A roughly 400-line markdown skill file lets Claude Code and Codex control a full computer screen through native terminal commands — PowerShell on Windows, AppleScript on Mac, and equivalent shell tool…
A developer outlined a practical workflow for combining several Claude Code skills to take a feature from a vague idea to a finished implementation, using an AI-generated bookmark collection feature a…
The AI SDK harness layer now supports authenticating coding-agent harnesses through their native subscriptions, Vercel announced in a changelog. The layer runs different coding agents through the same…
Amazon Web Services added a Consent portal to AgentCore Identity, a capability of Amazon Bedrock AgentCore, giving customers a managed web experience and session binding endpoint for the AgentCore Gat…
Slowave, a GitHub project, has added an adaptive memory layer that stores codebase decision context across AI agent sessions, addressing the loss of context when agents open a new session or switch to…
Replay Doctor, a locally run diagnostic tool, reads Claude Code transcripts to identify which turn caused prompt cache expiry or other failures and how many tokens were re-billed at write prices. The …
Cline founder Saoud Rizwan launched Cline Desktop, a standalone beta coding agent for macOS and Windows, on September 14th, giving the open-source tool its own interface outside an IDE with support fo…
Polign released Recall, a shared typed memory system that lets AI agents store, correct, and read back facts, preferences, and project context across processes and sessions. Recall is available throug…
Laravel has released Laravel Vet in beta, a Composer plugin that audits PHP dependencies by showing the code each `composer update` would write into `vendor/` and recording trusted packages in a `vet.…
A developer outlined five operational boundaries for running coding agents safely, arguing that access, spend, change, and release controls should be enforced by the environment rather than the agent'…
Anthropic will bring outside safety reviewers into the company with office desks, access badges and laptops and let them publish findings on risks, incidents and practices "without editorial control b…
A developer has documented how to diagnose JavaScript heap out of memory crashes in AI coding CLIs by reading the garbage-collector output before raising the heap size. The writeup explains that near-…
A developer built ds_usage, a free MIT-licensed VS Code extension that displays Claude Code usage limits in the status bar, showing 5-hour and 7-day percentages with amber and red warnings at 75% and …
A developer released Cognition-Claude-proxy, a local proxy that lets Anthropic's Claude Code use Devin's model catalog — including SWE-2, GLM-5.2, and DeepSeek V4.1 Flash — as its backend by translati…
Anthropic shipped a first-party evaluation command for Claude Code, `claude plugin eval`, that runs a test suite with a plugin loaded and again without it to report the delta the plugin actually contr…
A security engineer built m8m, a tool for auditing the persistent memory files that AI coding agents like Claude Code, Codex, and Cursor write automatically, after finding no way to inspect what those…
ProGantt launched a built-in MCP server that lets AI agents read and write Gantt chart tasks, milestones, resources, tags, and dependencies, with MCP access free on every plan. The server connects to …
A developer built VBridge, a tool that runs Claude Code directly against a user's actual Excel VBA project on their own machine, letting the agent read real .bas and .cls modules and execute macros ag…
A hybrid AI code security review workflow, in which large language models flag potential vulnerabilities such as SQL injection or broken access control and a human developer manually verifies and patc…
DeepMem launched a plugin for Claude Code and Cursor that provides persistent, semantically searchable memory across coding sessions, distributed through the Claude Code plugin marketplace and the Ope…