termaxa

Termaxa — Security skill for Claude Code

Security community

A cooperative gate for the shell commands AI agents run.

How to install Termaxa

This entry records only its repository, not the path inside it, so there is no exact command to give. Open termaxa/termaxa and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Termaxa does

A cooperative gate for the shell commands AI agents run. Previews, backups, policy, audit. Claude Code + Cursor. A windshield, not a sandbox.

Alternatives in Security

  • Security Guardian — Comprehensive security analysis for RTK CLI tool, focusing on command injection, shell escaping, hook security 11.9k ★
  • OpenTag — Open-source, channel-native agent gateway for Slack 499 ★
  • Loongsuite Pilot — Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cu 150 ★

README

🛡 Termaxa

**Run AI coding agents with confidence.**

Termaxa gates the shell commands an agent runs — previews the blast radius, backs up first, blocks the dangerous ones, and escalates repeat offenders. It's a cooperative windshield, not a sandbox.

[![CI](https://github.com/termaxa/termaxa/actions/workflows/ci.yml/badge.svg)](https://github.com/termaxa/termaxa/actions/workflows/ci.yml) [![Release](https://img.shields.io/github/v/release/termaxa/termaxa?display_name=tag)](https://github.com/termaxa/termaxa/releases) [![License](https://img.shields.io/badge/license-MIT%2FApache--2.0-blue)](#license)

Your AI agent wants to run `git push --force`, `DROP TABLE users`, `terraform apply`, `rm -rf`. Most of the time it's right. Sometimes it isn't. Today your only options are *supervise every command* (which defeats the point of an agent) or *trust it blindly* (which defeats your Friday).

Termaxa is a third option: a gate the agent's commands pass through. It reads a policy you wrote, shows you what's actually about to happen, backs up what's about to change, and records everything. Built for **Claude Code** and **Cursor** today; works as a standalone CLI anywhere.

  Claude Code --> TERMAXA --> git . postgres . docker . terraform . your shell
                    |
                    +- decide    allow / ask / deny  (your policy)
                    +- preview   commits lost, rows affected, resources destroyed
                    +- insure    automatic backup before destructive ops
                    +- escalate  repeated destructive intent -> auto-deny
                    +- record    every attempt, with an execution report

Quick start (5 minutes)

**1. Install.**

brew install termaxa/tap/termaxa     # macOS / Linux (prebuilt, sha256-pinned)
cargo install termaxa                # any OS, with a Rust toolchain

Windows: download `termaxa-windows-x86_64.exe` from [Releases](https://github.com/termaxa/termax

Related Skills

GuardRun — Security skill for Claude Code

GuardRun

GuardRun: a safety-first AI agent harness for DeepSeek and Claude, with a path sandbox, shell command policy,

Security community
Prelaunch — Security skill for Claude Code

Prelaunch

Pre-launch gate for an ASEN project - runs every pre-launch checklist for its type and integrations, plus secu

Security community
Memnox — Security skill for Claude Code

Memnox

See what your AI coding agents can actually do on your machine, and put the dangerous actions behind ask or de

Security community
Openmoat — Security skill for Claude Code

Openmoat

Security for AI coding agents. One policy controls what Claude Code, Codex and Cursor can run, read, write and

Security community
Coding Agent Security Checklist — Security skill for Claude Code

Coding Agent Security Checklist

Stop your AI coding agent (Claude Code, Cursor, Codex) from installing malware straight out of llms.txt docume

Security community
Aestheris — Security skill for Claude Code

Aestheris

Let your AI agents act without handing them your keys or your data. Local, open-source trust layer: vault & ph

Security community

Related Agents

Wlroots Expert — Development agent for Claude Code

Wlroots Expert

wlroots C API expert — scene graph, listener wiring, surface lifecycle, seat/cursor invariants, xdg-shell + xw

Development community
Governance Reviewer — Security agent for Claude Code

Governance Reviewer

Reviews a change for governance compliance using PromptWise — security scan, policy check, quality gate, and a

Security community
QA Execution Operator — Testing & QA agent for Claude Code

QA Execution Operator

Requests approved sandbox execution through an allowlisted adapter and reports test-run evidence without direc

Testing & QA community