537 security Claude Code mods, most popular first. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| burnrate Full mod: live limits band above the prompt plus the guard (cache watchdog and limit brake). | 1 ★ | Low risk |
| limit-guard Warns when the prompt cache is invalidated; near the 5h cap blocks subagents and wide scans and asks Claude fo | 1 ★ | Low risk |
| jev-suite Branch git acima do prompt e juízos do Jev (TypeSafe): guarda de comandos, roteador de esforço, detector de se | 1 ★ | High risk |
| secrets Hand Claude an API token without it reading the value: you type it into a field above the prompt, Claude uses | 1 ★ | Review before installing |
| secrets Claude asks for API keys in a masked field above the prompt, saves them to the macOS Keychain, Linux keyring o | 1 ★ | Review before installing |
| secret-mask Masks secrets (API keys, tokens, passwords, private keys) in the transcript; hover a masked value to reveal it | 1 ★ | Low risk |
| bouncer Bouncer for Claude Code: enforce condition-based markdown guardrail rules on tool calls — deny or annotate any | 1 ★ | Low risk |
| trip-guard Course example mod: denies edits to the generated trips.csv, shows the last failed command in the status line, | 1 ★ | Low risk |
| floatee Your Floatee backlog inside Claude Code: the open todos above the prompt (or in a side pane), one button to pr | 1 ★ | High risk |
| chottag Drive chottag (c-hottag) from Claude Code: switch the serving account, set the remote account, log accounts in | 1 ★ | Review before installing |
| workflow-toolbox Toolbox for Claude Code's Workflow tool — author deterministic multi-agent workflow scripts (workflow-composer | 1 ★ | Review before installing |
| pilot-guard Author, scaffold, and debug multi-agent workflows for Claude Code's Workflow tool — a skills-only plugin plus | 1 ★ | Review before installing |
| wt-secret-guard Function-hook secret scrubber for prompts, assistant text, tool results, and raw outbound tool inputs | 1 ★ | High risk |
| vault-jot Capture ideas, takes, and reading items into an Obsidian vault inbox from any Claude Code session | 1 ★ | High risk |
| session-band Prompt cache status band (c / ctx / rwc / sc / plan limits) with hover help, cold-send guard, keep-warm, /boar | 1 ★ | High risk |
| delete-guard | 1 ★ | Review before installing |
| wt-panel A /wt pane listing the repository's git worktrees: status, changes, copy path, open in VS Code, guarded delete | 1 ★ | Low risk |
| cinemetric Claude skills for your Plex server. Read-only reports on your media and server, plus mods for Claude Code: a r | 1 ★ | Review before installing |
| effort-router Routes each turn's effort from your prompt: git housekeeping replies ("merged", "commit and push", "push it") | 1 ★ | Review before installing |
| machine-guard Memory, swap, GPU and the CPU cores macOS is using on the status line, and a machine_status tool for Claude; r | 1 ★ | Review before installing |
| secret-guard Holds back a prompt that looks like it carries a secret (API keys, tokens, access-key pairs, private keys, pas | 1 ★ | Review before installing |
| branch-guard Stops Claude from editing files or running mutating git commands on main or master, and points it at a worktre | 1 ★ | Low risk |
| path-guard Blocks Write, Edit and MultiEdit calls that target a path outside the project root or inside .git, plus option | 1 ★ | Low risk |
| secret-guard Blocks Write, Edit and Bash calls that would put an API key, token or private key into a file or command. | 1 ★ | Low risk |
| sensitive-file-guard Blocks Read, Write, Edit, Grep, Glob and Bash calls that touch .env files, private keys and credential stores. | 1 ★ | Low risk |
| test-guard Blocks edits that make tests pass by weakening them: new skip/only markers, fewer assertions, a gutted test fi | 1 ★ | Low risk |
| redact Redacts secrets and PII from every row Claude Code stores, before the model reads it and before the transcript | 1 ★ | Low risk |
| unity-tools Unity no Claude Code: erros de compilação no contexto, painel de testes, build do servidor e guardas de arquiv | 1 ★ | Review before installing |
| guard Blocks .env access and destructive shell commands, with a red line saying why | 1 ★ | Low risk |
| secret-guard Keeps secrets out of Claude's context: gitleaks scans every tool output, prompt and attachment before the mode | 1 ★ | Review before installing |
| redact Local credential protection. Host failure qualifications and coverage limitations apply. | 1 ★ | Review before installing |
