Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add olaservo/mcp-agent-skills --skill claude-agent-sdk-tsgit clone --depth 1 https://github.com/olaservo/mcp-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/olaservo/mcp-agent-skills/claude-agent-sdk-ts)<a href="https://agentmods.dev/skills/olaservo/mcp-agent-skills/claude-agent-sdk-ts"><img src="https://agentmods.dev/badge/skills/olaservo/mcp-agent-skills/claude-agent-sdk-ts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/olaservo/mcp-agent-skills/claude-agent-sdk-ts"><img src="https://agentmods.dev/badge/skills/olaservo/mcp-agent-skills/claude-agent-sdk-ts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.03907 |
| Opus 5 | $0.00024 | $0.01954 |
| Sonnet 5 | $0.00010 | $0.00781 |
| Haiku 4.5 | $0.00005 | $0.00391 |
Grade A, and why
claude-agent-sdk-ts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TypeScript Claude Agent SDK Builder
Build AI agents using the Claude Agent SDK in TypeScript by referencing code snippets that demonstrate both V1 (query()) and V2 (session-based) API patterns.
How It Works
- Choose your API: V1 for scripts/batch processing, V2 for interactive apps
- Browse the snippet catalog below or in
snippets/ - Copy the snippets you need into your project
- Customize the copied code for your use case
Snippets are bundled in this skill's snippets/ directory.
Authentication
The Claude Agent SDK automatically uses Claude Code's authentication - no API key configuration required if you're logged into Claude Code.
How it works:
- The SDK looks for OAuth tokens in
~/.claude/(created when you runclaude login) - Falls back to
ANTHROPIC_API_KEYenvironment variable if set - No code changes needed - authentication is handled automatically
Check your auth status:
claude auth status
If not authenticated:
claude login
Alternative Providers (Bedrock, Vertex AI, Azure)
The SDK also supports cloud provider APIs. Set environment variables:
Amazon Bedrock:
export CLAUDE_CODE_USE_BEDROCK=1
export AWS_REGION=us-west-2
export AWS_PROFILE=your-profile # Optional: specify named credentials profile
# Or uses default AWS credentials (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, or IAM role)
Google Vertex AI:
export CLAUDE_CODE_USE_VERTEX=1
export CLOUD_ML_REGION=us-east5
export ANTHROPIC_VERTEX_PROJECT_ID=your-project-id
# Uses your Google Cloud credentials
Azure:
export CLAUDE_CODE_USE_AZURE=1
export AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
# Uses your Azure credentials
Note: If deploying to a server without Claude Code, set
ANTHROPIC_API_KEYin your environment (or use Bedrock/Vertex/Azure as above).
When to Use Claude Agent SDK
Use Claude Agent SDK when you want:
- Quick setup with minimal boilerplate
- Out-of-the-box Claude Code capabilities
- Pre-built tool ecosystem with MCP server integration
- Session management and multi-turn conversations
- Hook system for tool auditing and control
What ships with it
35 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- manifest.json 6.5 KB
- reference/agent_sdk_api_reference.md 11 KB
- reference/agent_sdk_patterns.md 17 KB
- snippets/agent-v1/basic-query.ts 1.2 KB runs code
- snippets/agent-v1/query-with-queue.ts 2.8 KB runs code
- snippets/agent-v1/query-with-resume.ts 2.4 KB runs code
- snippets/agent-v1/query-with-system-prompt.ts 1.6 KB runs code
- snippets/agent-v1/query-with-tools.ts 1.7 KB runs code
- snippets/agent-v2/basic-session.ts 1.6 KB runs code
- snippets/agent-v2/multi-turn.ts 1.9 KB runs code
- snippets/agent-v2/one-shot.ts 1.8 KB runs code
- snippets/agent-v2/session-resume.ts 2.5 KB runs code
- snippets/config/model-selection.ts 3.8 KB runs code
- snippets/config/settings-sources.ts 3.8 KB runs code
- snippets/config/working-directory.ts 4.5 KB runs code
- snippets/hooks/post-tool-use.ts 4.4 KB runs code
- snippets/hooks/pre-tool-use.ts 4.1 KB runs code
- snippets/patterns/ai-client-wrapper.ts 6.2 KB runs code
- snippets/patterns/message-queue.ts 4.4 KB runs code
- snippets/patterns/self-improving-agent.ts 7.7 KB runs code
- snippets/patterns/subagent-task.ts 6.4 KB runs code
- snippets/patterns/task-filesystem.ts 5.8 KB runs code
- snippets/patterns/websocket-session.ts 6.1 KB runs code
- snippets/persistence/chat-store-jsonl.ts 7.1 KB runs code
- snippets/persistence/chat-store-sqlite.ts 6.8 KB runs code
- snippets/tools/allowed-tools.ts 2.8 KB runs code
- snippets/tools/custom-mcp-server.ts 4.9 KB runs code
- snippets/tools/custom-skill.ts 3.7 KB runs code
- snippets/tools/mcp-server-config.ts 8.3 KB runs code
- snippets/tools/tool-registration.ts 4.6 KB runs code
- snippets/ui/tool-approval-hook.ts 7.2 KB runs code
- snippets/ui/tool-history-stream.ts 7.8 KB runs code
- snippets/ui/websocket-chat-session.ts 10 KB runs code
- snippets/ui/websocket-server-sqlite.ts 12 KB runs code
- snippets/ui/websocket-types.ts 1.8 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 485 lines · 49 tokens per session scan A 8e36a0a76b58
claude-agent-sdk-ts is a skill published in the GitHub repository olaservo/mcp-agent-skills (2 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 3,907 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.
aws-sst-development
SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework.
league-akari-shard-development
Use when creating, extending, refactoring, splitting, or reviewing League Akari main or renderer shards, including shard file organization, controller/loader/executor/handler boundaries, naming conventions, renderer TSX usage, platform guards, and public contract compatibility.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
fast-typescript-check
Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…
migrate-better-result-3
Migrate a TypeScript codebase from better-result 2.x to 3.0. Use when upgrading better-result across the TaggedError syntax, removed Result serialization helpers, recovery inference, matching, or retry APIs.