AI CODING

AI code review is the new bottleneck as coding agents outpace reviewers. Build review systems around reproduction, small diffs, tests and receipts.

Claude Agent SDK credits split programmatic agent usage from subscription usage on June 15. What changed and how to budget agent work in separate lanes.

Claude Code's newer plugin URL and hard-deny controls are small release-note items with a big implication: agent extensions now need supply-chain discipline.

Codex CLI 0.129.0 added modal Vim editing to the composer. A small feature, but a signal: terminal agents are becoming native engineering workbenches.

Matt Pocock's skills repo is a signal for AI coding teams: treat skills as governed production controls, not a folder of viral prompts.

Codebase graphs like Graphify give coding agents a durable map of how code, docs, schemas and decisions connect, so long runs stop rediscovering the repo.

InsForge is an open-source backend for agentic coding. Why agents still break databases, auth and deploys, and what an agent-readable control plane needs.

Five new apps and a Chrome extension shipped today. Here is what each one does, who it is for, and why we built them in a single sweep.

Terminal agents like Claude Code, Codex CLI and OpenCode are converging on one runtime layer: permissions, sandboxing, rollback, receipts and cost controls.

Cline is a free, open-source VS Code extension for agentic AI coding. Bring your own model, a cloud API or a local one via Ollama, with no vendor lock-in.

Claude Code token burn is an observability problem. Why coding agents need cache-hit telemetry, spend ceilings and repro-grade usage logs, not a quota bar.

Claude Code 2.1.128 is an ops release: fixes for MCP, worktrees, OTEL, plugins and permissions that matter for teams running coding agents every day.

Codex SDK vs Codex CLI vs the Codex GitHub Action: when to use each surface, and how to avoid building the same agent loop three times.

The trending Free Claude Code repo is not just about avoiding API bills. It points at a bigger developer-tool pattern: model gateways for AI coding agents.

OpenAI's May 8 macOS certificate rotation for ChatGPT, Codex, Codex CLI and Atlas, and a runbook for how teams should govern AI developer tool updates.

Agent skills work when they carry exit criteria. What Addy Osmani's agent-skills repo gets right about turning AI coding advice into engineering checklists.

GitHub Copilot cloud agent updates add usage metrics, session visibility, validation and review quality - the layer teams need to manage agent adoption.

Google's skills repo shows the next agent playbook: product-specific operating instructions that turn docs into executable procedures for coding agents.

Parallel coding agents only speed you up with merge discipline: clean task ownership, review receipts and a single merge owner instead of cleanup work.

Karpathy CLAUDE.md skills went viral as coding-agent rules. Treat them as a menu: turn the four principles into repo-specific operating constraints.