Haram

A welcome feature has been added for those who frequently use the Claude Code terminal environment. This 2.1.302 update introduces new configuration settings that allow for much finer control over your workflow.

The most notable change is the environment variable that lets you directly change the classification model used for Auto Mode decisions. Previously, the client-side auto-classification model was fixed, but now you can specify your preferred model via the CLAUDE_CODE_AUTO_MODE_MODEL environment variable.

For those who found it cumbersome to write Shell scripts or configure environment variables when using hook features to automate specific tasks in Claude Code, you're in luck. Now you can call connected MCP server tools directly just by configuring settings.json.

Instead of creating separate wrapper scripts to pass data or format JSON, you can simply specify type: "mcp_tool" to execute them immediately via existing RPC connections. For example, if you want to automatically run a security scanner right after writing or modifying code, you can register it simply as shown below.

OpenAI has released the Record & Replay feature for its macOS Codex desktop app. This is great news for anyone who has been tired of performing repetitive desktop tasks or rewriting prompts every time. 😄

The way it works is quite intuitive. You perform a task on your desktop while the Codex app records it, and Codex analyzes the action to automatically convert it into a reusable agent skill. From then on, you can simply call that skill to 'replay' the same workflow without having to input long commands.

It goes beyond simple mouse-click recording by turning actions into executable automation scripts that the agent can understand, which looks really useful. If you have any daily repetitive clicking tasks or data collection workflows, you should definitely give it a try.

Starting with version v2.1.287, Claude Code Mods is officially supported. It's a hook system that allows you to write plugins in JS and TS to directly customize Claude Code's internal operations. Now you can control your CLI agent environment exactly how you like without needing complex external wrapper tools.

The most notable features are tool execution control and prompt rewriting. You can now detect and block sensitive information or dangerous actions before the model executes commands, and create your own custom commands (/command) that run instantly without passing through the model. It even includes UI extensions to launch custom side panels in the terminal.

OpenAI has finally launched 'ChatGPT Dots,' an always-on agent that works autonomously in the background 24/7! It’s not the typical ping-pong interaction where you ask a question and wait for a response. Instead, you give it a goal, and it uses cloud-based virtual computers and a browser environment to navigate sites, compile data, and report back via Slack or within ChatGPT. It’s essentially like having a virtual assistant that keeps working for you even after you clock out.

Unfortunately, it's not available to everyone. Free plans and the $20/month Plus plan are excluded; it’s only available to subscribers of the ChatGPT Pro plan (starting at $100/month) or Business Premium. While individual Pro accounts may have restrictions in regions like Europe and the UK, business users can reportedly bypass these limitations regardless of location. There's also a limit of only one default agent per account.

This agent is powered by the robust GPT-6 Astra model. Chatting with the agent is unlimited, but the tokens provided in your plan are consumed when it performs tasks in the background, such as operating a virtual browser. However, there's a launch promotion offering the first month with no background execution token deduction, so I highly recommend eligible users set it up and try it out now. You’ll feel the convenience immediately once you set it up to do something simple, like generating an automated daily trend report.

Are you still using the Cursor agent with just a single .cursorrules file in your project root?

Recent community tests show that the latest Cursor agent mode ignores the old root .cursorrules entirely. While compliance with the old format is almost zero, the new format using .mdc files inside the .cursor/rules folder follows rules perfectly. 😄

Instead of stuffing all your rules into one file, you should now break them into multiple mdc files within the folder. Make sure to append .md extension so the rule engine recognizes them properly. YAML metadata at the top of the file is required. You don't have to type it all out—just type c to the /create-rule in the agent chat, and it will generate the mdc file for you based on a prompt. It's surprisingly convenient!

Here is one more pro tip: when the agent mode executes terminal commands, the CURSOR_AGENT environment variable is injected. Sometimes, heavy zsh or bash themes can cause the terminal to slow down or hang. Adding a simple conditional check in your shell config file, as shown below, ensures the agent can execute commands smoothly.

The terminal-based AI tool Claude Code has officially introduced a very exciting feature called 'Claude Mods' with its v2.1.287 update! While you were previously limited to simple settings or prompt changes, you can now use TypeScript plugins to customize everything from the agent's core behavior and prompt input control to custom UI panels right in your terminal 😄

The most notable part of this update is the built-in 'You Should Know' plugin. It acts as an auxiliary agent that monitors long-running background tasks and highlights details that developers might easily overlook in real-time. Note that it is disabled by default and requires telemetry sharing to be enabled, so make sure to check that if you want to try it out.

Configuration has also become much simpler since version v2.1.285. You can now control the installation environment interactively directly from the terminal using the commands below, or pass specific plugin configuration values at the time of installation.

Claude Code, the AI agent that runs in your terminal, has just been updated to v2.1, and its usability has improved significantly! Moving away from the traditional global npm installation, it now uses optimized native binaries downloaded directly from the website. Installation feels much faster and lighter now.

What I personally like most about this update is the addition of features that directly help save on token costs. Specifically, try setting your output style to 'Concise' using the /config command. It strips out unnecessary explanations and greetings, providing only the essential code. This alone can reportedly reduce token usage by up to 40%. 😄 Also, a /skill-doctor command has been added to diagnose and prevent unused sub-agents from wasting your context window, enabling much smarter context management.

Don't forget the keyboard shortcuts to maximize your terminal workflow. When changing the agent's operation mode, pressing Shift+Tab allows you to quickly toggle between Normal mode, Auto mode (which automatically approves file edits), and Read-only Plan mode. If you want to revert your code to a previous state while working, pressing the Esc key twice in a row opens the rewind menu, which is super convenient.

If you are still using the previous version, install the new native build with the command below and experience these improved features for yourself!