| token-weather A live forecast of the context window above the prompt, with the 5-hour and 7-day usage windows, the session c | 1 ★ | Low risk |
| smartworkbench SmartWorkbench for Claude Code: set the task contract, pin context, guard tool calls and verify the result | 1 ★ | High risk |
| hig Apple's Human Interface Guidelines inside Claude Code: Claude works with them in mind, each edit is checked ag | 1 ★ | Review before installing |
| lens Puts tsc, linter and secret-scan diagnostics in the result of every Edit and Write, so Claude fixes what it br | 1 ★ | Low risk |
| a11y-guard Flags accessibility misses as Claude writes UI: images without alt, unlabeled buttons, clickable divs. | 1 ★ | Low risk |
| audit-trail Writes every action Claude takes to an append-only JSONL audit log. | 1 ★ | Review before installing |
| big-read-guard Stops full reads of huge files and nudges toward offset/limit or grep. | 1 ★ | Low risk |
| copyright-guard Flags pasted code that carries someone else's license or copyright header. | 1 ★ | Low risk |
| crypto-guard Flags weak cryptography: MD5 or SHA1 for passwords, Math.random for tokens, ECB mode, hard-coded IVs. | 1 ★ | Low risk |
| css-token-guard Flags hard-coded hex colors and pixel values where your design tokens should be used. | 1 ★ | Low risk |
| curl-pipe-guard Blocks piping downloaded scripts straight into a shell. | 1 ★ | Low risk |
| disk-guard Warns when the disk is nearly full before builds, installs and docker pulls. | 1 ★ | Low risk |
| docker-prune-guard Blocks docker system prune -a --volumes and volume deletion that can wipe local databases. | 1 ★ | Low risk |
| env-guard Protects .env files, SSH keys and credential stores from being read or modified. | 1 ★ | Low risk |
| force-push-guard Forbids force-pushing to protected branches and suggests --force-with-lease. | 1 ★ | Low risk |
| gitignore-guard Warns before node_modules, build output, OS junk or huge files get staged. | 1 ★ | Low risk |
| guardian One security policy for every guard mod — permissive, standard or strict — plus a project safety score. | 1 ★ | Review before installing |
| i18n-guard Flags hard-coded user-facing strings in UI components. | 1 ★ | Low risk |
| leak-hint Flags event listeners, intervals and subscriptions created without cleanup. | 1 ★ | Low risk |
| link-vault Collects every URL from the conversation into one list. | 1 ★ | Low risk |
| lockfile-guard Prevents hand-editing lockfiles; they must change through the package manager. | 1 ★ | Low risk |
| migration-guard Prevents editing database migrations that already exist; write a new one instead. | 1 ★ | Low risk |
| next-guard Flags missing or needless "use client" and server-only imports leaking into client components in Next.js. | 1 ★ | Low risk |
| pii-in-logs Flags log statements that print emails, passwords, tokens or other personal data. | 1 ★ | Low risk |
| prod-guard Stops production-affecting commands (terraform apply, kubectl on prod, DROP TABLE) unless explicitly allowed. | 1 ★ | Review before installing |
| rate-limit-guard Stops Claude from hammering external APIs with curl loops. | 1 ★ | Low risk |
| redactor Masks secrets and personal data in tool results before the model ever reads them. | 1 ★ | Low risk |
| regression-guard Remembers which tests passed at the start of the session and warns if any of them now fail. | 1 ★ | Low risk |
| rm-rf-guard Blocks catastrophic shell commands like rm -rf /, mkfs, dd to disks and chmod -R 777. | 1 ★ | Low risk |
| secret-shield Blocks edits and writes that would commit API keys, tokens or private keys. | 1 ★ | Low risk |
| seed-guard Blocks database seed, reset and drop commands unless DATABASE_URL points at your own machine. | 1 ★ | Low risk |
| snippet-vault Save and reuse code snippets across projects with /save-snippet and /snippet. | 1 ★ | Low risk |
| tracker-guard Blocks adding analytics and tracking SDKs that haven't been approved. | 1 ★ | Low risk |
| venv-guard Blocks pip install outside an active virtualenv so system Python stays clean. | 1 ★ | Low risk |
| vuln-scan After installs, runs npm audit or pip-audit and shows any vulnerabilities in a pane. | 1 ★ | Review before installing |
| watch-mode-guard Blocks watch-mode and never-ending commands run in the foreground, where they'd hang the turn. | 1 ★ | Low risk |
| workflow-studio Build, save and share reusable workflows — release, dependency update, security audit — and run them with one | 1 ★ | Review before installing |
