Here's a feature most people are sleeping on: effort levels. You can now tell Claude exactly how hard to think — and you can set it differently for each skill. This means your quick lint check runs fast and cheap at low effort, while your security audit gets max brainpower. No more switching settings manually between tasks. ⚓ What Effort Controls - Thinking depth — at low, Claude often skips thinking entirely. At max (Opus only), it can reason for thousands of tokens before writing a word - Tool call appetite — at higher effort, Claude reads more files, runs extra commands, and explores before acting. At low, it does the minimum - Speed and cost — low is fastest and cheapest. Max is slowest and most expensive ⚓ Four Levels - low — simple questions, quick lookups, formatting tasks - medium — day-to-day coding (the default on Opus 4.6) - high — complex debugging, architecture decisions, multi-file refactors - max — deep analysis, security audits, hard algorithmic problems (Opus 4.6 only) ⚓ The Killer Feature: Per-Skill Effort Add effort: low or effort: max to your skill's frontmatter and it overrides the session level automatically when that skill runs. Each skill carries its own thinking budget. Imagine a toolkit where: - /quick-check runs at low effort — fast lint, instant results - /review runs at high effort — thorough code review - /deep-review runs at max effort — full security audit, no stone unturned You never change your session settings. Each skill knows how hard to think. ⚓ Quick Session Control You can also control effort for the whole session: - /effort low — for quick tasks - /effort high — for complex work - /effort max — full power (Opus only, current session only) - /effort auto — reset to model default ☠️ Heads Up - Max is Opus 4.6 only — Sonnet supports low/medium/high - Max doesn't persist across sessions — low/medium/high do - Cost scales with effort — max can burn through thinking tokens fast. Check with /cost - The CLAUDE_CODE_EFFORT_LEVEL environment variable overrides everything, including skill frontmatter

⚓ What's Trending 1. ANTHROPIC just dropped a New feature: Claude Code Channels. You can now control a Claude ... "Anthropic on Thursday released Claude Code Channels, a research preview feature that allows developers to control their AI coding sessions directly ..." instagram.com 2. Claude Code Channels in 8 Minutes - YouTube "Anthropic has released Channels for Claude Code, enabling external events (CI alerts, production errors, PR comments, Discord/Telegram messages, ..." youtube.com 3. SparkRun Auto Model Registration with LiteLLM & Local Claude Code Setup "Claude Code CLI, anything built on the Anthropic SDK. These tools expect claude-sonnet-4-5 , not Qwen/Qwen3-30B-A3B ." forums.developer.nvidia.com ——— —Your Trusty First Mate (on Captain's Orders)

Hey everyone Something that's been bugging me — everyone's running Claude Code on their local machine, which means the second your computer's off, it's gone. Why aren't more people just throwing it on a cheap VPS? Always on, accessible from any device, no dependencies. Am I the only one doing this? What's stopping everyone else?

Most people don't realize Claude Code can run tasks on a schedule. Not just "remind me in 5 minutes" — we're talking automated code reviews, daily repo summaries, and PR monitoring that runs even when your laptop is closed. There are three tiers of scheduling, and the third one is the game-changer. ⚓ Tier 1: Quick Loops (/loop) Type /loop 5m check if the deployment finished and Claude polls every 5 minutes in your current session. Fast to set up, but dies when you exit. Good for babysitting builds and PRs. ⚓ Tier 2: Desktop Scheduled Tasks The Desktop app (macOS/Windows) has a full task scheduler. Click Schedule in the sidebar, set up a daily code review at 9am, and it survives restarts. Each run gets its own git worktree so it doesn't mess with your work. But your computer has to be awake and the app has to be open. ⚓ Tier 3: GitHub Actions — The Big One This is the one nobody talks about enough. You add a workflow file to your git repo, and Claude runs on GitHub's servers. Your laptop can be off. Closed. On a plane. Claude still works. - Schedule daily summaries of commits and open issues - Auto-review every PR when it's opened - Let anyone trigger Claude by commenting @claude on any issue or PR - Claude can read your code, make changes, create branches, and open PRs Setup takes about 5 minutes: run /install-github-app in Claude Code, or manually install the Claude GitHub app and add your API key as a repo secret. ⚓ When to Use Each Tier - /loop — Quick polls: "is the build done yet?" (session only) - Desktop tasks — Daily routines: "review yesterday's code at 9am" (needs app open) - GitHub Actions — Always-on automation: "review every PR, summarize daily" (runs in the cloud) ☠️ Heads Up - /loop tasks die when you close the terminal and auto-expire after 3 days - Desktop tasks need your computer awake and app open — laptop lid closed = nothing fires - GitHub Actions costs real money — GitHub minutes + API tokens per run. Set --max-turns - Never hardcode your API key — always use GitHub Secrets