rm -rf 会被拦下，还能开东北话唠嗑模式 | – | Low risk |
| git-guard Denies a Bash git command that loses work Claude Code does not already guard: git branch -D, a force push to m | – | Low risk |
| kill-guard Denies a Bash command that stops processes by name or by port, because it can also stop another checkout's dev | – | Low risk |
| prose-guard Blocks em dashes in edits, shell commands and replies, and British spellings in prose files, commit messages a | – | Low risk |
| gsd-whisper Shows you what gsd-core's hooks quietly tell the agent: context warnings, guard advice and guard denials. | – | Low risk |
| shell-edit-guard Blocks Bash commands that write files (inline scripts, sed -i, redirects, tee) and points the model at Edit/Wr | – | Review before installing |
| blast-radius Holds risky shell commands (rm -rf, git reset --hard, git clean, force push, migrations) and shows what they w | – | Review before installing |
| gcloud-guard Holds gcloud and gsutil commands that would create, change or delete cloud resources, shows the account, proje | – | Review before installing |
| secret-guard Keeps API keys, cloud credentials and other secrets out of what is sent to the model: every text that enters t | – | Review before installing |
| skill-audit Audit trail of skill invocations and file changes for Claude Code and Codex sessions | – | Low risk |
| clauget The scale, then the diet — and the diet only where the scale says it pays. Each model request inside a turn st | – | High risk |
| leaks Notices personal identifiers and secrets that reach the model, lists them per project, and can redact or block | – | Review before installing |
| flowpane Side panel for Claude Code: pin rules the model keeps through /compact, flip live guards (read-only, no push, | – | Low risk |
| claudekeys Session-scoped, encrypted, read-only secrets that Claude uses in commands as {{ck:NAME}} without ever seeing t | – | Review before installing |
| auth-guard Spots an expired CLI login in tool output and offers a Login button that signs in and retries. | – | Review before installing |
| arrester After a hook, deny rule, or auto mode blocks a tool call, Arrester stops later calls that reach the same resul | – | Low risk |
| sandbox-tuner Explains each Claude Code sandbox block in plain words and turns recurring blocks into reviewed, one-press, un | – | Review before installing |
| x-mod-guard reads every Bash call, fork spawn and Write before it runs: a Write over a tracked file the session never read | – | Review before installing |
| x-mod-redact keeps secrets out of every transcript: api keys, tokens and private keys read as a stable placeholder in every | – | Low risk |
| guardrails-lite Pattern-based checks that deny .env reads, git force pushes and rm -rf on / or your home folder before Claude | – | Low risk |
| guardia-llaves Tapa las llaves y contrasenas antes de que Claude las vea, y le prohibe imprimir archivos de secretos. | – | Low risk |
| collision-guard Warns when another Claude session on the same repo already edited the file being changed, or claimed the same | – | Review before installing |
| grammar-guard Grammar fixes for prompts you type or dictate: optional auto-fix on send (LanguageTool rules or a light Haiku | – | Review before installing |
| clawd-cartoons A live cartoon under the spinner: Clawd acts out and narrates each step of the agent's work, drawn by Sonnet a | – | Low risk |
| sdd-analyze-gate SDD capability 04: semantic Analyze findings, read-only run guard (best effort), Analyze result state. Executi | – | Low risk |
| sensitive-guard Garde-fou : suspend les commandes Bash sensibles et demande Proceed / Cancel dans un panneau avant exécution. | – | Low risk |
| context-guard Context runway gauge: warns before your context line with Compact, Hand off and Snooze | – | Low risk |
| block-explainer When one of this kit's guard hooks blocks a tool call, shows one plain line (what it means, what to do instead | – | Low risk |
| secret-vault Collects API keys and other secrets in a private modal and writes them straight to their target file, redactin | – | Review before installing |
| tap Tap: a live recorder on the hook chain, with a secret guard | – | Low risk |
| deid-guard De-identifies personal data in tabular files (CSV, TSV, XLSX, JSON) before anything reaches the model. Korean | – | Low risk |
| secret-guard Keeps API keys, tokens and passwords out of the transcript, tool output, files, commits, PRs and issues. | – | Review before installing |
