The new rules of context engineering for Claude 5 models
Iโve written previously about how to best prompt the newest generation of Claude 5 models and work with them iteratively to discover what you want to build.
19 reads.
Iโve written previously about how to best prompt the newest generation of Claude 5 models and work with them iteratively to discover what you want to build.
one more thing: Orwell's rules for Claude Code/Codex missed the AI tic i recognize on sight: ๐ฐ๐ผ๐ฟ๐ฟ๐ฒ๐ฐ๐๐ถ๐๐ฒ ๐ท๐๐ ๐๐ฎ๐ฝ๐ผ๐๐ถ๐๐ถ๐ผ๐ป.
๐๐๐ผ๐ฝ telling Claude Code/Codex "no em dashes". ๐๐๐ผ๐ฝ telling Claude Code/Codex "stop saying delve". ๐๐๐ผ๐ฝ telling Claude Code/Codex "don't sound like AI".
New in Claude Code: /checkup
Thereโs a lot of talk right now about "designing loops" instead of prompting your coding agent. If you spend some time on X trying to pin down what a loop actually is, you'll come across multiple different answers.
The clearest writing yet on why the model stopped being the bottleneck. Thariq's frame: the gap between what you asked for and what the work actually needs is where quality leaks out, and the real skill is surfacing those gaps before, during, and after you build. Worth reading twice.
Boris Cherny on living inside Artifacts: visual explanations of tricky code, system diagrams, dashboards he shares with the team, all built from the session at a private link. The signal here is a power user telling you which everyday habit actually changed how he works. Small feature, big workflow shift.
A neat idea made real: a feedback loop that catches visual slop and design-system drift while the agent builds, instead of after. It turns design consistency from a thing you ask for into a hook that runs automatically. If your agents produce frontends that look slightly off every time, this is the missing guardrail.
The best long read on why a top-tier model isn't the point. The system around it is. Loops, memory, verifier sub-agents, and state files are what make each run leave the next one smarter, and the piece lays out the whole stack with cost-routing advice for when to reach for the expensive model versus a cheap one. Long, but it's the map most people are missing.
An Anthropic engineer on two things the top model changes: self-correction loops and memory. The sharpest takeaway is that the model shouldn't grade its own work. An independent verifier explores harder and recovers from dead ends where self-critique stalls at good enough. Short, concrete, and from someone who actually ran the experiments.
The best explainer on the phrase everyone was repeating without defining. A loop is cron plus a decision-maker in the body: the model, not a hardcoded script, picks the next move each tick. The punchlines land, that the loop, not the model, is now the expensive part, and that the real asset is the skills a loop calls, not the loop itself. If you read one thing on loops, this.
A plain-English tour of the Claude features hiding in plain sight: Projects, memory, extended thinking, scheduled tasks, prompt caching, custom roles. Nothing exotic, but the value is in the framing. Each one takes minutes to set up and pays off daily. Good to forward to anyone still treating Claude as a fancier search box.
Anthropic's own writeup on building agents that do data analysis. The useful parts are the unglamorous ones: skills, clean data foundations, and evaluations. If you're wiring an agent into real business numbers, this is the part everyone skips and then regrets.
A clean way to think about agent design: the model is deliberately thin, and intelligence gets pushed outward into memory, skills, and protocols that the harness composes at runtime. The useful question it hands you is where any new capability should live. Good conceptual scaffolding if agents still feel like a bag of tricks.
The canonical piece on dynamic workflows, from the Anthropic engineer who built them. Claude writes its own custom harness on the fly to beat the failure modes of one long context window: laziness, self-preference, goal drift. The example prompts alone are worth the read, and it names the reusable patterns (fan-out, adversarial verify, tournament) you'll see everywhere else. Start here.
A design studio's field report on a real shift: the deliverable is no longer a PDF brand guide but a folder of structured files an agent can build from. The value moves upstream to the thinking, and the sharp bit is what they call magic_trick.md, the one human, left-of-center idea the system can't generate on its own. Best essay here on where human creativity stays scarce.
A genuinely good step-by-step on running Claude Code 24/7 on an always-on Mac Mini so you can text it tasks from anywhere. The best detail is the one nobody mentions: there's no message queue, so a sleeping laptop drops everything, which is the whole case for dedicated hardware. Practical if you want a personal agent that never goes dark.
A crisp reminder of what belongs in your project config. Most hand-written setup was stuff the agent can discover by reading the code. The new approach keeps only what Claude would get wrong without it: security rules, mandatory workflows, non-obvious gotchas. Delete the rest. 458 lines to 68.
The reference for anyone configuring Claude Code seriously. It walks the whole control center: CLAUDE.md, path-scoped rules, and hooks, with the key nuance that instructions are suggestions but hooks are deterministic. Keep CLAUDE.md under 200 lines or adherence drops. This is the one to bookmark.