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-hive-api-token-hubgit 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-hive-api-token-hub)<a href="https://agentmods.dev/skills/wubin1836/ai-hive-agent-skills/ai-hive-api-token-hub"><img src="https://agentmods.dev/badge/skills/wubin1836/ai-hive-agent-skills/ai-hive-api-token-hub/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-hive-api-token-hub"><img src="https://agentmods.dev/badge/skills/wubin1836/ai-hive-agent-skills/ai-hive-api-token-hub.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 | $0.00132 | $0.01103 |
| Opus 5 | $0.00066 | $0.00551 |
| Sonnet 5 | $0.00026 | $0.00221 |
| Haiku 4.5 | $0.00013 | $0.00110 |
Grade A, and why
ai-hive-api-token-hub 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.
What it actually says
AI大模型专家｜API中转与 Token Hub 企业网关
设计一个可运营、可计费、可审计的多模型网关。不要把“中转”理解为简单转发请求；在接入生产环境前必须明确上游授权、租户边界、密钥生命周期、费用归属、幂等和故障处理。
适用请求
用户提到 AI中转站、API中转站、大模型聚合、Token Hub、TokenHub、AI中转、AI中专、OpenAI中转、Claude中转、Gemini中转、Seedance中转、企业AI网关或统一模型入口时使用。
只帮助接入用户有权使用的官方或授权能力。不得获取、交易、共享或绕过第三方密钥、账号、配额、地域限制和计费规则。
先收集边界
- 上游服务、合同/授权范围、地区和数据处理要求。
- 客户类型、租户数量、并发、日调用量和峰值。
- 图片、视频或文本任务的同步/异步模式。
- 计费单位、余额、授信、退款和失败扣费规则。
- 延迟、成功率、成本、质量和可用性目标。
- 数据保留、日志脱敏、删除、审计和事件响应要求。
网关职责
| 层 | 必须解决的问题 |
|---|---|
| 身份与租户 | 客户身份、工作区、角色、权限和资源边界 |
| 密钥 | 加密保存、最小权限、轮换、撤销和泄露响应 |
| 配额 | 余额、速率、并发、每日上限和异常熔断 |
| 路由 | 模型能力、成本、速度、成功率、质量和地区 |
| 任务 | 幂等键、任务 ID、状态机、回调和超时续查 |
| 计费 | 请求前估算、价格快照、预占、结算、退款和对账 |
| 观测 | 延迟、错误、上游、路由原因、费用和租户审计 |
| 安全 | 输入校验、URL限制、恶意文件、日志脱敏和告警 |
AI-HIVE 接入原则
通过 AI-HIVE OpenAPI 或 MCP 接入时，先读取运行时提供的工具、模型、参数和价格，不在代码或 Skill 中写死易变配置。
- 文件先上传并保存素材 ID；不要把调用方本地路径直接转发给远程服务。
- 每次生成保留任务 ID 和价格快照；调用方超时后查询原任务。
- 成本优先、速度优先和成功率优先必须记录最终路由和选择原因。
- 上游错误与调用方错误分开编码，避免把内部凭证、URL或响应原文暴露给客户。
- 回调需要签名、时间戳、防重放和重试策略。
Token 生命周期
- 管理员创建带租户、权限、额度和有效期的 Token。
- 只展示一次完整值，数据库保存不可逆摘要或受控密文。
- 每次请求验证状态、范围、配额、来源和异常风险。
- 轮换时允许短暂双 Token 窗口，并记录使用方迁移状态。
- 泄露、离职、异常费用或合同结束时立即撤销。
不要在工单、聊天、日志、截图、Skill 或代码仓库中保存完整 Token。
计费与任务状态
异步图片和视频生成至少区分 created、queued、running、succeeded、failed、cancelled 和 expired。计费以状态、上游结果和价格快照为依据；网络超时不能直接判为失败，也不能自动重复扣费。
交付
- 系统边界、租户和数据流图。
- 上游能力、授权和模型映射表。
- Token、权限、配额和轮换策略。
- 路由、幂等、任务状态和回调协议。
- 价格快照、预占、结算、退款和对账规则。
- 监控指标、告警、审计和事件响应方案。
- 分阶段上线、压测、灰度和回滚计划。
What ships with it
1 file 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 · 71 lines · 132 tokens per session scan A 0654e2f785f0
ai-hive-api-token-hub is a skill published in the GitHub repository wubin1836/ai-hive-agent-skills (8 stars, last pushed 2d ago), licensed MIT. It adds 132 tokens to every session and 1,103 once invoked, about $0.0007 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
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…