Blog

Use Claude to plan and critique your landing page, then build it in Framer. Includes a reusable brief, responsive checks and an SEO launch checklist.

ant apply, added in ant CLI 1.30.0, creates and updates Claude API agents, environments, skills and deployments from files in your repository, with a lockfile and a plan you approve.

Claude Code's diff panel, added in v2.1.260, opens beside the conversation in fullscreen mode and updates live as Claude edits files, with a fallback to the older diff viewer.

Claude Code reports whether your organisation's policy loaded through two lines, Organization policy and Managed settings (remote). Here is what each means and how to fix a failed load.

A new headless-mode flag reads the text appended to every subagent's system prompt from a file instead of the command line, for prompts too large to pass as an argument.

Two new Claude Code settings raise how much command and background-task output reaches Claude inline before it gets saved to a file, up to 128K characters.

/skill-doctor shows which loaded skills go unused and what they cost in context, giving you a direct way to prune a bloated skill listing without guessing.

Codex CLI's 0.153 line added Vim undo and redo, remote plugin marketplace management, a configurable auto-recap setting, and catalog support for GPT-6-Astra.

Claude Code's advisor tool pairs your main model with a stronger advisor it consults mid-task at decision points, set with /advisor, an advisorModel setting, or a --advisor flag.

Claude Code's --permission-prompts none flag denies anything that would need a person to answer, instead of hanging a scheduled or unattended run waiting for input that never comes.

Claude Code's timeFormat and timeZone settings control how times are written across the interface: 12-hour, 24-hour, 24-hour UTC, a custom strftime pattern, or a specific IANA time zone.

How Claude Code's own plugin system works: marketplaces, installing plugins that bundle skills, agents and MCP servers, and applying changes with /reload-plugins without restarting.

Claude Code now prompts once in auto mode before its first file read outside your working directories, and permissions.blockReadsOutsideWorkingDirectories lets you turn that into a standing block.

Claude Code v2.1.257 added a Containment Escape rule to auto mode's classifier, blocking cloud metadata-credential fetches, egress evasion, and cross-tenant reach unless your environment marks them expected.

Claude Code's new managedMcpServers managed setting lets organizations push HTTP and SSE MCP servers to every user through ordinary managed settings, no MDM-deployed file required.

Claude Code's CLAUDE_CODE_SUBAGENT_MODEL_FORCE environment variable pins every subagent, teammate and workflow agent to one model, overriding per-spawn requests and agent-definition overrides.

The Admin API landed in the ant CLI and seven language SDKs on 26 August 2026 under client.beta.organization. Here's what it covers, what still needs curl, and how to authenticate it.

Anthropic's own guidance for defining custom tools on the Claude API and Claude Managed Agents comes down to four rules, and the first one is the same lever that makes or breaks an agent skill.

Claude Fable 5.1 shipped 1 September 2026 as the default Fable model, with a quarter-price cache read and three breaking changes for anyone calling Claude Fable 5 today.

Codex CLI's hooks system gained async execution, MCP tool access, an Interrupt event, tool-result rewriting and per-tool output limits across five releases. Here's every change in order.

Claude's browser use tool drives a webpage through its accessibility tree and element references, not just screenshots. Here's how it works and when to reach for it over computer use.

The claude-api skill's cost-optimize subcommand profiles a project's Claude API spend and proposes savings, caching first, one measured change at a time, instead of generic advice.

Claude Managed Agents' web_search and web_fetch tools now accept allowed_domains and blocked_domains, each with its own list. Here's the exact config shape and validation rules.

modelPicker lets you replace or extend Claude Code's built-in /model picker with your own ordered, labelled list of models, ideal for teams standardising on specific Bedrock or Vertex deployments.