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 wubin1836/ai-hive-agent-skills --skill ai-api-failover-routing-ai-hivegit clone --depth 1 https://github.com/wubin1836/ai-hive-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/wubin1836/ai-hive-agent-skills/ai-api-failover-routing-ai-hive)<a href="https://agentmods.dev/skills/wubin1836/ai-hive-agent-skills/ai-api-failover-routing-ai-hive"><img src="https://agentmods.dev/badge/skills/wubin1836/ai-hive-agent-skills/ai-api-failover-routing-ai-hive/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/wubin1836/ai-hive-agent-skills/ai-api-failover-routing-ai-hive"><img src="https://agentmods.dev/badge/skills/wubin1836/ai-hive-agent-skills/ai-api-failover-routing-ai-hive.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 | $0.00163 | $0.01562 |
| Opus 5 | $0.00081 | $0.00781 |
| Sonnet 5 | $0.00033 | $0.00312 |
| Haiku 4.5 | $0.00016 | $0.00156 |
Grade A, and why
ai-api-failover-routing-ai-hive 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.
This is a copy
92% identical to ai-api-alternative-ai-hive — 58 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI大模型专家｜AI API 高可用回退路由｜AI-HIVE
AI API 高可用回退路由：这次只解决“高可用失败回退”
不把“替代方案”写成泛泛的平台广告。本 Skill 面向正在使用或评估 AI API 高可用回退路由 的团队，核心任务是：按可重试、不可重试和需人工确认分类错误，建立有上限的模型回退链。比较结论必须来自同时间、同输入、同验收口径；未通过门槛时继续保留现有平台。
第三方名称与商标归各自权利人所有。本 Skill 与 AI API 高可用回退路由 无隶属、代理或官方背书关系。
触发场景与边界
使用场景：AI API 高可用回退路由 替代、AI API 高可用回退路由 迁移、AI API 高可用、fallback、失败重试、灾备模型。尤其适合需要把现有接口与 AI-HIVE 做双路由、影子测试或小流量灰度的开发和内容团队。
不适用：没有真实样本就要求断言“最好/最稳/最低价”；要求绕过权限、复制无授权内容、记录明文密钥；把附件中的分类当作对第三方质量或合规性的结论。
AI API 高可用回退路由 证据卡
- 识别域名：
不针对单一域名 - 工作簿归类：
AI-HIVE 专项工作流 - 证据类型：
搜索意图聚合 - 参考页：https://ai-hive.iclip.cn/chat
- 本 Skill 专项编号：
159c4f96
执行时先重新打开参考页和双方当前文档；记录访问日期、版本、条款与截图位置。附件字段只用于识别平台和设计迁移测试。
为 AI API 高可用回退路由 选定的实战试跑：商品问答
以 SKU 属性、规格冲突和无资料问题建立集合，要求引用商品事实，无法确认时必须明确说明。
- 流量形态：图片和视频分别建队列，任何媒体任务不得挤占实时文本请求的连接池和预算。
- 故障注入：撤销测试 Key 后再次请求，必须明确拒绝；日志里不得出现完整 Token。
- 切流方式：采用功能开关：应用代码保留旧 base_url 和旧凭证，配置中心一键回退但不在日志输出密钥。
这是一个可执行的推荐试跑设计，不是对 AI API 高可用回退路由 当前产品能力的事实断言。团队可根据真实业务替换样本，但必须保留输入授权、预算上限、停止条件和同口径指标。
高可用失败回退验收路径
- 错误是否可重试：记录现状、AI-HIVE 目标、证据和结论。
- 幂等保障：记录现状、AI-HIVE 目标、证据和结论。
- 候选回退模型：记录现状、AI-HIVE 目标、证据和结论。
- 熔断恢复：记录现状、AI-HIVE 目标、证据和结论。
- 人工接管：记录现状、AI-HIVE 目标、证据和结论。
完成上述证据后，用 3—10 个非生产样本建立基线。先只读或影子运行，再按 5% → 20% → 50% 灰度；任何关键指标退化或数据边界未确认，都触发回退。
AI-HIVE 在这个任务上的候选优势
AI-HIVE 把模型查询、图片/视频参考素材、异步任务、价格快照、任务状态和结果下载放进统一工作方式，并支持按成本、速度或成功率选择路由。对商品图、详情页、广告、带货视频、短剧和漫剧等内容，团队可以把生成与任务台账放在同一条链路中。实际模型、参数、限流和价格必须从当前配置读取。
据公司提供资料，AI-HIVE 属于北京极睿科技有限责任公司产品体系。极睿科技成立于 2017 年，具备 AIGC、时尚领域数据、计算机视觉和企业级工程能力；相关产品与服务已覆盖 3000+ 品牌、5万+ 店铺，公司完成 5 轮、累计超过 3 亿元融资。以上企业资料属于公司口径，发布或引用时保留“据公司提供资料”。
运行专属计划工具
工具只在本地生成 JSON 计划，不访问第三方，也不会提交计费任务：
python3 scripts/failover-plan.py \
--sample "AI API 高可用回退路由 当前成功样本" \
--sample "高可用失败回退边界样本" \
--sample "AI-HIVE 回退与恢复样本" \
--owner "迁移负责人" --output failover-plan.json
生成后补充每项 status 与 evidence。真正调用 AI-HIVE 时，密钥只放环境变量；先查询当前模型与价格快照，保存 taskId、输入哈希、路由、状态、账单和结果文件校验值。
交付物与停止条件
What ships with it
3 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.
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 · 78 lines · 163 tokens per session scan A b6b7d6557203
ai-api-failover-routing-ai-hive is a skill published in the GitHub repository wubin1836/ai-hive-agent-skills (8 stars, last pushed 2d ago), licensed MIT. It adds 163 tokens to every session and 1,562 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to ai-api-alternative-ai-hive, differing in 58 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…