| jarvis A JARVIS-style voice for Claude Code: say "Hey Jarvis" (or hold push-to-talk) to speak, hear the reply, talk o | 1 ★ | High risk |
| ciel-mode ciel-mode (Call-in-CEL mode) for Claude Code: the model writes a small sandboxed CEL program that calls MCP an | 1 ★ | Low risk |
| barmkin-mod Claude Code mods security layer: secret redaction, untrusted-content taint with a Rule-of-Two egress gate, ski | 1 ★ | Review before installing |
| blast-guard Holds risky shell commands for a yes/no with a dry-run report, blocks Python heredocs carrying backslash escap | 1 ★ | Low risk |
| cost-guard Watches session and daily spend, warns when the context grows large, and holds a prompt once when the prompt c | 1 ★ | Low risk |
| main-guard A red band when you are on main or in prod, and no force-push, reset --hard or unconfirmed push to a protected | 1 ★ | Review before installing |
| night-mode Late at night Claude gets more careful and asks before deploys, force pushes and rm -rf | 1 ★ | Review before installing |
| phone-approve Approve or deny Claude Code's permission prompts from Telegram, with the terminal prompt as the fallback. | 1 ★ | Low risk |
| rubber-duck A fast second opinion on every edit: a small model flags removed error handling, deleted tests, secrets and mo | 1 ★ | Low risk |
| secret-guard Stops Claude from writing API keys, tokens, private keys and database passwords into files. | 1 ★ | Low risk |
| effort-guard Claude Code mod: context/token band, escalation signals and per-turn effort log. | 1 ★ | Low risk |
| safety-net Blocks destructive tool calls before they run (force pushes, rm -rf outside the project, DROP TABLE, terraform | 1 ★ | Low risk |
| secret-scrubber Redacts API keys, tokens, private keys and .env secrets from tool output before the transcript stores it and b | 1 ★ | Low risk |
| delete-guard Stops Claude before it deletes or overwrites files: a side panel lists every folder and file at stake, with Ca | 1 ★ | Review before installing |
| guards dotfiles のガード群 (git 操作のスキル強制・ブランチロック・コメント規約・文脈注入)。機能ごとに hooks/ 配下の 1 ファイル | 1 ★ | Review before installing |
| goalpost-guard Stops Claude from passing a check by lowering the bar: weakened or deleted tests, new suppressions, relaxed co | 1 ★ | Low risk |
| sec-default Security default for organizations: seated outermost, it keeps the organization's classic hooks, prompt conten | – | Low risk |
| telemetry Plugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a firs | – | High risk |
| secret-guard Masks API keys and tokens in tool results before Claude reads them, and blocks a git push that would leak secr | – | Review before installing |
| windvane Babysits a long Claude Code session so you don't have to: the context fill is watched, the recorder drafts the | – | High risk |
| rook rook by TestMu AI inside Claude Code: Claude runs rook against the agent it is building and gets failures back | – | Review before installing |
| anime-cheer Voiced pixel anime girls who roam the Claude Code transcript: they dance while Claude works and serve tea when | – | Review before installing |
| env-guard Claude Code mod: blocks Claude from reading .env secret files and counts blocked attempts in the status line | – | Low risk |
| browser-guard Stops Chrome actions when the Chrome profile is not the one paired with the active cswap account | – | Low risk |
| danger-check Asks you before a command that can destroy work, such as rm -rf, git reset --hard or git push --force. | – | Low risk |
| adaflow-governance Trilha de auditoria do Claude Code no Adaflow: /adaflow login (device flow) e envio em lote so de metadados (s | – | Review before installing |
| adaflow-guard Guardrail para apps integrados ao Adaflow: impede vazar o app token (x-ada-token) para o browser, para o codig | – | Low risk |
| minecraft Playable first-person voxel sandbox inside Claude Code. Mine, build, explore, and save your world. | – | Low risk |
| code-buddy A rubber duck in your Claude Code session: a quiet second opinion on each turn, a guard for risky commands, re | – | Review before installing |
| cache-guardian Reloj de caché, cuota (5 h y semanal) frente al ritmo ideal, handoff preventivo y guardián del regreso | – | Review before installing |
| secret-guard Stops Claude from writing API keys, private keys and other secrets into your files | – | Low risk |
| pasek-zadan Pasek nad promptem w vaultcie asystenta: zadania na dziś i zaległe z Dashboardu oraz nowe wiadomości ze Skrzyn | – | Low risk |