On working with coding agents
Hands-on guides to running Claude Code, Codex, Gemini CLI and other agents together, cutting cost and keeping their work in check.
October 4, 2026 · 6 min readHitting Claude Code usage limits? What to do
When Claude Code usage limits hit mid-task: track remaining usage, shrink context and set up account chains that switch within your provider’s terms.
Read the post- October 2, 2026 · 6 min read
Best AI coding tools: 18 CLI agents compared
An honest look at the best AI coding tools that run in the terminal: 18 CLI agents with vendor, command, MCP support, effort levels and how each takes a role.
- September 30, 2026 · 6 min read
AI code review: check what your agents write
Use AI code review to have a second model read agent-written code after every turn: findings with severity, file:line links and a bounded feedback loop.
- September 28, 2026 · 6 min read
Git worktrees for parallel AI agents
Use git worktrees for parallel AI agents: give each agent its own working tree, avoid conflicts and keep every turn reversible. Commands and workflow.
- September 26, 2026 · 6 min read
AI agent workflow: research, plan, then build
Split your AI agent workflow into research, plan and build stages, with handoff files, a human approval step and flow nodes that keep each agent focused.
- September 24, 2026 · 6 min read
What is an MCP server? Setup for coding agents
What is an MCP server and how do you connect one to coding agents? stdio and HTTP servers, token cost, secrets and the right scope, explained step by step.
- September 22, 2026 · 6 min read
Cut Claude Code token usage by 61%
Reduce Claude Code token usage with context profiles, /compact and a narrower tool set: a measured guide that takes the first request from 34.4k to 13.3k.
- September 20, 2026 · 7 min read
Parallel coding agents: Claude Code and Codex together
Run Claude Code and Codex side by side as parallel coding agents: split the work, avoid file conflicts with worktrees and pass output between agents.