Context engineering for Claude 5: what changes for teams Anthropic removed over 80% of Claude Code's system prompt for models like Claude Opus 5 and Claude Fable 5 with no measurable loss on its coding evaluations, according to a July 24, 2026 post by Thariq Shihipar titled "The new rules of context engineering for Claude 5 generation models." The post advises teams to keep a lightweight CLAUDE.md focused on codebase gotchas, replace rigid rules with judgment-based guidance, move detail into skills, and use auto memory instead of hand edits; Claude Code 2.1.206 or later adds a /doctor command that proposes trims to checked-in CLAUDE.md files. Blog Context engineering for Claude 5: what changes for teams Published: September 23, 2026 Anthropic's July 24, 2026 post says newer Claude models need less instruction, not more. It cut over 80 percent of Claude Code's system prompt with no measurable eval loss. For team files that means a short CLAUDE.md of gotchas, judgment over rigid rules, detail moved into skills, and auto memory in place of hand edits. The post is “The new rules of context engineering for Claude 5 generation models” https://claude.dev/blog/the-new-rules-of-context-engineering-for-claude-5-generation-models/ by Thariq Shihipar. This note reads it for teams: what to change in the files you commit, and the one question it leaves open. What did Anthropic change in Claude Code's system prompt? It deleted most of it. The opening claim: “We removed over 80% of Claude Code's system prompt for models like Claude Opus 5 and Claude Fable 5 with no measurable loss on our coding evaluations.” The reason given is not token cost. It is that instructions collide. When the system prompt, a skill, and the user each say something slightly different, “Claude must think more carefully about these overlapping and conflicting messages before deciding what to do.” Rules written to correct an older model's habits become friction for a newer one that did not have the habit. This follows Anthropic's September 2025 essay on effective context engineering https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents , which set the goal as “the smallest possible set of high-signal tokens that maximize the likelihood of some desired outcome.” The July post is the same idea applied to their own prompt, with a number attached. What should go in CLAUDE.md now? Less. The post's advice is specific: “Keep your CLAUDE.md lightweight and briefly describe what your repo is for, but spend most of the tokens on gotchas inside of the codebase.” A gotcha is something the model cannot infer from the tree. That the test command is pnpm test is inferable from package.json . That payment webhooks must dedupe on the provider's event ID before any write, because of a double refund your team argued about in eng-payments , is not. The first line is noise. The second is the reason the file exists. The docs back this with tooling. /doctor now proposes trims for a checked-in CLAUDE.md : it cuts directory layouts, dependency lists and architecture overviews Claude can derive, and keeps “pitfalls, rationale, and conventions that differ from tool defaults” Claude Code 2.1.206 or later, per the memory docs https://code.claude.com/docs/en/memory , checked 2026-09-23 . Judgment over rules: what does that look like? The post shows an old line from Claude Code's own prompt. It told Claude to default to writing no comments and never to write multi-line comment blocks, one short line at most. Its replacement: “Write code that reads like the surrounding code: match its comment density, naming, and idiom.” The first is a rule that is wrong wherever the codebase disagrees with it. The second tells the model what to look at and trusts it to look. For team files the move is the same. “Never use any ” is a fine rule. “Always put handlers in src/api/handlers/ ” is fine until the day someone moves them, after which it is a rule that fights the code. The post also warns off examples: “giving examples actually constrains them to a certain exploration space.” Where you need precision, it prefers code: “Generally you should prefer files that are in code as it provides clear, high-fidelity instructions to Claude in a language it knows very well.” A test that fails on a missing dedupe check says more than a paragraph about idempotency. What is progressive disclosure in Claude Code? Loading detail only when the task needs it. The post: “Use progressive disclosure heavily, for example if you have several unique instructions on how to verify your work, create a verification skill and reference it from your CLAUDE.md.” Claude Code itself does this with tools: some are “deferred loading,” so the agent searches for their definitions before it uses them. In practice there are three layers. CLAUDE.md is always on. Path-scoped rules in .claude/rules/ arrive when Claude reads a matching file. Skills send a name and description every turn and the body only when invoked. The trade is that anything behind a trigger can be missed when the trigger does not fire; which layer suits which rule is laid out in CLAUDE.md vs skills vs hooks https://gethrbr.com/blog/claude-md-vs-skills-vs-hooks . Does auto memory replace CLAUDE.md? For personal learnings, yes. The post: “We used to encourage users to save things to Claude's memory, by using the hotkey to write to their CLAUDE.md automatically. Instead, Claude now automatically saves memories that are relevant to the work and to you.” For the team, no, and the docs say why. Auto memory lives in ~/.claude/projects/