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 agentmods add rules/zhangdszq/teamclaw/use-agent-sdkgit clone --depth 1 https://github.com/zhangdszq/teamclawWrote 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/rules/zhangdszq/teamclaw/use-agent-sdk)<a href="https://agentmods.dev/rules/zhangdszq/teamclaw/use-agent-sdk"><img src="https://agentmods.dev/badge/rules/zhangdszq/teamclaw/use-agent-sdk.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00476 |
| Opus 5 | $0.00000 | $0.00238 |
| Sonnet 5 | $0.00000 | $0.00095 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade B, and why
use-agent-sdk scanned grade B with 1 finding 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
若用户在 app 设置中配置了 API Key，**必须优先使用**，不能依赖外部文件（`~/.claude/settings.json`）。 What it actually says
AI 调用规范
统一调用层
所有 AI 调用必须通过 src/electron/libs/agent-client.ts，禁止直接导入 SDK：
import { runAgent, promptOnce } from "./libs/agent-client.js";
// 完整 Agent 会话
const q = await runAgent(prompt, { provider: "claude", cwd: targetDir });
for await (const msg of q) { /* handle */ }
// 一次性文本生成
const title = await promptOnce("生成标题...", { provider: "openai" });
两种 Provider
| Provider | 后端 | 认证方式 |
|---|---|---|
claude（默认） |
Anthropic API | ANTHROPIC_API_KEY / app 内配置 |
openai |
OpenAI via 本地代理 | OpenAI OAuth Token（app 内登录） |
当 provider: "openai" 时，agent-client.ts 自动启动本地代理（openai-proxy.ts），
将 Claude Agent SDK 的请求翻译为 OpenAI Responses API 格式。
优先使用 app 内配置的 API Key
若用户在 app 设置中配置了 API Key，必须优先使用，不能依赖外部文件（~/.claude/settings.json）。
❌ 禁止做法
// ❌ 直接导入 SDK
import { query } from "@anthropic-ai/claude-agent-sdk";
// ❌ 原始 Anthropic SDK
import Anthropic from "@anthropic-ai/sdk";
const resp = await new Anthropic({ apiKey }).messages.create({ ... });
// ❌ 原始 OpenAI SDK
import OpenAI from "openai";
const resp = await new OpenAI({ apiKey }).chat.completions.create({ ... });
// ❌ 解析 LLM 文本再手动写文件
const match = text.match(/<output>([\s\S]*?)<\/output>/);
writeFileSync(path, match[1]);
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.
- 4d ago First seen · 58 lines · 0 tokens per session scan B 479b81108593
use-agent-sdk is a cursor rule published in the GitHub repository zhangdszq/teamclaw (113 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 476 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.