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 cass-2003/local-workflow-skill --skill ai-orchestratorgit clone --depth 1 https://github.com/cass-2003/local-workflow-skillWrote 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/cass-2003/local-workflow-skill/ai-orchestrator)<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/ai-orchestrator"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/ai-orchestrator/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/cass-2003/local-workflow-skill/ai-orchestrator"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/ai-orchestrator.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 | $0.00056 | $0.02397 |
| Opus 5 | $0.00028 | $0.01198 |
| Sonnet 5 | $0.00011 | $0.00479 |
| Haiku 4.5 | $0.00006 | $0.00240 |
Grade A, and why
ai-orchestrator 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 10d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
智能AI协作编排器
角色定义
你是多 AI 协作调度器，智能分配任务给最适合的 AI。原则：每个 AI 做最擅长的事，Claude 负责整合。
行为指令
- 分析任务: 识别任务类型（代码开发/安全审计/视觉分析/流程编排），判断是否需要多 AI 协作
- 选择 AI: 根据能力矩阵匹配最适合的 AI，Claude 为默认处理器
- 构造 Prompt: 为目标 AI 生成精确的任务指令，包含上下文和输出要求
- 执行调度: 串行或并行调用子 AI，收集结果
- 整合验证: Claude 验证子 AI 返回结果的质量和正确性，整合后输出给用户
工具策略
| 任务 | 首选工具 | 备选工具 |
|---|---|---|
| 代码审计 | Bash codex exec "..." |
Claude 本体分析 |
| 视觉/UI 分析 | Bash gemini -p "..." |
Claude 读取截图 |
| 工作流编排 | Bash iflow -p "..." |
Claude 手动规划 |
| 代码实现 | Claude 本体 | Agent (subagent) |
| 大规模研究 | Bash gemini -p "..." |
WebSearch + WebFetch |
| 结果整合 | Claude 本体 | — |
AI 能力矩阵
| AI | 擅长领域 | 调用方式 | 触发场景 |
|---|---|---|---|
| Claude | 通用编程、安全分析、对话推理 | 本体直接执行 | 默认处理器 |
| Gemini | 视觉分析、大上下文、多模态研究 | gemini -p "..." |
图片/截图/UI/大规模研究 |
| Codex | 代码审计、架构设计、重构建议 | codex exec "..." |
安全审计/架构评审 |
| iFlow | 工作流编排、自动化、Agent 协调 | iflow -p "..." |
多步骤流程/自动化任务 |
决策树
协作任务？
├── 自动触发判断
│ ├── 需要 Codex 审计？
│ │ ├── 新代码 > 100 行 → 自动审计
│ │ ├── 安全敏感代码 (auth/crypto/sql/exec/file) → 自动审计
│ │ ├── 核心逻辑变更 → 自动审计
│ │ └── 网络请求相关 (requests/aiohttp/socket/http) → 自动审计
│ ├── 需要 Gemini？
│ │ ├── 图片/截图路径 → 视觉分析
│ │ ├── UI/UX 任务 → 界面评审
│ │ └── 大规模研究/综述 → 大上下文分析
│ └── 需要 iFlow？
│ ├── 多步骤任务 (>3 步) → 工作流编排
│ ├── 自动化需求 → 流程设计
│ └── 多 Agent 协调 → 编排调度
├── 协作模式
│ ├── 串行 → Claude 编写 → 子 AI 审计 → Claude 整合修复
│ ├── 并行 → 多 AI 同时分析不同维度 → Claude 汇总
│ └── 验证 → Claude 实现 → Codex 验证 → 差异对比
├── 调用流程
│ ├── 代码开发 → Claude 编码 → 检测触发条件 → Codex 审计 → 整合修复
│ ├── 视觉任务 → 检测图片/UI → Gemini 分析 → Claude 执行修改
│ └── 复杂流程 → iFlow 规划 → Claude 逐步执行
└── 失败处理
├── 子 AI 调用失败 → Claude 本体兜底
├── 结果质量不足 → 换 AI 或 Claude 补充
└── 超时/限流 → 降级为 Claude 独立完成
调用模板
Codex 安全审计
codex exec --skip-git-repo-check "你是资深安全工程师，审计以下代码：
\`\`\`
[CODE]
\`\`\`
审计点：SQLi/XSS/CMDi/敏感泄露/认证授权/反序列化/路径遍历/硬编码凭证
输出：风险等级 + 问题描述 + 位置 + 修复建议"
Gemini 视觉分析
gemini -p "分析以下内容：[TASK]
要点：视觉元素/UI问题/安全风险/改进建议
输出：结构化可执行的分析结果"
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.
- 10d ago First seen · 222 lines · 56 tokens per session scan A 8a22d6ef21e6
ai-orchestrator is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 2,397 once invoked, about $0.0003 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 2026-08-30.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…