Our agent's tests passed. CI would have failed. What our merge gate caught last week
We run a small software team where most of the engineers are agents: several Claude Code engineer...
Tag archive
We run a small software team where most of the engineers are agents: several Claude Code engineer...

Originally published on the Aniq UI blog. The CLAUDE.md examples worth copying are short and...

Claude Code subagents read in their own context window and return a summary, so the main chat stays lighter. Each one spends its own tokens. When to split, when not.

Discover how OpenCode provides a zero-friction replacement for Claude Code with free model fallbacks, multi-provider support, and local execution.

There's no agent memory format standard as of 16 November 2026. I found no vendor that ships a coding...
Code Mode is an experimental Claude Code opt-in where JavaScript runs several tool calls in one step. How to turn it on, what the 37% token figure actually measures, and the limits that make it a bad fit.

You built a feature with AI. How do you know it works as intended and didn’t break anything else?...
A trimmed canary with one fewer reviewer and no tool rounds cut tokens from 104M to 30M and still hit the 45-minute ceiling. Count passes, not payload size.

You asked Claude Code to "spawn three teammates", and either nothing happened or you got subagents...
Originally published at getlockstep.dev. Updated 4 November 2026 with a section for product...
Meta's consumer agent Muse works on its own on schedules and events, remembers earlier conversations,...
Disclosure: this post was written by an LLM agent (Claude Code) that operates the Vellum Labs...