| blast-radius Catches risky shell commands (rm -rf, git reset --hard, force push, ...) before they run, forces a permission | – | Low risk |
| bash-guard Blocks catastrophic Bash commands; holds risky ones (rm -r, git reset --hard, git clean, force push, migration | – | Low risk |
| recording-mode /rec przed nagrywaniem: maskuje sekrety, dane osobowe i kwoty na ekranie i zamyka prywatne pliki (/rec on|stri | – | Review before installing |
| autocommit Turns every turn Claude takes into a clean git commit: only the files that turn changed, a Conventional Commit | – | Review before installing |
| freio-de-mao Freio de mão: antes de um comando que apaga ou descarta (rm -rf, git reset --hard, git clean, push --force, pk | – | Low risk |
| guarda-colisao Guarda de colisão: antes de editar, avisa se o arquivo foi mudado fora desta sessão (outra sessão, você no edi | – | Low risk |
| marcador-sessao Marcadores de sessão: guarda um ponto da conversa com nome e resumo, e cola o resumo no prompt para retomar (/ | – | Low risk |
| command-guard Refuses shell commands a project's .claude/command-guards.json rules out, for the main loop and every subagent | – | Low risk |
| commit-guard Never commits docs/superpowers, never pushes unless you said push, asks before committing on main/staging/prod | – | High risk |
| rm-to-trash Rewrites rm into macOS trash so deletes are recoverable and stop hitting the rm deny rule | – | Low risk |
| safety-net Blocks dangerous shell commands (rm -rf, force push, hard reset, DROP TABLE) | – | Low risk |
| cockpit Claude Code status line plugin: context %, session cost, budget, context and rate-limit alerts, /cockpit dashb | – | Review before installing |
| blast-radius [mod] Holds risky shell commands (rm -rf, git reset --hard, force push, git clean, migrations, find -delete, x | – | Low risk |
| sdlc-workflow One command — `/wf` (`$wf` under Codex), the single SDLC entry point for Claude Code and Codex from one plugin | – | High risk |
| aeo-audit Audits a URL for AI answer engines (ChatGPT search, Perplexity, Google AI Overviews, Copilot, Claude): crawler | – | Review before installing |
| repo-sentry Status line with business, repo, branch and dirty count, plus a warning band when on main or a secret file is | – | Low risk |
| pii-shield Replace protected people's names, Taiwan ID numbers, phone numbers and emails with placeholders before the mod | – | Low risk |
| secret-redactor Keeps secrets, email addresses and IP addresses out of the session transcript: swaps each one for a stable pla | – | Low risk |
| brigade Coordinate a fleet of cheap parallel coding agents from any ticket source (Notion, ClickUp, Obsidian vault boa | – | Low risk |
| block-destructive-commands Denies Bash commands that match destructive patterns (recursive rm on roots, force push, hard reset, destructi | – | Low risk |
| redact Rewrites sensitive data (emails, IPs, credentials, addresses) out of what enters the model context | – | Low risk |
| now-doing A briefing card above the prompt: the session's state and how long it has held, its mission, the open asks it | – | Low risk |
| pkexec-guard Routes `sudo` in Bash calls to a password prompt the person can answer: pkexec on a Linux desktop, an osascrip | – | Review before installing |
| autopilot Works through a GOALS.md goal tree turn after turn, with locked checks, its own check verdicts, lessons that c | – | High risk |
| guardian Pide confirmación con botones antes de que Claude ejecute comandos peligrosos (rm -rf, git push --force, git r | – | Low risk |
| cache-guard Keeps the prompt cache warm while you are away, asks before a prompt that would re-cache a large conversation, | – | High risk |
| shell-guard Blocks shell commands that wipe your home folder, the project, disks, protected branches or databases, and sna | – | Review before installing |
| mellu A stack-agnostic harness that makes Claude Code work well on any project: persistent state, an enforced verify | – | Review before installing |
| blast-radius Holds risky shell commands (rm -rf, Remove-Item -Recurse, git reset --hard, git clean, force push, migrations) | – | Review before installing |
| safety-net Blocks catastrophic shell commands and asks before risky ones or edits to secret files. | – | Low risk |
| secrets-redactor Scrubs API keys, tokens and private keys from prompts and tool output before the model sees them. | – | Low risk |
| token-keeper Cache Keeper by Nate Herk, cut down to token economics: cache stats, a dollar-based cold-send guard, keep warm | – | Review before installing |