Maintainer of this skill?
Automated security scan — not a certification.
by linuztx
RAM efficient terminal agent harness for coding, cybersecurity, and automation.
# Add to your Claude Code skills
git clone https://github.com/linuztx/alter-zeroLast scanned: 10/28/2026
{
"issues": [
{
"file": "README.md",
"line": 67,
"type": "remote-install",
"message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://raw.githubusercontent.com/linuztx/alter-zero/main/install.sh \"",
"severity": "low"
},
{
"file": "prompts/skills/jina-reader/SKILL.md",
"line": 29,
"type": "secret-exfiltration",
"message": "Instruction appears to send credentials/secrets to an external endpoint",
"severity": "medium"
}
],
"status": "PASSED",
"scannedAt": "2026-10-28T10:23:08.856Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how alter-zero compares with popular alternatives.
alter-zero is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by linuztx. RAM efficient terminal agent harness for coding, cybersecurity, and automation. It has 105 GitHub stars.
Yes. alter-zero passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/linuztx/alter-zero" and add it to your Claude Code skills directory (see the Installation section above).
alter-zero is primarily written in Rust. It is open-source under linuztx on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh alter-zero against similar tools.
No comments yet. Be the first to share your thoughts!
From $49 · 30 days · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
Read, build, debug, and review code with an agent that works alongside you. Use the same tools for cybersecurity research, technical investigation, and everyday automation.
Quick start · Features · Model providers · Commands & shortcuts · Support · Acknowledgements
Alter Zero is an open-source AI coding agent written in Rust. It works directly in your project: reading files, making edits, running commands, and checking results while you follow along in your terminal. Coding is its focus, with the flexibility to investigate security issues, explore unfamiliar systems, and automate tasks using your existing tools.
| What you get | Why it matters |
|---|---|
| Work you can follow | Live command output, readable diffs, and a task checklist make progress easy to inspect. |
| Control over execution | Choose a permission mode, review proposed changes, and steer the agent while it works. |
| Your choice of model | Connect with a supported subscription or API key, or run local models with Ollama or LM Studio. |
| Room to extend | Add specialist subagents, reusable skills, lifecycle hooks, and MCP servers to fit your workflow. |
| A native terminal experience | A single Rust binary with persistent sessions, inline images, and keyboard-driven controls. |
Alter Zero runs on Linux (x86_64, arm64) and macOS (Intel, Apple silicon) in a modern terminal.
One line on Linux or macOS:
curl -fsSL https://raw.githubusercontent.com/linuztx/alter-zero/main/install.sh | sh
It picks the build for your machine, verifies its SHA-256 against the checksum published with the release, installs alter-zero into ~/.local/bin, and tells you if that directory is not on your PATH.
Or install the same build with npm:
npm install -g @linuztx/alter-zero
Set ALTER_ZERO_INSTALL_DIR to install somewhere else, or ALTER_ZERO_VERSION=vX.Y.Z to pin a release. CHANGELOG.md records what changed between versions.
ALTER_ZERO_INSTALL_DIR="$HOME/bin" ALTER_ZERO_VERSION=v0.1.0 \
sh -c "$(curl -fsSL https://raw.githubusercontent.com/linuztx/alter-zero/main/install.sh)"
For a manual install, each release's notes list every archive with its SHA-256, so you can download, verify, and extract one by hand.
docker/ builds a small headless Kali Rolling image around the latest release, with a working set of command-line tools, for Docker or Podman. One command builds it and starts a container on a folder of yours:
docker/build.sh ~/projects/site # add --engine podman for Podman
docker exec -it -e TERM -e COLORTERM -e TERM_PROGRAM -e KITTY_WINDOW_ID -e TMUX \
alter-zero-kali alter-zero
Outside a multiplexer, the -e flags hand over your terminal's identity so
pictures render as real images rather than half-blocks. The
container guide covers workspaces, the published ports,
pasting images, and adding tools.
Inside tmux, enable allow-passthrough on the host and explicitly select the
outer terminal's image protocol for that docker exec; the
tmux instructions include a
ready-to-run Podman example.
You need rustup and a C compiler. The repository pins the Rust toolchain, which rustup installs automatically.
git clone https://github.com/linuztx/alter-zero.git
cd alter-zero
cargo install --path .
alter-zero
Without a configured provider, Alter Zero opens an offline demo with scripted turns so you can explore the interface. To work on your own tasks:
/login and choose a supported subscription, API provider, or local model server. Follow the prompts to connect./model to choose a model. Alter Zero remembers your selection for this directory.Sign-ins added through /login are saved to ~/.alter-zero/.env, outside your repository. Use / to browse commands or ? in an empty composer to see shortcuts.
You can also select your provider before launch. Set its API key variable and provider ID, then start the app. For example, with OpenRouter:
export OPENROUTER_API_KEY="your-api-key"
export ALTER_ZERO_PROVIDER=openrouter
alter-zero
Choose a model with /model, or set ALTER_ZERO_MODEL to its model ID before launching.
Start with a concrete task and let the agent work through it with you.
| Use case | Try asking |
|---|---|
| Coding and debugging | "Find why this test fails, fix the cause, and run the relevant tests." |
| Cybersecurity research | "Review this repository for security vulnerabilities. Trace each finding to the code and suggest a fix." |
| Technical investigation | "Trace how authentication works in this project and explain where access checks happen." |
| Automation | "Write a script that summarises these logs and flags recurring errors." |
Connect to a supported subscription service, API provider, or local model server. Use /login to connect and /model to choose your model.
| Provider | How you connect | Good to know |
|---|---|---|
| Agent Zero API | API key. | Accesses Venice.ai models through the Agent Zero proxy, with a free daily quota for A0T token holders. |
| Venice | API key. | Venice.ai's private, uncensored models straight from Venice's own API — the same catalog the Agent Zero API proxies, reached with your own account. |
| GitHub Copilot | Subscription, using a one-time device code. | Model capabilities, including context window, vision, and reasoning levels, come from Copilot. |
| ChatGPT Codex | Subscription, with a ChatGPT Plus or Pro account: a browser sign-in, or a one-time device code on a headless machine. | Uses the account sign-in flow; no API key to paste. |
| Anthropic | API key or account sign-in through the Anthropic Console. | Usage is billed to your API organisation with either method. |
| Cline | API key. | The models behind the Cline extension and CLI, through Cline's OpenAI-compatible API — Anthropic, OpenAI, Google and more, billed to your account's credits. |
| ClinePass | Subscription ($9.99/month), with a Cline account sign-in. | 2-5x usage on Cline's curated open coding models — the plan's cline-pass/… models appear in /model. |
| OpenRouter | API key. | Access models from multiple providers through one account. |
| Ollama | Local model: enter your server's address, which is tested before it's saved; no key required. | Run inference on your own machine with locally hosted models. |
| LM Studio | Local model: enter your server's address, tested the same way; a token only if the server requires one. | Run the models you downloaded in LM Studio; start its server first. |
| Ollama Cloud | API key. | Use open models hosted by Ollama. |
The footer shows your active model, thinking mode, speed tier and context usage. Ctrl+T cycles the model's supported reasoning levels, a ChatGPT model that lists speed tiers gets a command per tier (/fast, /ultrafast) that switches it to that processing (faster replies at increased plan usage), vision support is checked before sending images, and requests support prompt c