# CLI Articoli collegati

OpenAI, Open-Sourced

OpenAI has open-sourced its code security tool, Codex Security CLI. The tool, which originated from the private beta project Aardvark in October 2025, is designed to automatically discover, verify, and fix vulnerabilities in codebases. It functions as an application security agent, first analyzing a repository to build a threat model, then identifying and ranking vulnerabilities based on real-world impact, and finally testing them in a sandbox for validation. According to OpenAI, in its first 30 days, the tool scanned over 1.2 million commits, uncovering 792 critical and 10,561 high-severity vulnerabilities, with a reported reduction of over 50% in false positives upon repeated scans of the same repositories. However, initial user experiences on platforms like Hacker News highlighted significant issues, particularly concerning cost and reliability. Developers reported failed scans that consumed substantial portions of API rate limits and incurred high expenses, with one user noting a cost of approximately $13 for an aborted run. The high cost is attributed to the tool's default configuration, which uses the premium GPT-5.6-sol model with inference intensity set to "extra-high." The release follows public statements by NVIDIA's Jensen Huang advocating for open-source AI. While OpenAI has open-sourced the application-layer CLI and SDK, the core AI models remain proprietary. The move opens the door for community development and potential adaptations of the tool.

marsbit07/30 07:43

Racking Up 24,000 Stars: With One Command, AI Can Now Find Its Own Skills

Vercel, known for its developer tools like Next.js, has launched 'skills', a package manager for AI coding agents, garnering 24,000 GitHub stars. It allows developers to add specialized capabilities, such as React best practices, to AI assistants like Claude Code or Cursor with a single command: `npx skills add <package>`. Skills are shareable, reusable modules that define an AI agent's behavior for specific tasks, moving beyond one-off prompt engineering towards standardized 'capability engineering'. A key innovation is the 'find-skills' skill, which acts as an internal search engine, allowing an agent to autonomously find and install the right skill for a user's request. This lowers the barrier for non-developers to leverage advanced AI coding assistance. However, this 'npm moment' for AI brings significant security risks. Security audits of thousands of skills on platforms like skills.sh and ClawHub found over 30% contained security flaws, with about 13% classified as severe. Threats include malicious scripts that can access local files and credentials, and prompt injection hidden within skill documentation. Unlike traditional code packages, skills blend instructions, code, and system access, posing a direct risk to user machines and data. Experts advise treating skills like code—reviewing them carefully before installation, especially their scripts, and being wary of excessive permissions. Ultimately, Vercel's initiative represents a major shift towards modular, reusable AI capabilities, but its rapid adoption requires developers to bring the same caution used in managing traditional software dependencies.

marsbit07/06 00:19

28,000-Star Hit Creator Unexpectedly Fired by Google, Silicon Valley Big Shots Quickly Vie for the Talent

A nearly 7-year Google veteran, Justin Poehnelt, was fired shortly after his open-source project 'gws' (a Google Workspace CLI built in Rust) went viral, amassing over 28,000 GitHub stars. The tool, designed for both humans and AI agents, allowed terminal access to all major Workspace services like Gmail and Drive by dynamically generating commands from Google's own APIs. The dismissal came just two days after Google announced its "official" Workspace CLI at its Cloud Next 2026 conference, leading to widespread criticism that the company appropriated his work. Poehnelt believes the real reason was internal fear that his project demonstrated how AI agents could fundamentally disrupt and simplify interaction with Google's core Workspace products, potentially threatening its established business model. Following his public disclosure of the events, which garnered millions of views, tech leaders like OpenClaw's Peter Steinberger and CEOs from OpenRouter and Vercel swiftly offered him jobs, highlighting the perceived misstep by Google in letting a top-performing innovator go.

