anthropic-agent-sdk
Claude Agent SDK (code.claude.com/docs/en/agent-sdk) の TypeScript / Python リファレンス。 query(), ClaudeAgentOptions / Options, fallbackModel, maxTurns, maxBudgetUsd, custom tools (in-process MCP), createSdkMcpServer, hooks, permissions (canUseTool), subagents, sessions (resume / fork), streaming, structured outputs, Agent Skills (SKILL.md), slash commands (/compact, /clear), tool search, hosting / observability。
- Installs
- 70
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/fandhe-ai/agent-reference-skills --skill anthropic-agent-sdk- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads anthropic-agent-sdk automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
anthropic-agent-sdk
Claude Agent SDK (code.claude.com/docs/en/agent-sdk) — TypeScript / Python でエージェントをビルドする公式 SDK の
リファレンス。query() によるエージェントループ実行、custom tools（in-process MCP）、外部 MCP 接続、hooks、
subagents、permissions（canUseTool）、セッションの永続化・再開・分岐、streaming、structured outputs、
本番ホスティングをカバーする。
Claude Code CLI 本体は anthropic-claude-code / anthropic-claude-code-extend、Messages API 直接呼び出しは
anthropic-api-core、Claude API 側の tool use / Agent Skills / MCP は anthropic-api-tools-mcp を参照
（本スキルは SDK 経由でエージェントをビルド・運用する側を担当）。
Source: https://code.claude.com/docs/en/agent-sdk 、2026-10-16 取得（その時点の npm @anthropic-ai/claude-agent-sdk 0.3.301 / PyPI claude-agent-sdk 0.2.168）。
ディレクトリ構成
skills/anthropic-agent-sdk/
SKILL.md
references/
getting-started/
README.md
agent-loop.md
claude-code-features.md
configuration.md
examples.md
migration-guide.md
overview.md
quickstart.md
api-reference/
README.md
python.md
typescript.md
extending/
README.md
custom-tools.md
hooks.md
mcp.md
plugins.md
skills.md
slash-commands.md
subagents.md
tool-search.md
sessions-io/
README.md
file-checkpointing.md
session-storage.md
sessions.md
streaming-output.md
streaming-vs-single-mode.md
structured-outputs.md
todo-tracking.md
control/
README.md
modifying-system-prompts.md
permissions.md
user-input.md
operations/
README.md
cost-tracking.md
hosting.md
observability.md
secure-deployment.md
troubleshooting.md
samples/
README.md
minimal-agent.md
configure-agent.md
custom-tools.md
mcp-servers.md
hooks.md
permissions.md
subagents.md
sessions.md
streaming.md
structured-outputs.md
system-prompts.md
scripts/
README.md
setup.md
runtime.md
探索手順
タスクからカテゴリを引き、カテゴリの README.md で目的のページを特定する:
- 下記マッピング表でタスクに対応するカテゴリを探す
- そのカテゴリの
references/{category}/README.md（samples/scripts/は直下の README.md）を参照して目的のページを特定する - 該当ページの
.mdを Read して詳細を確認する
タスク → カテゴリ マッピング
| タスク | カテゴリ | 参照 README |
|---|---|---|
| Agent SDK の概要・エージェントループの仕組みを知りたい・インストールして最初のエージェントを作りたい・Claude Code SDK からの移行・SDK 内で Claude Code の機能（CLAUDE.md, Agent Skills, hooks）を使いたい・options オブジェクトを組み立てたい（model / fallbackModel, env / cwd / maxTurns / maxBudgetUsd）・セッション中に model や permission mode を変更したい（setModel / setPermissionMode / applyFlagSettings / updateSettings）・動かせるサンプルプロジェクトを探したい（claude-agent-sdk-demos / Claude Cookbook） | getting-started | references/getting-started/README.md |
query() や ClaudeAgentOptions / Options など TypeScript / Python の完全な型・関数シグネチャを確認したい | api-reference | references/api-reference/README.md |
custom tools（in-process MCP, createSdkMcpServer）を定義したい・外部 MCP サーバーに接続したい・hooks でツール呼び出しを制御したい・plugins・Agent Skills (SKILL.md) の skills オプション・コマンド名による呼び出し（/compact, /clear, カスタムコマンド。slash-commands は skills に統合済み）・subagents・tool search を扱いたい | extending | references/extending/README.md |
| セッションの永続化・再開・分岐（resume / fork）・外部ストレージへの保存・file checkpointing・todo 管理・streaming 出力・structured outputs を扱いたい | sessions-io | references/sessions-io/README.md |
system prompt をカスタマイズしたい・permission mode や canUseTool で権限制御したい・ユーザー入力/承認フローを扱いたい | control | references/control/README.md |
| 本番環境へのホスティング・セキュアなデプロイ・OpenTelemetry での observability・コスト/トークン追跡・エラーのトラブルシューティングを知りたい | operations | references/operations/README.md |
| 典型的な使い方を知りたい（最小エージェント, options 構成（configure-agent）, custom tools, MCP サーバー接続, hooks, permissions, subagents, セッション継続, streaming, structured outputs, system prompt カスタマイズ） | samples | samples/README.md |
| SDK インストール・API キー設定・ホスティング用テレメトリー環境変数を知りたい | scripts | scripts/README.md |
FAQ
What does the anthropic-agent-sdk skill do?
