Anthropic published a technical guide on August 15, 2026, explaining how users can reduce costs and extend session limits in Claude Code, its terminal-based coding assistant, by leveraging prompt cach…
Claude Code's auto mode became the default on Pro, Max, and Team plans today, but a pseudonymous researcher published a bypass two days early that hid instructions in an image and succeeded in 6 of 10…
Anthropic's Opus 5 model produces verbose output, and a developer offers four methods to fix it, from writing rules in CLAUDE.md to using output styles. The developer explains that output styles, whic…
An engineer from tamiz.pro argues that the trust problem in AI agents stems from a structural mismatch between traditional software engineering and autonomous code generation, and proposes five archit…
Anthropic has made auto mode the default permission setting in Claude Code for Pro, Max, and Team users, replacing repeated approval prompts with a classifier that checks each tool call for risky acti…
A new framework called the Agent Bill of Materials (AgBOM) is emerging to inventory autonomous coding agents in software pipelines, formalized through OWASP's Agent Observability Standard (AOS) projec…
A developer created a bash script, claude-history.sh, that lists recent Claude Code sessions across all project directories, sorted by the last activity timestamp recorded inside each transcript rathe…
A developer revamped their terminal workflow to improve both human and AI-assisted command-line efficiency, installing lightweight zsh plugins for autocomplete and history search, and adopting modern …
A developer discovered that Claude Code's co-authorship attribution was disabled not by a config file but by a single sentence in a rules file, revealing that prose in LLM agent systems functions as t…
Developer egnaro9 released evalmut, an open-source mutation testing tool for LLM evaluation suites, available via pip install evalmut and on GitHub under an MIT license. The tool injects 18 provenance…
MongoDB, Inc. (NASDAQ: MDB) announced at MongoDB.local Build Fest the availability of MongoDB Atlas Managed MCP Server, a fully hosted service that connects coding agents to MongoDB Atlas without addi…
Developer Daniel Lublinsky released Skill Atlas, a free, open-source graph-search plugin for Claude Code that adds a 'searchable' tier between enabled and disabled skills, cutting per-session token us…
Anthropic's Claude Code documentation explains how to maximize token efficiency in coding sessions, noting that output tokens cost roughly 5x input tokens and that prompt caching reduces input costs t…
Graft, a tool that optimizes AI coding workflows, reduced Claude Code's grep token usage by 42% by filtering file search output before it reaches the language model. The hooks limit results to filenam…
AI agents can orchestrate a full software factory by treating the SDLC as a connected assembly line with specialized agents for planning, implementation, testing, and deployment, while humans act as q…
Postman's plugin for Claude Code, backed by the Postman MCP server, demonstrates two patterns for orchestrating AI agents: loops and beads, with beads enabling parallel execution of independent tasks.…
Rendemo, an interactive product demo tool, offers a free plan and flat-rate pricing starting at $39 per month, undercutting competitors like Storylane, Navattic, Arcade, and Supademo, which charge fro…
A developer has released 'the writing whip,' a Claude Code skill designed to eliminate AI writing tropes and response behaviors at the generation stage. The skill enforces strict rules against preambl…
An engineer discovered that a line of documentation in a rules file acted as a global configuration flag, overriding actual settings in a Claude Code-based multi-agent system. The false claim in the p…
DeepSeek released DeepSeek Harness, an open-source agent framework under an MIT license, on August 13, 2026, the same day it declared V4-Pro generally available. The framework, which powers DeepSeek's…