A developer built ai-vuln-scan, an open-source static analysis tool tuned to catch security flaws that appear disproportionately in AI-generated code, and published a versioned seven-pattern taxonomy …
A developer's practical map of the 2026 AI development stack argues the tooling landscape has settled into distinct layers — coding assistants, application frameworks, model gateways, evaluation and o…
A community project called Algo-Trading-Skills has released 501 structured algorithmic trading skills across 16 engineering domains, each backed by working reference implementations and 20,291 unit te…
A developer who switched from Anthropic's Claude Code to OpenAI's Codex (Terra/Sol/Astra) reported that Codex's Astra model generated a one-line git commit message — "Fix YouTube resolver playback and…
A developer published a Claude Code PreToolUse hook that inspects the session transcript to detect whether the active model is a "fable" model and, if so, blocks the parent session from editing files …
Benzi, a new code-intelligence harness, resolved 78.2% of 500 real issues on SWE-bench Verified at under 10 cents per fix, according to benchmarks published on the project's site. In a 24-bug, 10-lang…
A developer known as Yamada attempted to test whether AI can genuinely understand legacy code by having Claude Code and Codex recreate a 2008-era VB.NET business application, complete with the specifi…
Details.so launched a handpicked website-design inspiration gallery that captures individual interface details — hero sections, footers, page transitions, preloaders and micro-interactions — from live…
Developer Forrest Chang turned four observations from AI researcher Andrej Karpathy about how large language models fail at coding into a CLAUDE.md file that Claude Code reads automatically at the sta…
Rails Baseline released a free, repo-aware architecture checkup tool for existing Rails applications that runs inside coding agents such as Codex, Claude Code, and Cursor. The checkup flags where an a…
A developer built a post-session logging system for Claude Code using the Stop hook, parsing transcript JSONL files to track subagent invocation times, error rates, and costs. Measuring subagent perfo…
Dam Secure launched Secure Spec, a CLI that captures coding agents' implementation plans and routes them through a security review before any code is written, using agent hooks such as Claude Code's P…
An MCP server is a small program that exposes tools, data or prompt templates to an AI agent over the Model Context Protocol, an open standard Anthropic open sourced on 25 November 2024, according to …
Anthropic's new documentation for Claude Opus 5 and Fable 5.1 advises users to hand over a complete task specification up front rather than a step-by-step script, warning that skills and prompts writt…
Netlify shipped smarter credit scoping for its Agent Runners on Sept. 4, 2026, so an ambitious prompt on a new project no longer exhausts the credit budget mid-build and dead-ends in a "Cancelled" run…
A free, MIT-licensed plugin called Quartermaster, available in the Eigenwise Toolshed marketplace, watches Claude Code sessions and proposes one workspace change at a time for user approval, then veri…
Anthropic's Claude Code is a command-line interface agent that installs via `npm install -g @anthropic-ai/claude-code` on Node.js v18 or later, authenticates through an Anthropic Console account, and …
A head-to-head test of Cursor, Windsurf, and Claude Code on a 40k-line Next.js project found Cursor's Composer needed 4 tries to fix a React useEffect race condition, Windsurf's Flow took 2 attempts, …
An open-source command line tool called Claude Task Master automates the full pull request workflow, planning tasks, writing code, running tests, pushing commits, opening pull requests, responding to …
Cursor and Claude Code maintain separate discussion venues, with Cursor hosted on its own forum at forum.cursor.com and Claude Code discussions scattered across the Anthropic Discord and X, according …