10 ファイル変更+25-24
この更新の概要
各モデルのプロンプトエンジニアリング指針や、エージェントループ、ワークフロー設計に関する公式ブログ記事への参照リンクが多数追加されました。Windows環境でのインストールエラーに関するトラブルシューティングが更新され、証明書の失効確認を回避する具体的なPowerShellコマンドが提示されています。設定ファイルにおけるスキルリストの予算管理や文字数制限の項目から、特定のバージョン制限に関する記述が削除されました。
@@ -147,16 +147,16 @@ Claude Fable 5 is generally available on the Claude API, Claude Platform on AWS,
## Prompt and output performance
Claude 4 models excel in:
Current Claude models excel in:
* **Performance:** Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing. See the [Claude 4 blog post](https://www.anthropic.com/news/claude-4) for more information.
* **Performance:** Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing. See [Prompting Claude Sonnet 5](/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5) and [Prompting Claude Opus 4.8](/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-4-8) for model-specific prompting guidance.
* **Engaging responses:** Claude models are ideal for applications that require rich, human-like interactions.
* If you prefer more concise responses, you can adjust your prompts to guide the model toward the desired output length. Refer to the [prompt engineering guides](/docs/en/build-with-claude/prompt-engineering) for details.
* For prompting best practices, see [Prompting best practices](/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices).
* **Output quality:** When migrating from previous model generations to Claude 4, you may notice larger improvements in overall performance.
* **Output quality:** When migrating from a previous model generation, you may notice larger improvements in overall performance.
## Migrating to Claude Opus 4.8
@@ -423,4 +423,4 @@ Now that you understand the loop, here's where to go depending on what you're bu
- **Need tighter control over what the agent can do?** Lock down tool access with [permissions](/en/agent-sdk/permissions), and use [hooks](/en/agent-sdk/hooks) to audit, block, or transform tool calls before they execute.
- **Running long or expensive tasks?** Offload isolated work to [subagents](/en/agent-sdk/subagents) to keep your main context lean.
For the broader conceptual picture of the agentic loop (not SDK-specific), see [How Claude Code works](/en/how-claude-code-works).
For the broader conceptual picture of the agentic loop (not SDK-specific), see [How Claude Code works](/en/how-claude-code-works). For a practical guide to designing loops in Claude Code, from turn-based to goal-based and proactive loops, see [Loop engineering: getting started with loops](https://claude.com/blog/getting-started-with-loops) on the blog.
@@ -7,7 +7,7 @@ source: https://code.claude.com/docs/en/agent-sdk/overview.md
> Build production AI agents with Claude Code as a library
Build AI agents that autonomously read files, run commands, search the web, edit code, and more. The Agent SDK gives you the same tools, agent loop, and context management that power Claude Code, programmable in Python and TypeScript.
Build AI agents that autonomously read files, run commands, search the web, edit code, and more. The Agent SDK gives you the same tools, agent loop, and context management that power Claude Code, programmable in Python and TypeScript. For the thinking behind agent harness design, see [A harness for every task: dynamic workflows in Claude Code](https://claude.com/blog/a-harness-for-every-task-dynamic-workflows-in-claude-code) on the blog.
```python Python theme={null}
import asyncio
@@ -64,7 +64,7 @@ The same triggers tell you when to update what you already have. A repeated mist
### Compare similar features
Some features can seem similar. Here's how to tell them apart.
Some features can seem similar. For a deeper walkthrough of choosing between them, see [Steering Claude Code: when to use CLAUDE.md, skills, hooks, and subagents](https://claude.com/blog/steering-claude-code-skills-hooks-rules-subagents-and-more) on the blog. Here's how to tell them apart.
Skills and subagents solve different problems:
@@ -18,6 +18,8 @@ For the `model` setting in Claude Code, you can configure either:
- Microsoft Foundry: a deployment name
- Google Cloud's Agent Platform: a version name
For guidance on which model and effort level fit different kinds of work, see [Choosing a Claude model and effort level in Claude Code](https://claude.com/blog/claude-model-and-effort-level-in-claude-code) on the blog.
`ANTHROPIC_BASE_URL` changes where requests are sent, not which model answers them. To route Claude through an LLM gateway, see [LLM gateways](/en/llm-gateway).
