コンテキストエンジニアリングでClaude Codeの指示を80%削減

"Jul 24, 2026"／"Most recently, we noticed a large jump in the way we prompt the newest generation of Claude models."／"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."／"Overall, we found that we were overconstraining Claude Code, both through our system prompt and in our CLAUDE.md files and skills."／"This article was written by Thariq Shihipar, member of technical staff, Anthropic." — Anthropic 公式ブログ（2026年7月24日）の日付欄・冒頭・Unhobbling Claude 節・末尾の署名より

"But when you send a message to Claude, the prompt is only a small part of the context it gets. Much of your context is assembled from your system prompt, Skills, CLAUDE.md files, memory, and other sources."／"We call this context engineering"／"Unlike a prompt, context is used generally across many requests, so it cannot be as specific."／"How do you build these general prompts and guidance for Claude, especially when you don’t know what a user’s prompt might be?"／"This can be surprisingly difficult as Claude’s own capabilities evolve." — Anthropic 公式ブログ（2026年7月24日）冒頭の段落より

"For example, when we read transcripts of our own internal usage of Claude Code, we see several conflicting messages in a single request like “leave documentation as appropriate,” or “DO NOT add comments” as our system prompt, skills, and user requests clash with each other."／"Generally, Claude can interpret the user’s intent to get to the right answer, but Claude must think more carefully about these overlapping and conflicting messages before deciding what to do."／"And while these constraints were once needed to avoid worst case scenarios, we have since found we can delete many of them and let the model use surrounding context and judgement instead." — Anthropic 公式ブログ（2026年7月24日）Unhobbling Claude 節より

"Additionally, Claude Code now has many more tools. Claude used to rely on CLAUDE.md as a source of memory, information, and guidance. Now we have memory, artifacts, and skills, which Claude can use to create new ways of loading and sharing context across sessions."／"There were a number of previous context engineering best practices that had become myths."／"Then: Give Claude rules"／"Now: Let Claude use judgement"／"Then: Give Claude examples"／"Now: Design interfaces"／"Then: Put it all upfront"／"Now: Use progressive disclosure"／"Then: Repeat yourself"／"Now: Simple tool descriptions"／"Then: Memory in CLAUDE.md files"／"Now: Auto-memory"／"Then: Simple specs"／"Now: Rich references" — Anthropic 公式ブログ（2026年7月24日）Unhobbling Claude 節と Then and now 節の各見出しより

"When we first rolled out Claude Code, we needed to be sure that Claude avoided worst case scenarios, such as deleting files."／"In code: default to writing no comments. Never write multi-paragraph docstrings or multi-line comment blocks — one short line max."／"But for a certain subset of prompts, this guidance would be wrong. In the case of documentation, the user may have their own preferences, or specific parts of very complex code might need multi-line comment blocks."／"Still, without these guardrails for older models, the comments Claude wrote would be incorrect in many cases and we had to accept this tradeoff. But newer models have better judgement and can handle these decisions well without explicit rules."／"In the new system prompt we say: Write code that reads like the surrounding code: match its comment density, naming, and idiom." — Anthropic 公式ブログ（2026年7月24日）Then: Give Claude rules の節より

"Providing context or motivation behind your instructions, such as explaining to Claude why such behavior is important, can help Claude better understand your goals and deliver more targeted responses."／"Claude is smart enough to generalize from the explanation."／"Tell Claude what to do instead of what not to do" — Claude Platform Docs「Prompting best practices」の Add context to improve performance 節と Control the format of responses 節より

"The number one rule for tool usage was to give Claude examples on how to use them. With our newest models, we’ve found that giving examples actually constrains them to a certain exploration space."／"Instead of using examples, think more about the design of your tools, scripts and files- what parameters does Claude have and how can they be more expressive?"／"For example, in the Todo tool example, just listing status as an enumeration between pending, in_progress, and completed, hints to Claude about how to use it. The instruction on keeping one item in_progress helps define our requested behavior." — Anthropic 公式ブログ（2026年7月24日）Then: Give Claude examples の節より

"Examples are one of the most reliable ways to steer Claude's output format, tone, and structure. A few well-crafted examples (known as few-shot or multishot prompting) improve accuracy and consistency." — Claude Platform Docs「Prompting best practices」の Use examples effectively 節より

