Atlas

The Atlas blog

Building software with AI coding agents

What's new in AI coding, explained plainly. Guides for founders, product owners and testers who work with an AI team, and hands-on how-tos for the engineers who run Claude Code and OpenAI Codex.

RSS
  1. Plain EnglishWhat's newClaude Code Review Levels: Quick, Standard and DeepClaude Code Review now has Quick, Standard and Deep levels and a switch for a whole GitHub organization. What changed on 19 Oct 2026 and what to check. · 6 min read
  2. TechnicalHow-toAGENTS.md and CLAUDE.md: One Instruction File for BothUse one AGENTS.md for Claude Code and Codex: how each tool finds the file, the import and symlink options, size limits, and how to check what loaded. · 7 min read
  3. Plain EnglishExplainerWhat AI Coding Agents Can and Cannot Do: A Plain GuideWhat can an AI coding agent do for your product, and where does it still need a person? A plain-English guide with everyday examples for non-coders. · 7 min read
  4. Plain EnglishWhat's newClaude Code Hooks Can Now Fail Closed: What It MeansClaude Code 2.1.295 lets a safety check block an action when the check itself breaks. Here is what changed, why it matters and what to ask your team. · 7 min read
  5. TechnicalHow-toClaude Code Rewind: Undo AI Edits with CheckpointsHow Claude Code checkpoints and /rewind restore code, conversation or both, what they can't undo (Bash, most subagent edits), and how to pair them with git. · 7 min read
  6. Plain EnglishExplainerHow Much Does an AI Coding Agent Cost? A Plain GuideWhat an AI coding agent costs: flat plans versus pay-per-use, Anthropic's published Claude Code averages, why bills climb, and habits that keep spending in check. · 6 min read
  7. Plain EnglishWhat's newClaude Code Forked Subagents Now On by DefaultClaude Code 2.1.302 (16 Oct 2026) turns on forked subagents in headless runs, the Agent SDK, desktop and VS Code. What a fork is and what to check. · 6 min read
  8. TechnicalHow-toClaude Code Plan Mode and Verification WorkflowA step-by-step Claude Code workflow: explore in plan mode, write a spec, give the agent a check it can run, then review in a fresh context before you commit. · 7 min read
  9. Plain EnglishExplainerAI Coding Agent Risks and How to Reduce ThemIs an AI coding agent safe? A plain-English guide to what can go wrong, from deleted files to leaked passwords, and the simple controls that lower the risk. · 7 min read
  10. Plain EnglishWhat's newCodex GPT-5.5 Retirement: What Your Team Should CheckOpenAI retired GPT-5.5 from Codex for ChatGPT sign-ins on 14 October 2026. Here is what changed, who is affected and what to check before work breaks. · 6 min read
  11. TechnicalHow-toClaude Code Permissions: Allow, Deny Rules and ModesSet up Claude Code permissions that hold: how allow, ask and deny rules are ordered, which mode to pick, and the Bash rule traps that let commands slip through. · 6 min read
  12. Plain EnglishHow-toHow to Brief an AI Coding Agent: A Plain-English GuideHow to brief an AI coding agent without writing code: what to put in the request, how to define "done", and the common mistakes that cost you rework. · 7 min read
  13. Plain EnglishWhat's newClaude Code Idle Compaction: Cheaper Breaks, Same SessionClaude Code 2.1.299 (14 Oct 2026) now compacts very long idle chats before the one-hour cache runs out. What changed, the trade-off, and how to turn it off. · 6 min read
  14. TechnicalExplainerClaude Code Skills: Turn Repeated Prompts into CommandsClaude Code skills turn a checklist you keep pasting into a reusable /command. Covers SKILL.md, arguments, shell injection and tool permissions. · 6 min read
  15. Plain EnglishHow-toHow to Check AI-Built Software When You Don't Write CodeYou can't read the code, but you can still tell whether an AI agent's work is good. Ask for evidence, set pass/fail checks, and try the edge cases yourself. · 6 min read
  16. Plain EnglishWhat's newClaude Haiku 5.5: What the Cheapest Claude Means for TeamsClaude Haiku 5.5 arrived on 7 October 2026 with a 1M-token window at $0.10 per million input tokens. What it is good for, what it is not, and how to test it. · 8 min read
  17. TechnicalExplainerMCP Servers in Claude Code: Connect Databases and ToolsHow MCP servers work in Claude Code: add local and remote servers, choose a scope, handle OAuth and secrets, limit context use and lock them down for a team. · 7 min read
  18. TechnicalHow-toClaude Code Costs: Cut Token Usage and Stretch LimitsWhere Claude Code spends tokens and how to cut it: /usage, model and effort choice, /clear vs /compact, prompt cache lifetime and team spend limits. · 10 min read
  19. TechnicalHow-toAI Code Review with Claude Code: What It Catches and MissesSet up AI code review in Claude Code with /code-review, ultrareview, managed Code Review or GitHub Actions, and learn what it catches, misses and costs. · 9 min read
  20. TechnicalHow-toClaude Code Headless in CI: -p Mode and Safe PermissionsRun Claude Code headless in CI with claude -p: bare mode, dontAsk and allowedTools permissions, JSON output, exit codes and cost caps for unattended jobs. · 9 min read
  21. TechnicalHow-toClaude Code Subagents: When to Split Work and HowWhen Claude Code subagents help and when they don't: writing the agent file, choosing tools and models, and catching frontmatter mistakes that fail silently. · 9 min read
  22. TechnicalHow-toClaude Code Hooks as Guardrails: Block, Format, TestUse Claude Code hooks to block risky shell commands, protect files, format every edit and keep Claude working until tests pass, with configs you can copy. · 7 min read
  23. TechnicalComparisonClaude Code vs Codex for Teams: A Workflow ComparisonClaude Code vs OpenAI Codex for engineering teams: instruction files, permissions, hooks, CI, cloud tasks and PR review compared, and when to pick which tool. · 9 min read
  24. TechnicalHow-toCodex CLI Setup: Install, Approval Modes and SandboxingSet up OpenAI Codex CLI: install it, sign in, write a config.toml and profile files, and choose the sandbox mode and approval policy for each kind of task. · 8 min read