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 skills/itmisx/deepx-code/creating-workflowsnpx skills add itmisx/deepx-code --skill creating-workflowsgit clone --depth 1 https://github.com/itmisx/deepx-codeWhat 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 | $0.00058 | $0.03992 |
| Opus 5 | $0.00029 | $0.01996 |
| Sonnet 5 | $0.00012 | $0.00798 |
| Haiku 4.5 | $0.00006 | $0.00399 |
Grade A, and why
creating-workflows 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 yesterday.
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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
创建 workflow
deepx 的 workflow 是一段 JavaScript 脚本,用固定流程编排多个子 agent:脚本控制流程(循环、扇出、汇总),每个 agent() 调用做一次真正的 LLM 工作。脚本在 QuickJS 沙箱里跑,只能通过下列全局函数触达外界。
何时用
- 多视角审查、扇出研究、流水线处理、对抗式验证、循环到无新增——这类固定可复用、会重复跑的多步编排。
- 一次性的简单任务别用 workflow,直接做。
脚本格式(务必照此)
export const meta = {
name: "my-flow", // 必须等于文件名(不含后缀 .mjs),kebab-case
description: "一句话说明这个 workflow 做什么",
phases: [ // 可选,用于进度展示
{ title: "Collect", detail: "收集信息" },
{ title: "Report", detail: "汇总成报告" },
],
};
export default async function main(args) { // 入口必须是 default 导出的 async 函数
phase("Collect");
const data = await agent("收集关于 X 的信息", { label: "收集信息", model: "flash" });
phase("Report");
// 汇总/出报告这步用 pro(更稳),收集那步用默认 flash。label 用任务描述、跟随用户语言。
return await agent("基于以下内容写报告:\n" + data, { label: "写报告", model: "pro" });
}
规则:
- 第一段(去注释后)必须是
export const meta = {...},且meta.name等于文件名。 - 名字只能小写字母、数字、连字符(kebab-case)。
- 入口必须是
export default async function main(args)。
全局 API
-
agent(prompt, opts?)→ Promise:跑一个子 agent,resolve 出它的文本结果。opts:label:进度显示名(单行显示在步骤里)。写成简短的任务描述(如「正确性审查」/「collect changes」),让用户一眼看懂这步在干嘛;用与用户请求相同的语言(用户用中文提需求就用中文 label,英文就英文)。别用collector/step1这种没信息量的英文 ID。model:"flash"(默认,快、便宜,适合收集/检索/简单审查这类轻活)或"pro"(更强,适合汇总合并、复杂推理、写最终报告这类重活)。不写就是 flash。phase:归属阶段(配合phase())。schema:JSON Schema,要结构化结果时用,resolve 出已解析的对象。
// 轻活:用 flash(省略 model 也是 flash)。label 写成任务描述、跟随用户语言。 const data = await agent("收集 X 的资料", { label: "收集资料", model: "flash" }); // 重活(汇总/出报告):显式 model: "pro" const report = await agent("把上面资料合并成 markdown 报告:\n" + data, { label: "写报告", model: "pro", }); // 要结构化结果:加 schema(resolve 出已解析对象,不是字符串) const picks = await agent("列出 3 条改进建议", { label: "列改进建议", model: "pro", schema: { type: "object", required: ["items"], properties: { items: { type: "array", items: { type: "string" } }, }, }, }); // picks.items 是数组
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.
- yesterday First seen · 228 lines · 58 tokens per session scan A dd2cee4aeb8d
creating-workflows is a skill published in the GitHub repository itmisx/deepx-code (383 stars, last pushed 7d ago), licensed MIT. It adds 58 tokens to every session and 3,992 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
ai-style
当任务是用中文撰写或改写面向读者的文案(产品发布稿、公众号文章、邮件、README 等), 或用户反馈文字「AI 味太重」「不像人写的」时,加载本 Skill。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
data_analysis
基于已确认数据执行可审计的数学计算和描述统计。.
pr-comments
Use when the user asks to review pull request comments, or when the /pr-comments command runs — fetch and analyze PR review comments on the current branch and summarize actionable items.
review
Use when asked to review a codebase or a change, or when the /review command runs — assess design, correctness, maintainability, and test coverage with actionable feedback.
dsh-doc-site-sync
Use when publishing, updating, moving, or removing DeepSeek Harness documentation website pages; editing website/docs.ts mappings or navigation; diagnosing a page missing from the VitePress site; fixing projected documentation links; or running the docs:dev, docs:check, and doc-sync workflow after website-content…