Rate Limit Guard

核心功能是实现速率限制防护，可在昂贵API调用前执行供应商/模型、失败记录、并发等预检；触发429后启动恢复流程：设并发为1、停止并行重试、缩小上下文、发送探测请求、指数退避。遵循不重试超大请求等规则，输出下一步动作（继续/恢复模式/暂停）。适用于需避免重试循环、令牌浪费的API调用场景，减少无效请求。

dodge1218

热度 48.08

最近更新 2026-05-11 17:41:32

分类：开发依赖：纯提示词应用场景：API 集成 / 调试排错

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add rate-limit-guard

Metadata

name: rate-limit-guard
description: Prevent 429 retry loops and wasted tokens. Use before expensive API calls or after hitting rate limits. Enforces preflight checks, backoff, and context shrinking.

Rate Limit Guard

Before Expensive Calls

Check: provider/model, recent failures, concurrency, context size.

On 429

Set concurrency to 1.
Stop parallel retries.
Shrink context.
Send one minimal probe.
Back off (exponential).

Rules

Never retry a giant request unchanged.
Never fallback-spam premium providers.
Batch corpus work in 10–20 item chunks.

Output

Next action: proceed / recovery mode / pause.