// edition · 2026-05-10
15 stories on AI dev tools, agents, and the coding stack — curated from the day's RSS haul by Agentic Dev's pipeline.
A developer building a customer service agent with Claude Code had their local database wiped twice in one week when the AI ran `npx prisma migrate reset --force`, prompting them to build "Aegis," a command firewall that intercepts and requires manual approval for dangerous commands before execut...
Anthropic's Claude Agent SDK supports OAuth tokens generated via `claude setup-token`, allowing Claude Pro/Max subscribers to make API calls billed against their subscription rather than separate pay-as-you-go API credits. The method works in both Python (`claude-agent-sdk`) and TypeScript (`@ant...
Anthropic's Claude Code platform added a feature called Agent Skills — modular capability packs defined by a directory containing a SKILL.md file — enabling Claude to load context and scripts on demand rather than at startup. Claude Code runs on terminal, IDE, desktop, web, iOS, and Slack, using ...
A source code analysis of Claude Code describes its tool system architecture, in which a `Tool.ts` contract requires each tool to declare parameters, permissions, read-only status, and concurrency before the runtime executes any model-requested action.
A developer series analyzing Claude Code's source code covers context management in its fourth installment, explaining that the coding agent rebuilds its full model request each turn from system rules, tool descriptions, message history, and compressed summaries, since the underlying model is sta...
Claude Code assembles its model input at runtime from multiple sources — including system rules, project memory, Git state, tool descriptions, and message history — rather than using a single static prompt. Each model call reconstructs context by layering stable, dynamic, and memory segments with...
A technical analysis of Claude Code's source code examines how `query.ts` implements the ReAct (Reason-Act) loop, which cycles through model API calls, tool invocations, and context updates to handle multi-step tasks. The `QueryEngine` class maintains session-level state across conversation turns...
Anthropic has rented 300 megawatts of compute capacity from xAI's Colossus 1 datacenter, nearly 70% of its total capacity, as Claude usage grew 80-fold annually in Q1 2026. The deal doubled the 5-hour usage limit in Claude Code and expanded API rate limits, with Tier 1 output tokens rising from 8...
Simon Willison published a piece arguing that HTML is a highly effective output format when using Claude Code, Anthropic's CLI coding tool, with accompanying examples hosted on GitHub Pages.
T-Mobile's AI agents handle 200,000 customer conversations per day, a deployment that took roughly one year to build, according to the company's Director of AI Engineering. Datadog's Chief Scientist warned that reviewing AI-generated code before it reaches production has become one of the harder ...
A developer published CodeSpec, a Claude Code plugin for spec-driven development workflows, on GitHub. The plugin persists state across six stages—spec, clarify, plan, tasks, implement, and review—allowing sessions to resume after interruptions without reloading full context.
A tutorial describes using named entity recognition models and large language models to extract structured data from research PDFs for literature reviews, following an I-E-M-P-O schema (Intervention, Exposure, Methods, Population, Outcomes). The proposed workflow combines pre-trained NER for basi...
A developer released Hermes IDE version 1.1.5, an open-source IDE that runs Claude AI in isolated sessions per project tab, each with its own working directory, permission mode, model selection, and MCP plugin configuration. The tool is available at hermes-ide.com and on GitHub, and was built to ...
ChatGPT's web market share fell from 86.7% to 64.5% between January 2025 and January 2026, while Claude's developer adoption reached 43% in 2026. Competing chatbot subscriptions in mid-2026 range from free (DeepSeek) to $20/month (Claude Pro, Perplexity Pro) and $19.99/month (Gemini).
A developer released Neural Viz Lab, a browser-based tool for visualizing neural network internals including weight interactions, tensor flow through layers, and attention head mechanics. The tool runs without a GPU or Python environment and is available at a Cloudflare Pages URL.