Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

claude-code-templates

Large catalog of Claude Code agents, commands, hooks and MCPs, listed with community Jev mods for guardrails and subagent models.

CLIproductionMIT
View on GitHub ↗Live demo ↗

Overview

Claude Code Templates (aitmpl.com) is a large, MIT-licensed collection of ready-to-use configurations for Claude Code: AI agents, custom commands, settings, hooks, MCP integrations and project templates, installable through an npx CLI and browsable on a website.

Per the list summaries, it includes community mods that use Jev: a jev-guardrails mod that screens prompts and turns for jailbreaks, harm and policy breaches, and a mod that suggests subagent models and reasoning levels. The README excerpt available here does not describe these mods, so their exact questions and thresholds are not confirmed. Its CLI installs bundles of skills and MCP servers in one command, and the catalog aggregates components from other open-source collections that keep their own licences.

What the decision model decides

TypeQuestionAnswers
Yes / noIs this prompt or turn a jailbreak, harmful or a policy breach?(inferred)yes · no
ChoiceWhich model and reasoning level should this subagent use?(inferred)—

How it works

  1. Install the relevant mod with the CLI
  2. Mod hooks into prompts or subagent spawns
  3. Jev returns typed judgments
  4. Mod blocks, warns or sets the model

Strengths

  • Easy install through a popular template catalog

Caveats

  • Jev mods not described in the README excerpt
  • Community mods vary in quality

Getting started

npx claude-code-templates@latest (browse components at https://aitmpl.com)

At a glance

Type
CLI
Status
production
Language
JavaScript
Runtime
CLI + Claude Code components
Has code
yes
License
MIT

Use cases and integrations

How curated lists describe it

  • Agent safety: CLI configuration suite for Claude Code featuring a `jev-guardrails` mod that screens prompts and turns against jailbreaks, harm, and policy breaches via TypeSafe System One.

    yibie/awesome-jev

  • A community Claude Code Templates mod that uses Jev to suggest subagent models and reasoning levels.

    logicrw/awesome-jev-projects

Frequently asked questions

Where is Jev used?

In community mods for guardrails and subagent model selection, per the listing.

How do I install components?

With npx claude-code-templates@latest.

Is Jev required?

No, only for those specific mods.

Related projects

  • jev-axi

    Agent-ergonomic Jev CLI and PreToolUse hook that scores shell commands for hazards and screens fetched text for injection.

    PluginbetaTypeScript
  • jev-firewall

    PreToolUse firewall for Claude Code and Codex: shell-aware rules first, then Jev returns allow, ask or block, failing closed.

    HookbetaTypeScript
  • jev-guard (leepokai)

    Security hook giving Codex, Copilot, Gemini, Cursor, pi, OpenCode and ACP an auto-mode-like guard via three Jev questions.

    LibrarybetaTypeScript
  • jev-injection-guard

    OpenBles Firewall 1: open prompt-injection detector for agent inputs, with a Claude Code hook and an optional Jev backend.

    MCP serverbetaPython
  • jev-shield

    Semantic MCP firewall that screens tool calls, results and descriptions with Jev, plus allowlists and session taint tracking.

    MCP serverbetaTypeScript
  • reflex (ursuciprian)

    Pre-execution hook for coding agents that lets shell commands run, asks a human, or blocks them, with optional Jev classification.

    ProjectbetaJavaScript