### Model aliases
@@ -19,19 +19,19 @@ To install Claude Code, use one of the following methods:
**macOS, Linux, WSL:**
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null}
curl -fsSL https://claude.ai/install.sh | bash
```
**Windows PowerShell:**
```powershell theme={null}
```powershell theme={null} theme={null} theme={null} theme={null}
irm https://claude.ai/install.ps1 | iex
```
**Windows CMD:**
```batch theme={null}
```batch theme={null} theme={null} theme={null} theme={null}
curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd
```
@@ -43,7 +43,7 @@ If the install command fails with `syntax error near unexpected token '<'`, a `4
Native installations automatically update in the background to keep you on the latest version.
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null}
brew install --cask claude-code
```
@@ -51,7 +51,7 @@ Homebrew offers two casks. `claude-code` tracks the stable release channel, whic
Homebrew installations do not auto-update. Run `brew upgrade claude-code` or `brew upgrade claude-code@latest`, depending on which cask you installed, to get the latest features and security fixes.
```powershell theme={null}
```powershell theme={null} theme={null} theme={null} theme={null}
winget install Anthropic.ClaudeCode
```
@@ -191,6 +191,7 @@ Once you've installed Claude Code, these guides help you go deeper.
- [Quickstart](/en/quickstart): walk through your first real task, from exploring a codebase to committing a fix
- [Store instructions and memories](/en/memory): give Claude persistent instructions with CLAUDE.md files and auto memory
- [Common workflows](/en/common-workflows) and [best practices](/en/best-practices): patterns for getting the most out of Claude Code
- [A harness for every task](https://claude.com/blog/a-harness-for-every-task-dynamic-workflows-in-claude-code): how the Claude Code team uses [dynamic workflows](/en/workflows) to orchestrate subagents at scale
- [Settings](/en/settings): customize Claude Code for your workflow
- [Troubleshooting](/en/troubleshooting): solutions for common issues
- [code.claude.com](https://code.claude.com/): demos, pricing, and product details
@@ -284,8 +284,6 @@ Plugins can declare background monitors that Claude Code starts automatically wh
Plugin monitors use the same mechanism as the [Monitor tool](/en/tools-reference#monitor-tool) and share its availability constraints. They run only in interactive CLI sessions, run unsandboxed at the same trust level as [hooks](#hooks), and are skipped on hosts where the Monitor tool is unavailable.
Plugin monitors require Claude Code v2.1.105 or later.
**Location**: `monitors/monitors.json` in the plugin root, or inline in `plugin.json`
**Format**: JSON array of monitor entries
@@ -288,8 +288,8 @@ This tolerance applies only to managed settings. User, project, and local settin
| `showClearContextOnPlanAccept` | **Default**: `false`. Show the "clear context" option on the plan accept screen. Set to `true` to restore the option | `true` |
| `showThinkingSummaries` | **Default**: `false`. Show [extended thinking](/en/model-config#extended-thinking) summaries in interactive sessions. When unset or `false`, thinking blocks are redacted by the API and shown as a collapsed stub. Redaction only changes what you see, not what the model generates: to reduce thinking spend, [lower the budget or disable thinking](/en/model-config#extended-thinking) instead. This setting has no effect in non-interactive mode (`-p`), the Agent SDK, or IDE extensions such as VS Code | `true` |
| `showTurnDuration` | **Default**: `true`. Show turn duration messages after responses, e.g. "Cooked for 1m 6s". Appears in `/config` as **Show turn duration** | `false` |
| `skillListingBudgetFraction` | **Default**: `0.01`. Fraction of the model's context window reserved for the [skill listing](/en/skills#skill-descriptions-are-cut-short) Claude sees each turn, so the default reserves 1%. When the listing exceeds the budget, descriptions for the least-used skills are dropped and only their names are listed, so Claude can still invoke them but can't see what they do. Raise to keep more descriptions visible at the cost of more context per turn. `/doctor` estimates the listing cost against the budget. Requires Claude Code v2.1.105 or later | `0.02` |
| `skillListingMaxDescChars` | **Default**: `1536`. Per-skill character cap on the combined `description` and `when_to_use` text in the [skill listing](/en/skills#skill-descriptions-are-cut-short) Claude sees each turn. Text longer than this is truncated. Raise to keep long descriptions intact at the cost of more context per turn; lower to fit more skills under [`skillListingBudgetFraction`](#available-settings). Requires Claude Code v2.1.105 or later | `2048` |
