Anthropic added Claude Mods to Claude Code v2.1.287 on October 1. Plugins now redraw the interface and intercept or pre-approve tool calls from inside the Claude Code process. There is no sandbox, mods can read environment variables and API keys, and the feature is on by default.
Armature ran Claude Code, Codex, and Cursor through 16,893 sessions where each agent had to pick a third-party service and write the integration. The three agreed 42% of the time, and switching the repo language changed the winning email provider.
Sonar instrumented its own coding-agent session traces. An 800-line PR took 512 model round trips, 152.8M cache-read tokens, and roughly $41, while newly read code accounted for only 106K tokens.
OpenAI served SpaceX a termination notice on August 28, closing direct access to GPT models inside Cursor on November 12. Cursor says those models are 5% of its traffic, and the bring-your-own-key workaround only reaches non-reasoning chat models.
Clustering 461,121 GitHub pull request descriptions by word usage alone, one cluster grew from 0.7% to 41%. Its top marker word, load-bearing, sits in Claude Code’s built-in prompt text, which is why banning it in CLAUDE.md does not work.
Spotify opened its coding agent session manager Xirp to public beta on August 10. The Mac app came out of 36,000+ internal sessions and splits Claude Code, Codex, and Gemini runs across Git worktrees.
Meta opened the Muse Code terminal agent in beta on August 5. Muse Spark 1.2 lost to Claude Opus 5 on all four benchmark charts Meta published itself. What is actually new is a contributor tier at $0.20 per million output tokens.
DeepSeek moved the V4-Flash API into public beta on July 31, added native Responses API support, and published its own documentation for wiring the model into OpenAI Codex.
Stack Overflow opened a beta knowledge exchange for coding agents, connecting TILs, Questions, Blueprints, reputation, votes, and verification loops through an API-first workflow.
Xiaomi released MiMo Code, an MIT-licensed OpenCode-based coding agent that puts memory, checkpoints, and completion verification at the center of long-horizon development work.
Cohere released North Mini Code, an Apache 2.0 coding model that activates 3B of 30B parameters for agentic software engineering, terminal work, and long-context tool use.
Apple expanded Xcode 27 and Foundation Models with MCP, ACP, Gemini, Claude, OpenAI agents, and new model choices for Apple app teams.