marsbit06/26 00:19

From IDE to Terminal: A Practical Guide to Agent Engineering

marsbit06/03 07:01

10 Claude Code Usage Tips: The Sooner You Know, The Sooner You Benefit

Here is an English summary of the article "10 Must-Know Claude Code Tips: The Sooner You Know, The Sooner You Benefit": This article shares essential tips for using Claude Code, an AI coding assistant, to significantly boost productivity. It is divided into three main sections. First, it covers three ways to launch Claude: 1) A simple GUI desktop app for non-programmers, 2) A command-line method with a key tip (`claude -c`) to resume from a specific point in the chat history, avoiding restarting context, and 3) A headless mode (`-p` flag) for automation tasks using a subscription token. Second, it details three crucial in-session techniques: 1) Using `Esc` to gracefully interrupt a response and `Esc+Esc` to revert to a previous checkpoint, 2) Using the `!` syntax (e.g., `!ls`) to run shell commands without leaving the chat, and 3) Managing context with `/clear` to remove history or `/compact` to optimize it when performance slows down. Finally, the article recommends companion software to solve human-AI collaboration bottlenecks: 1) **Superpowers**, a structured workflow methodology for higher-quality code output. 2) Voice input tools like **Typeless** and **Douban Input法** to overcome typing speed limit. 3) Tools like **Cmux** (a terminal for managing multiple AI agent instances) and **Vibe Island** (for seamless context switching between tasks) to solve the problem of lost focus when multitasking. The overall goal is to help users focus more deeply on their programming work by streamlining their interaction with Claude Code.

marsbit04/08 07:05

Agentic Workflows for Crypto Research

AI coding agents are transforming crypto research by automating data analysis through natural language. This article demonstrates using an agent (like Claude Code) with the Glassnode CLI to test a hypothesis: whether extreme Bitcoin exchange inflows predict 7-day price drawdowns. The agent autonomously discovers metrics, fetches data, performs statistical analysis, and generates insights. Results show a moderate association—spike days saw ~1.9% greater drawdowns—though the sample is small. A follow-up prompt produces visualizations for validation. The workflow allows rapid iteration and is applicable to various research questions using Glassnode data, requiring only an API key and an AI agent.

insights.glassnode04/01 12:41

OpenAI Official Plugin Strongly Integrated into Claude Code

OpenAI has officially released the "codex-plugin-cc" on GitHub, enabling developers to integrate OpenAI’s Codex model capabilities directly into Anthropic’s command-line development tool, Claude Code. This cross-platform integration breaks down ecosystem barriers between major AI tools, allowing developers to leverage the strengths of both models without switching environments. With simple configuration, Claude Code becomes a versatile programming assistant combining the advantages of both companies. Key features include: - Standard code review via the `/codex:review` command, providing expert improvement recommendations and double-checking for logic errors. - Adversarial review using `/codex:adversarial-review`, which challenges design decisions to identify potential performance bottlenecks or security risks. - Task delegation through `/codex:rescue`, allowing complex debugging or repair tasks to be handed off to a Codex sub-agent for collaborative problem-solving. This integration enhances code quality and development efficiency through multi-model collaboration.

marsbit03/31 05:55

Amid the OpenClaw Craze, CEXs Vie for AI Agent Trading Entry Points

Under the "OpenClaw Craze," major cryptocurrency exchanges like OKX, Binance, Gate, and Bitget are aggressively competing to become the primary transaction entry point for AI Agents. They are no longer just chasing trends but are transforming their core capabilities—trading, market data, wallets, and payments—into modular interfaces that Agents can understand and execute. OKX is focusing on execution, integrating spot, perpetual, and options trading with local signing and simulation modes. Binance is strengthening its information layer and skill distribution, expanding from market data into derivatives and asset management. Bitget is pushing for greater depth, incorporating copy trading, wealth management, and payment services. Gate is building a foundational platform with DEX/CEX MCP, CLI, and Skills Hub. The shift is significant: exchanges are moving beyond AI-assisted analysis to enabling actual system calls and execution. While pre-trade actions like research and screening are becoming smoother, challenges around permissions, security, and risk management in fully automated trading remain. The core competition is about which platform can best modularize its services, ensure security, and become the default financial infrastructure called by Agents in interfaces like Claude and ChatGPT.

Odaily星球日报03/16 06:03