| `skillListingBudgetFraction` | **Default**: `0.01`. Fraction of the model's context window reserved for the [skill listing](/en/skills#skill-descriptions-are-cut-short) Claude sees each turn, so the default reserves 1%. When the listing exceeds the budget, descriptions for the least-used skills are dropped and only their names are listed, so Claude can still invoke them but can't see what they do. Raise to keep more descriptions visible at the cost of more context per turn. `/doctor` estimates the listing cost against the budget | `0.02` |
| `skillListingMaxDescChars` | **Default**: `1536`. Per-skill character cap on the combined `description` and `when_to_use` text in the [skill listing](/en/skills#skill-descriptions-are-cut-short) Claude sees each turn. Text longer than this is truncated. Raise to keep long descriptions intact at the cost of more context per turn; lower to fit more skills under [`skillListingBudgetFraction`](#available-settings) | `2048` |
| `skillOverrides` | Per-skill visibility overrides keyed by skill name. Value is `"on"`, `"name-only"`, `"user-invocable-only"`, or `"off"`. Lets you hide or collapse a skill without editing its SKILL.md. Does not apply to plugin skills, which are managed through `/plugin`. The `/skills` menu writes these to `.claude/settings.local.json`. See [Override skill visibility from settings](/en/skills#override-skill-visibility-from-settings). Requires Claude Code v2.1.129 or later | `{"legacy-context": "name-only", "deploy": "off"}` |
| `skipWebFetchPreflight` | Skip the [WebFetch domain safety check](/en/data-usage#webfetch-domain-safety-check) that sends each requested hostname to `api.anthropic.com` before fetching. Set to `true` in environments that block traffic to Anthropic, such as Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry deployments with restrictive egress. When skipped, WebFetch attempts any URL without consulting the blocklist | `true` |
| `spinnerTipsEnabled` | **Default**: `true`. Show tips in the spinner while Claude is working. Set to `false` to disable tips | `false` |
@@ -38,19 +38,19 @@ To install Claude Code, use one of the following methods:
**macOS, Linux, WSL:**
```bash theme={null} theme={null} theme={null} theme={null}
```bash theme={null}
curl -fsSL https://claude.ai/install.sh | bash
```
**Windows PowerShell:**
```powershell theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
irm https://claude.ai/install.ps1 | iex
```
**Windows CMD:**
```batch theme={null} theme={null} theme={null} theme={null}
```batch theme={null}
curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd
```
@@ -62,7 +62,7 @@ If the install command fails with `syntax error near unexpected token '<'`, a `4
Native installations automatically update in the background to keep you on the latest version.
```bash theme={null} theme={null} theme={null} theme={null}
```bash theme={null}
brew install --cask claude-code
```
@@ -70,7 +70,7 @@ Homebrew offers two casks. `claude-code` tracks the stable release channel, whic
Homebrew installations do not auto-update. Run `brew upgrade claude-code` or `brew upgrade claude-code@latest`, depending on which cask you installed, to get the latest features and security fixes.
```powershell theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
winget install Anthropic.ClaudeCode
```
Windowsでの証明書失効確認エラーへの対策として、curlのフラグ指定ではなくPowerShellインストーラーの使用を推奨する内容に変更されました。
@@ -400,11 +400,11 @@ Errors like `curl: (35) TLS connect error`, `schannel: next InitializeSecurityCo
```
Ask your IT team for the certificate file if you don't have it. You can also try on a direct connection to confirm the proxy is the cause.
4. **On Windows, bypass certificate revocation checks** if you see `CRYPT_E_NO_REVOCATION_CHECK (0x80092012)` or `CRYPT_E_REVOCATION_OFFLINE (0x80092013)`. These mean curl reached the server but your network blocks the certificate revocation lookup, which is common behind corporate firewalls. Add `--ssl-revoke-best-effort` to the install command:
```batch theme={null}
curl --ssl-revoke-best-effort -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd
4. **On Windows, switch installers if your network blocks revocation checks**. The errors `CRYPT_E_NO_REVOCATION_CHECK (0x80092012)` and `CRYPT_E_REVOCATION_OFFLINE (0x80092013)` mean curl reached the server but your network blocks the certificate revocation lookup, which is common behind corporate firewalls. Adding curl's `--ssl-revoke-best-effort` flag doesn't fix this: the flag only applies to downloading `install.cmd` itself, and the script's own downloads run without it, so the install fails with the same error. Use an install method that tolerates the blocked lookup instead. Open PowerShell and run the PowerShell installer, which downloads through .NET and doesn't fail when the revocation server is unreachable:
```powershell theme={null}
irm https://claude.ai/install.ps1 | iex
```
Alternatively, install with `winget install Anthropic.ClaudeCode`, which avoids curl entirely.
You can also install with `winget install Anthropic.ClaudeCode`, which avoids curl entirely.
### `Failed to fetch version from downloads.claude.ai`