"Because Claude Code was focused on coding, our system prompt included detailed information on how to do code review and verification. These were not always needed, but when they were, it was crucial information."／"Since then, Claude Code has gotten very competent at using progressive disclosure- loading the right context at the right times. For example, we moved verification and code review into their own skills that Claude Code could selectively call."／"But progressive disclosure is not just for skills, we also use it for tools. Some of our tools are ‘deferred loading,’ which means the agent must search for their full definitions using ToolSearch before using them. This allows us to have more tools (such as our Task tools) that don’t take up context until they’re needed."／"The same can be applied to your own CLAUDE.md and Skill.md files. A common myth is that you want to make these a central repository for every known practice that you might run into, because Claude would not find it otherwise. Instead, consider having a tree of files that can be loaded at the right time" — Anthropic 公式ブログ（2026年7月24日）Then: Put it all upfront の節より

"Earlier Claude models could sometimes need repeated instructions or be more likely to listen to instructions at the end of their context window than at the start. This meant our system prompt would sometimes have references to tools in the main system prompt as well as instructions in the tool description."／"We found we could delete these repeat examples and put instructions on how to use tools in the tool descriptions rather than the system prompt." — Anthropic 公式ブログ（2026年7月24日）Then: Repeat yourself の節より

"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." — Anthropic 公式ブログ（2026年7月24日）Then: Memory in CLAUDE.md files の節より

"In plan mode, Claude Code has heavily relied on markdown files with plans. Storing these files as plans helped Claude refer to them when needed. Another similar best practice was to store specs in the codebase for Claude to refer to while working across longer projects."／"But we’ve found that Claude can handle increasingly more complicated references. Instead of simple markdown files, Claude can reference HTML artifacts created by our new artifacts feature."／"You may also give Claude references in the form of code. A spec may also be a detailed test suite, or a function in a different codebase that Claude might port."／"Rubrics are another form of references. Rubrics allow Claude to try and verify your taste in a particular field (e.g. what does a good API design look like) by using dynamic workflows and spinning up verifier agents with those rubrics." — Anthropic 公式ブログ（2026年7月24日）Then: Simple specs の節より

"Pulling this all together, what does this look like when you assemble your context?"／"A system prompt is heavily tied to the product context. It tells Claude what product it’s operating in and what it’s doing. For Claude Code, you will likely never modify this, but if you are building your own agent harness, this is where you should spend a lot of time."／"You can @ mention files to include them as references. References allow Claude to refer to in-depth information about the current plan."／"This might be in specs files, mockups, or even entire codebases. 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. For example, a HTML mockup of a design will generally produce better results than a description of the design or a screenshot." — Anthropic 公式ブログ（2026年7月24日）Applying this to your context 節の System Prompt と References より

"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. For example, you may organize your code to keep types in one monolithic file and nowhere else. Avoid stating ‘the obvious’ things Claude should know by looking at your file system or your repo."／"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." — Anthropic 公式ブログ（2026年7月24日）Applying this to your context 節の CLAUDE.md より

"Think of skills as lightweight guides to let Claude find information when needed. Avoid making them overconstrained, except in highly important areas."／"For long skills, try and use progressive disclosure as much as possible- divide it into many files and split them out."／"It’s best when skills encode particular opinions, knowledge, or best practices that are particular to you, your team, or product." — Anthropic 公式ブログ（2026年7月24日）Applying this to your context 節の Skills より

"We’ve put these best practices in claude doctor; use the command /doctor in Claude Code to rightsize your skills, and CLAUDE.md files."／"Across your system prompt, skills, and CLAUDE.md files, you may need to simplify just like we did."／"We rolled out a new command called claude doctor, which will help you do this automatically as well. For more details on prompting more advanced models specifically, check out our Fable field guide" — Anthropic 公式ブログ（2026年7月24日）冒頭と Try simplifying 節より

"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."／"Still, without these guardrails for older models, the comments Claude wrote would be incorrect in many cases and we had to accept this tradeoff." — Anthropic 公式ブログ（2026年7月24日）冒頭と Then: Give Claude rules の節より

"Where a technique names a specific model, treat it as measured on that model and re-check it against your own evals before applying it to another."／"Claude Opus 4.5 and Claude Opus 4.6 are also more responsive to the system prompt than previous models. If your prompts were designed to reduce undertriggering on tools or skills, these models may now overtrigger. The fix is to dial back any aggressive language." — Claude Platform Docs「Prompting best practices」の General principles 節と Tool usage 節より