Borrowing it
Nothing to install: this file belongs to xiaojilele-glitch/WhyBuddy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xiaojilele-glitch/WhyBuddy/main/.kiro/steering/platform-thesis.mdgit clone --depth 1 https://github.com/xiaojilele-glitch/WhyBuddyWrote 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/instructions/xiaojilele-glitch/whybuddy/platform-thesis)<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/platform-thesis"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/platform-thesis/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/instructions/xiaojilele-glitch/whybuddy/platform-thesis"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/platform-thesis.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 | $0.01085 | $0.01085 |
| Opus 5.5 | $0.00434 | $0.00434 |
| Sonnet 5.5 | $0.00217 | $0.00217 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
WhyBuddy platform-thesis.md 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 1mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
平台主张:在 SlideRule 中构建图式 Agent 运行时
文档目的
本文用于说明,为什么 SlideRule 需要吸收 web-aigc 中部分 AI Agent 编排能力,以及为什么迁移目标应该是“分层平台能力”,而不是一次性的页面搬运或节点复制。
核心判断
SlideRule 目前已经具备比较强的运行时底座能力:
- mission / task 运行时
- workflow 引擎
- replay 与 audit 能力
- RAG 与 knowledge 路由
- voice 与 vision 路由
- A2A 与 skill / plugin 集成
而 web-aigc 的优势不在于这些底座,而在于另一层能力:
- 面向图结构的编排定义
- 节点级配置 schema
- 编排实例与节点监控
- 会话关联的执行观察能力
- 覆盖对话、人工介入、检索、多模态、工具调用、向量操作等的大量节点体系
所以正确战略不是把整个 web-aigc 后台壳子照搬过来,而是让 SlideRule 变成一个“运行时优先、可承载图式编排”的 Agent Office 平台:
- 保留 Cube 当前 mission / task / replay / audit 作为系统主记录
- 吸收
web-aigc中可迁移的编排运行时契约 - 将完整的可视化流程定义能力延后到图运行时模型稳定之后
- 把迁移结果沉淀为平台能力,而不是 52 个互不相关的节点克隆
非目标
- 第一阶段不重建完整的
web-aigc编排后台 CRUD 系统 - 第一阶段不把所有节点都作为正式产品能力落地
- 不让前端节点 schema 先于服务端运行时契约失控扩张
- 不做“52 个节点,52 套孤岛 spec”的碎片化方案
文档与设计立场
正确的文档与实现方式应当是分层的:
- 顶层:平台主张、迁移计划、接口 inventory、ADR
- 中层:平台核心 spec
- 能力层:吸收一组节点家族的能力簇 spec
- 叶子层:只为高价值迁移对象建立节点 dossier
这样的好处是:既能保证扩展性,又不会落成“一节点一孤岛”的脆弱结构。
为什么 web-aigc 值得迁移
从已检查的源码来看,web-aigc 已经形成了比较清晰的三层能力分离:
- 编排定义与版本管理 API
- 设计器校验 / 执行 API
- 实例监控与会话查看 API
已检查的关键文件包括:
web-aigc/src/pages/aigc/orchestration/list/services/index.tsweb-aigc/src/pages/aigc/orchestration/designer/services/index.tsweb-aigc/src/pages/aigc/agent-monitoring/services/monitorApi.tsweb-aigc/src/pages/aigc/orchestration/designer/nodes/nodeTypes.ts
而这些能力与 Cube 现有服务端运行时接口天然存在衔接点,例如:
server/routes/workflows.tsserver/routes/tasks.tsserver/routes/replay.tsserver/routes/rag.tsserver/routes/voice.tsserver/routes/vision.tsserver/routes/knowledge.tsserver/routes/a2a.tsserver/routes/skills.ts
产品定位
如果迁移方向正确,SlideRule 可以形成这样一种差异化定位:
- 不是单纯 canvas-first 的流程平台,而是 runtime-first 的 Agent 平台
- 默认具备 replay、audit、lineage、operator control
- 既能支持图式编排,又保留 mission-centric 的任务操作模型
- 对企业治理、权限、安全和运营动作更友好
- 能把底层节点流和上层 mission 执行壳连接起来
成功标准
web-aigc中选中的编排接口,在 Cube 中都有明确承接落点- 平台文档优先描述可复用抽象,而不是先堆节点细节
- 后续实现可以按能力簇逐步推进,而不会频繁打碎 API
- 图式编排成为 Cube 的增强能力,而不是一套分裂出去的新产品
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.
- 1mo ago First seen · 105 lines · 1,085 tokens per session scan A cbde298186fd
WhyBuddy platform-thesis.md is an instructions file published in the GitHub repository xiaojilele-glitch/WhyBuddy (380 stars, last pushed 1mo ago), licensed MIT. It adds 1,085 tokens to every session, about $0.0043 per session on Opus 5.5. 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 2026-09-23.
WhyBuddy platform-thesis.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| WhyBuddy platform-thesis.mdxiaojilele-glitch/WhyBuddy | Instructions file | 380 | 1mo ago | MIT | A | 1,085 | Kiro |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |