Slash Commands dalam SDK
Pelajari cara menggunakan slash commands untuk mengontrol sesi Claude Code melalui SDK
Slash commands menyediakan cara untuk mengontrol sesi Claude Code dengan perintah khusus yang dimulai dengan /. Perintah-perintah ini dapat dikirim melalui SDK untuk melakukan tindakan seperti memadatkan konteks, mencantumkan penggunaan konteks, atau memanggil perintah khusus. Hanya perintah yang bekerja tanpa terminal interaktif yang dapat dikirim melalui SDK; pesan system/init mencantumkan yang tersedia di sesi Anda.
Menemukan Slash Commands yang Tersedia
Claude Agent SDK menyediakan informasi tentang slash commands yang tersedia dalam pesan inisialisasi sistem. Akses informasi ini ketika sesi Anda dimulai:
import { query } from "@anthropic-ai/claude-agent-sdk";
for await (const message of query({
prompt: "Hello Claude",
options: { maxTurns: 1 }
})) {
if (message.type === "system" && message.subtype === "init") {
console.log("Available slash commands:", message.slash_commands);
// Example output: ["clear", "compact", "context", "usage"]
}
}
import asyncio
from claude_agent_sdk import query, ClaudeAgentOptions, SystemMessage
async def main():
async for message in query(prompt="Hello Claude", options=ClaudeAgentOptions(max_turns=1)):
if isinstance(message, SystemMessage) and message.subtype == "init":
print("Available slash commands:", message.data["slash_commands"])
# Example output: ["clear", "compact", "context", "usage"]
asyncio.run(main())
Mengirim Slash Commands
Kirim slash commands dengan memasukkannya dalam string prompt Anda, seperti teks biasa:
import { query } from "@anthropic-ai/claude-agent-sdk";
// Send a slash command
for await (const message of query({
prompt: "/compact",
options: { maxTurns: 1 }
})) {
if (message.type === "result" && message.subtype === "success") {
console.log("Command executed:", message.result);
}
}
import asyncio
from claude_agent_sdk import query, ClaudeAgentOptions, ResultMessage
async def main():
# Send a slash command
async for message in query(prompt="/compact", options=ClaudeAgentOptions(max_turns=1)):
if isinstance(message, ResultMessage):
print("Command executed:", message.result)
asyncio.run(main())
Slash Commands Umum
`/compact` - Memadatkan Riwayat Percakapan
Perintah /compact mengurangi ukuran riwayat percakapan Anda dengan merangkum pesan yang lebih lama sambil mempertahankan konteks penting:
import { query } from "@anthropic-ai/claude-agent-sdk";
for await (const message of query({
prompt: "/compact",
options: { maxTurns: 1 }
})) {
if (message.type === "system" && message.subtype === "compact_boundary") {
console.log("Compaction completed");
console.log("Pre-compaction tokens:", message.compact_metadata.pre_tokens);
console.log("Trigger:", message.compact_metadata.trigger);
}
}
import asyncio
from claude_agent_sdk import query, ClaudeAgentOptions, SystemMessage
async def main():
async for message in query(prompt="/compact", options=ClaudeAgentOptions(max_turns=1)):
if isinstance(message, SystemMessage) and message.subtype == "compact_boundary":
print("Compaction completed")
print("Pre-compaction tokens:", message.data["compact_metadata"]["pre_tokens"])
print("Trigger:", message.data["compact_metadata"]["trigger"])
asyncio.run(main())
`/clear` - Atur Ulang Konteks Percakapan
Perintah /clear mengatur ulang percakapan ke konteks kosong, sehingga prompt berikutnya dimulai tanpa riwayat percakapan sebelumnya. Percakapan sebelumnya tetap tersimpan di disk dan dapat dikembalikan dengan melewatkan ID sesinya ke opsi resume.
Ini berguna dalam mode input streaming, di mana Anda mengirim beberapa prompt melalui satu koneksi. Untuk panggilan query() sekali jalan, setiap panggilan sudah dimulai dengan konteks kosong, jadi mengirim /clear tidak memiliki efek praktis; mulai query() baru sebagai gantinya.
Membuat Slash Commands Khusus
Selain menggunakan slash commands bawaan, Anda dapat membuat perintah khusus Anda sendiri yang tersedia melalui SDK. Perintah khusus didefinisikan sebagai file markdown di direktori tertentu, mirip dengan cara subagents dikonfigurasi.
Lokasi File
Slash commands khusus disimpan di direktori yang ditentukan berdasarkan cakupan mereka:
- Perintah proyek:
.claude/commands/- Tersedia hanya di proyek saat ini (warisan; lebih suka.claude/skills/) - Perintah pribadi:
~/.claude/commands/- Tersedia di semua proyek Anda (warisan; lebih suka~/.claude/skills/)
Format File
Setiap perintah khusus adalah file markdown di mana:
- Nama file (tanpa ekstensi
.md) menjadi nama perintah - Konten file mendefinisikan apa yang dilakukan perintah
- Frontmatter YAML opsional menyediakan konfigurasi
Contoh Dasar
Buat .claude/commands/refactor.md:
Refactor the selected code to improve readability and maintainability.
Focus on clean code principles and best practices.
Ini membuat perintah /refactor yang dapat Anda gunakan melalui SDK.
Dengan Frontmatter
Buat .claude/commands/security-check.md:
---
allowed-tools: Read, Grep, Glob
description: Run security vulnerability scan
model: claude-opus-4-7
---
Analyze the codebase for security vulnerabilities including:
- SQL injection risks
- XSS vulnerabilities
- Exposed credentials
- Insecure configurations
Menggunakan Custom Commands di SDK
Setelah didefinisikan di sistem file, perintah khusus secara otomatis tersedia melalui SDK:
import { query } from "@anthropic-ai/claude-agent-sdk";
// Use a custom command
for await (const message of query({
prompt: "/refactor src/auth/login.ts",
options: { maxTurns: 3 }
})) {
if (message.type === "assistant") {
console.log("Refactoring suggestions:", message.message);
}
}
// Custom commands appear in the slash_commands list
for await (const message of query({
prompt: "Hello",
options: { maxTurns: 1 }
})) {
if (message.type === "system" && message.subtype === "init") {
// Will include both built-in and custom commands
console.log("Available commands:", message.slash_commands);
// Example: ["clear", "compact", "context", "usage", "refactor", "security-check"]
}
}
import asyncio
from claude_agent_sdk import query, ClaudeAgentOptions, AssistantMessage, SystemMessage
async def main():
# Use a custom command
async for message in query(
prompt="/refactor src/auth/login.py", options=ClaudeAgentOptions(max_turns=3)
):
if isinstance(message, AssistantMessage):
for block in message.content:
if hasattr(block, "text"):
print("Refactoring suggestions:", block.text)
# Custom commands appear in the slash_commands list
async for message in query(prompt="Hello", options=ClaudeAgentOptions(max_turns=1)):
if isinstance(message, SystemMessage) and message.subtype == "init":
# Will include both built-in and custom commands
print("Available commands:", message.data["slash_commands"])
# Example: ["clear", "compact", "context", "usage", "refactor", "security-check"]
asyncio.run(main())
Fitur Lanjutan
Argumen dan Placeholder
Perintah khusus mendukung argumen dinamis menggunakan placeholder:
Buat .claude/commands/fix-issue.md:
---
argument-hint: [issue-number] [priority]
description: Fix a GitHub issue
---
Fix issue #$0 with priority $1.
Check the issue description and implement the necessary changes.
Gunakan di SDK:
import { query } from "@anthropic-ai/claude-agent-sdk";
// Pass arguments to custom command
for await (const message of query({
prompt: "/fix-issue 123 high",
options: { maxTurns: 5 }
})) {
// Command will process with $0="123" and $1="high"
if (message.type === "result" && message.subtype === "success") {
console.log("Issue fixed:", message.result);
}
}
import asyncio
from claude_agent_sdk import query, ClaudeAgentOptions, ResultMessage
async def main():
# Pass arguments to custom command
async for message in query(prompt="/fix-issue 123 high", options=ClaudeAgentOptions(max_turns=5)):
# Command will process with $0="123" and $1="high"
if isinstance(message, ResultMessage):
print("Issue fixed:", message.result)
asyncio.run(main())
Eksekusi Perintah Bash
Perintah khusus dapat mengeksekusi perintah bash dan menyertakan output mereka:
Buat .claude/commands/git-commit.md:
---
allowed-tools: Bash(git add *), Bash(git status *), Bash(git commit *)
description: Create a git commit
---
## Context
- Current status: !`git status`
- Current diff: !`git diff HEAD`
## Task
Create a git commit with appropriate message based on the changes.
Referensi File
Sertakan konten file menggunakan awalan @:
Buat .claude/commands/review-config.md:
---
description: Review configuration files
---
Review the following configuration files for issues:
- Package config: @package.json
- TypeScript config: @tsconfig.json
- Environment config: @.env
Check for security issues, outdated dependencies, and misconfigurations.
Organisasi dengan Namespacing
Organisir perintah dalam subdirektori untuk struktur yang lebih baik:
.claude/commands/
├── frontend/
│ ├── component.md # Creates /component (project:frontend)
│ └── style-check.md # Creates /style-check (project:frontend)
├── backend/
│ ├── api-test.md # Creates /api-test (project:backend)
│ └── db-migrate.md # Creates /db-migrate (project:backend)
└── review.md # Creates /review (project)
Subdirektori muncul dalam deskripsi perintah tetapi tidak mempengaruhi nama perintah itu sendiri.
Contoh Praktis
Perintah Code Review
Buat .claude/commands/code-review.md:
---
allowed-tools: Read, Grep, Glob, Bash(git diff *)
description: Comprehensive code review
---
## Changed Files
!`git diff --name-only HEAD~1`
## Detailed Changes
!`git diff HEAD~1`
## Review Checklist
Review the above changes for:
1. Code quality and readability
2. Security vulnerabilities
3. Performance implications
4. Test coverage
5. Documentation completeness
Provide specific, actionable feedback organized by priority.
Perintah Test Runner
Buat .claude/commands/test.md:
---
allowed-tools: Bash, Read, Edit
argument-hint: [test-pattern]
description: Run tests with optional pattern
---
Run tests matching pattern: $ARGUMENTS
1. Detect the test framework (Jest, pytest, etc.)
2. Run tests with the provided pattern
3. If tests fail, analyze and fix them
4. Re-run to verify fixes
Gunakan perintah-perintah ini melalui SDK:
import { query } from "@anthropic-ai/claude-agent-sdk";
// Run code review
for await (const message of query({
prompt: "/code-review",
options: { maxTurns: 3 }
})) {
// Process review feedback
}
// Run specific tests
for await (const message of query({
prompt: "/test auth",
options: { maxTurns: 5 }
})) {
// Handle test results
}
import asyncio
from claude_agent_sdk import query, ClaudeAgentOptions
async def main():
# Run code review
async for message in query(prompt="/code-review", options=ClaudeAgentOptions(max_turns=3)):
# Process review feedback
pass
# Run specific tests
async for message in query(prompt="/test auth", options=ClaudeAgentOptions(max_turns=5)):
# Handle test results
pass
asyncio.run(main())
Lihat Juga
- Slash Commands - Dokumentasi slash command lengkap
- Subagents dalam SDK - Konfigurasi berbasis sistem file serupa untuk subagents
- Referensi TypeScript SDK - Dokumentasi API lengkap
- Gambaran umum SDK - Konsep SDK umum
- Referensi CLI - Antarmuka baris perintah