Hooks in AI coding agents like Claude Code and Codex enforce rules deterministically by running scripts on specific events, returning exit codes that block or force agent actions, unlike probabilistic…
OpenAI's open-source Codex repository saw an 8x increase in monthly commits, from 98 in May 2025 to 791 in March 2026, and over 1,000 in the first 25 days of August 2026, with authors growing from six…
A single page on a Snippet Digital client site earned 102,657 image-search impressions and 2 clicks in 90 days, while the site's overall image-search impressions ran at 64% of web's volume and clicks …
A general-purpose coding agent such as Claude Code, Codex CLI, or Gemini CLI can outperform single-purpose marketing AI tools for data and file tasks, according to a playbook that identifies five tran…
A developer's 14-hour comparison of Cursor, Windsurf, and Claude Code found Cursor's Composer mode best for integrated multi-file edits, Windsurf's Flow most autonomous for debugging, and Claude Code …
Developer hetpatel-11 released agent-hop 0.1.3, an open-source Rust TUI runtime that lets users run Claude Code, Codex, OpenCode, Pi, and Grok in one terminal and hop a live chat session between them …
Developer zhaoxuya520 has released reverse-skill, an open-source framework that routes AI coding agents through verified execution paths for cybersecurity tasks such as reverse engineering and vulnera…
A developer reports that AI coding assistants like Claude Code and aider deliver the greatest productivity gains not in writing code but in reading unfamiliar codebases, performing mechanical migratio…
Revyl, a startup building tools for the new software development loop, argues that coding agents are improving exponentially, making verification and simulation the bottleneck and rewriting product de…
Shopify CEO Tobi Lütke signaled on Twitter that the company is considering banning Claude Code from enterprise use, citing unspecified security, governance, or productivity concerns. The statement ref…
A developer has been using Anthropic's Claude Code to run three small projects, including a Japanese-language blog and a subscription pitch, with seven AI subagents handling roles from CEO to marketer…
AgentBridge, a new open-source tool, synchronizes custom skills, MCP servers, and project rules across Google Antigravity, Claude Code, and OpenAI Codex using a shared hub at ~/.agentbridge/skills wit…
Coddy Tech's AI Coding Addiction Report, published August 13, 2026, found that 80% of 305 developers surveyed said their AI use felt more like dependence than advantage at least once, with 43% coding …
A developer explains why they stopped relying on Claude Code, arguing that over-dependence on AI coding assistants is eroding engineers' problem-solving skills and portable knowledge. The developer wa…
A developer has shared a starter prompt and job ideas for building a personal-ops system: a local platform that runs scheduled jobs, stores their output, and notifies the user when something needs att…
Actualis, a new open-source tool from Digital Foundry, reads coding-agent session logs on a user's machine to report shell commands, credential exposure, refused tool calls, and per-project costs acro…
JetBrains' Developer Ecosystem Survey 2026, which polled over 15,000 professional developers worldwide, found that on average, 47% of code is fully written by AI agents, 38% with some AI assistance, a…
Microsoft researchers propose treating the harness boundary as an integration point for training modern AI agents, addressing the challenge that harnesses own tools, context, and control flow. The pap…
A developer's hands-on comparison finds that Cursor's Composer mode outperforms both Claude Code and manual RAG setups for building a codebase knowledge base, citing Cursor's local indexing and instan…
Tenet Security researchers demonstrated at DEF CON 34 a new attack called 'Ghostjacking' that tricks AI coding agents into proposing DNS changes by planting malicious instructions in error logs, achie…