Claude Agent SDK (code.claude.com/docs/en/agent-sdk) の TypeScript / Python リファレンス。 query(), ClaudeAgentOptions / Options, fallbackModel, maxTurns, maxBudgetUsd, custom tools (in-process MCP), createSdkMcpServer, hooks, permissions (canUseTool), subagents, sessions (resume / fork), streaming, structured outputs, Agent Skills (SKILL.md), slash commands (/compact, /clear), tool search, hosting / observability。
How do I install anthropic-agent-sdk?
Run npx skills add https://github.com/fandhe-ai/agent-reference-skills --skill anthropic-agent-sdk in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/anthropic-agent-sdk/ (personal) or .claude/skills/anthropic-agent-sdk/ (project).
Which AI agents can use anthropic-agent-sdk?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is anthropic-agent-sdk safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains anthropic-agent-sdk?
It is published by fandhe-ai in fandhe-ai/agent-reference-skills. It has 70 recorded installs.
More from fandhe-ai/agent-reference-skills
github-docs
fandhe-ai/agent-reference-skills
GitHub 公式ドキュメント (docs.github.com)。REST API, GraphQL, Webhooks, GitHub Apps, OAuth Apps, gh CLI, PAT / GITHUBTOKEN, Actions (jobs, steps, expressions, workflow commands, concurrency, OIDC, artifact attestations, lockfile), pull requests, issues, Projects v2, immutable releases, Codespaces, Packages, Copilot API / cloud agent, code scanning, secret scanning, Dependabot, Dependency graph / SBOM, Teams, Billing, activity (events / notifications)。
commitlint
fandhe-ai/agent-reference-skills
commitlint (Conventional Commits メッセージ検証ツール) リファレンス。 rules 設定、plugins、shareable-config、@commitlint/config-conventional、 Husky / lefthook / simple-git-hooks 連携、CI 統合、custom rules。
lefthook
fandhe-ai/agent-reference-skills
Lefthook (高速並列 Git hooks マネージャー) リファレンス。 lefthook.yml 設定、pre-commit / pre-push / commit-msg 等のフック、 parallel / piped 実行、glob / run / tags フィルタ、stagedfiles、 lefthook の ai 設定 (beta)、JSON schema、Composer / npm / pip 等インストール、 保護ブランチ、CI スキップ、Husky からの移行。
editorconfig
fandhe-ai/agent-reference-skills
EditorConfig (エディタ設定統一フォーマット) リファレンス。 .editorconfig ファイル、glob パターン、root、 indentstyle / indentsize / tabwidth、endofline, charset、 trimtrailingwhitespace, insertfinalnewline, maxlinelength, spellinglanguage。
rust
fandhe-ai/agent-reference-skills
Rust 言語リファレンス。 別名: rustlang, rs (拡張子)、Rust-lang。 TRPL (The Rust Programming Language)、Rust by Example、Reference、 Cargo Book、rustc Book、rustdoc Book、Rustonomicon (Unsafe Rust)、 Edition Guide、Standard Library、Error Index。 所有権、ライフタイム、トレイト、async / await、エラーハンドリング、マクロ。
anthropic-claude-code
fandhe-ai/agent-reference-skills
Claude Code (code.claude.com) の CLI 本体リファレンス。 CLAUDE.md memory, settings.json (All settings, settings precedence, managed-settings.json), env-vars, model config, keybindings, statusline, terminal config, cli-reference (-p / --continue / --resume), sessions, checkpointing, worktrees, remote control, channels, deep links, troubleshooting。
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available