CLAUDE CODE

claude.dev's Opus 5.5 playbook says to name the finish line, delete 'think hard' lines and write stop rules into CLAUDE.md. What each tip changes, plus what 130 Hacker News comments say about where long runs go wrong.

CC Switch is an open-source desktop app that switches API providers for Claude Code, Codex, Gemini CLI and seven other agents in one click, and syncs MCP servers, skills, and prompts between them. Here is what it does, how to install it, and how to use it safely across Claude Code and Codex.

Superpowers is an MIT-licensed skills plugin that gives Claude Code a full development methodology: brainstorm, plan, TDD, subagent execution, and review. Here is how to install it from the official marketplace, what each skill does, and when it is worth the overhead.

Claude Code is Anthropic's agent for software engineering; Claude Cowork is the same agent loop pointed at documents, spreadsheets, and research. Both come with every paid Claude plan from $17/month. Here is how to pick, with a verified September 2026 pricing table.

Claude Sonnet 5.5 (claude-sonnet-5-5) is Anthropic's new mid-tier model: $2/$10 per million tokens, 70.6% on Terminal-Bench 4.0, 1M context, now GA in GitHub Copilot and on Vercel AI Gateway. The pricing math, the five breaking API changes, and where it fits next to Opus 5.5 and Sonnet 5.

The HeyGen CLI lets Claude Code and Codex create, fetch, and download AI avatar videos from the terminal. Here is the verified setup for both agents, the official skills install, the commands the video relies on, and where the workflow is worth using.

You cannot install Claude Code or Codex inside the Meta Muse app, but you can run both agents on Muse Spark 1.3 through the Meta Model API, use Muse Spark from OpenCode Go, and bring your Claude Code and Codex setup into Muse Code. Here are the verified configs.

OpenClaw is an open-source, self-hosted personal AI agent you run on your own machine and reach through chat apps like Telegram, Slack, Discord, and WhatsApp. This guide covers install, onboarding, OpenClaw skills and ClawHub, the OpenClaw MCP server, using it with Claude Code, and running it on local models with Ollama.

Claude Opus 5.5 (claude-opus-5-5) is Anthropic's new default Opus: $4/$20 per million tokens, $0.20 cache reads, 1M context, thinking always on with medium default effort. Runnable TypeScript and Python SDK examples, Claude Code setup, before/after prompts, and a decision guide vs Sonnet 5, Haiku 4.5, and Fable 5.1.

Claude Code 2.1.269 adds plugin evals, baseline comparisons, JSON and HTML reports, and CI gates. That changes plugins from clever prompts into measurable agent infrastructure.

The Rime CLI streams natural-sounding text-to-speech straight from your terminal, so Claude Code, Codex, Devin, and OpenCode can end each step with a brief spoken summary plus a next-step question. Install, commands, flags, and the agent prompt pattern behind the demo.

A decision-intent comparison of pi, Claude Code, OpenCode and Codex CLI as your main agentic coding harness in late 2026, with a verified capability matrix and pick-X-if verdicts.

Claude Code and Codex can build a website in minutes, but the result often looks generic and obviously AI-generated. Higgsfield's MCP and CLI put Nano Banana Pro and Seedance inside the agent loop, so your coding agent generates its own food imagery, hero video, and visual polish before it ships the site.

dontpastetheai.com, Vomit, and NoBuzz hit Hacker News in the same week. A social contract, a local rewrite, and a second-model Claude Code skill - compared with a table and a when-to-stay guide.

Slack Code puts coding agents in dedicated Slack channels with diffs, live HTML previews, and an audit log. Here is when that beats a local Claude Code session, Cursor, or OpenCode - and when to skip it.

Anthropic confirms that every Claude model released after August 2, 2026 embeds a machine-readable watermark in generated text and attaches C2PA provenance metadata to generated files, across the API, Claude Code, Cowork, and Tag. Detection tooling for third parties is coming, but details are not published yet.

Claude Code v2.1.224 lets one running session message another over a first-party channel - plain text, permission-aware, with approval dialogs when bypass-mode sessions talk to each other. Here is what ships, how delivery and inbound controls work, and where the feature stops.

Prime Intellect open-sourced Prime Agent on August 5, 2026. It gives the model exactly one tool - a persistent IPython kernel - and lets the harness rewrite its own prompts, skills, memory, and sub-agents mid-run. Here is how it works, what the benchmarks actually show, a full provider and model guide, and an honest comparison to Claude Code, Codex, OpenCode, OpenClaw, Hermes, and Pi.

Self-improving applications shift the economics of maintenance. Instead of per-token pricing, you pay per closed issue - and the closed loop (user feedback to GitHub issue to Codex scheduled task to reviewed PR) means the cost is predictable, the fixes are testable, and the human is in the merge decision, not the implementation.

A new arXiv benchmark ran 6,560 sandboxed runs across Claude Code, Codex, OpenClaw, and Hermes with five LLMs. 68% of runs triggered unsafe signals, and 66% of all runs were unsafe yet still passed completion checks. Task completion does not prove an agent ran safely.