Claude Code routes Grep, Glob through Bash

// 45d agoPRODUCT UPDATE

Claude Code routes Grep, Glob through Bash

Claude Code 2.1.117 replaces native Glob and Grep tools on macOS and Linux native builds with embedded bfs and ugrep routed through Bash, while Windows and npm installs are unchanged. The change aims to speed searches by avoiding separate tool round trips, but early users are flagging workflow and permission side effects.

// ANALYSIS

This is a performance-minded agent tooling change with a real ergonomics bill: faster search is useful, but moving core exploration into Bash changes how developers audit, hook, and constrain agent behavior.

–Native-build users may see fewer explicit Grep/Glob calls and more Bash-mediated search behavior
–Teams with hooks, allowlists, or monitoring keyed to tool names need to revisit their Claude Code policies
–The npm and Windows carve-out makes behavior less uniform across developer environments
–The update lands alongside broader 2.1.117 improvements for subagents, plugins, resume flows, and model defaults

// TAGS

claude-codeai-codingcliagentdevtool

DISCOVERED

45d ago

2026-04-23

PUBLISHED

45d ago

2026-04-23

RELEVANCE

8/ 10

AUTHOR

noahzweben

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

NEWS23m ago

xAI Grok 1.5T enters reinforcement learning

Elon Musk has confirmed that xAI's 1.5T parameter Grok model is currently undergoing reinforcement learning (RL). This indicates that the base training phase for the large language model is finished, and the development team has transitioned to the final post-training stage to refine safety, alignment, and task performance before a public release.

NEWS26m ago

DAIR.AI curates week's top AI papers

DAIR.AI has released its weekly curation of top AI research papers for May 31 to June 7, 2026. The roundup highlights LEAP, an agentic framework wrapping LLMs with Lean compiler feedback to solve formal mathematics; AutoLab, a benchmark evaluating frontier models on long-horizon, closed-loop research and engineering tasks; Learn From Your Own Latents, a theoretical study demonstrating why predicting internal representations rather than raw tokens decreases sample complexity; and Reusable Context Engineering, which explores modular design patterns for standardizing agent contexts to mitigate token bloat.

UPDATE45m ago

Prime Intellect joins the NVIDIA Nemotron Coalition to provide hosted post-training, reinforcement learning, and evaluation infrastructure for Nemotron 3 Ultra on its Lab platform.

Prime Intellect has announced a partnership with NVIDIA by joining the NVIDIA Nemotron Coalition. As part of this collaboration, Prime Intellect is integrating support for Nemotron 3 Ultra—a 550-billion-parameter Mixture-of-Experts (MoE) reasoning model—into its decentralized AI training platform, Lab. This integration provides developers and enterprises with a repeatable post-training loop that runs natively on Blackwell GPU infrastructure, enabling day-0 hosted reinforcement learning (RL), automated sandbox orchestration, evaluations, and inference to customize Nemotron models for specific workflows and industries.