WhyBuddy: Instructions file for Kiro

.kiro/steering/platform-thesis.md

WhyBuddy platform-thesis.md is an instructions file for Kiro from xiaojilele-glitch/WhyBuddy. It costs 1,085 tokens per session, scanned A, original, MIT.

A platform design for running AI agents as connected workflows, where each step can call tools, retrieve information, involve a person, or process different kinds of input. It proposes adding this graph-based runtime to SlideRule while keeping missions, task records, replays, and audits as the main system records.

In plain words
What is it for?
Use it to guide the design of agent execution, workflow steps, human intervention, retrieval, tool calls, monitoring, replay, and auditing.
Why use it?
It separates reusable runtime capabilities from future visual workflow editors and avoids copying an entire product or building many isolated features. That gives later agent features a shared foundation and clear boundaries.

Instructions file for Kiro

Written for Kiro: installed under .kiro/.

This is xiaojilele-glitch/WhyBuddy's own configuration. It tells Kiro how to work on WhyBuddy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything WhyBuddy configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/xiaojilele-glitch/WhyBuddy/main/.kiro/steering/platform-thesis.md
Clone the repo
git clone --depth 1 https://github.com/xiaojilele-glitch/WhyBuddy

Made for: Kiro.

Wrote 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.

agentmods badge for WhyBuddy platform-thesis.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/platform-thesis/github.svg)](https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/platform-thesis)
Your own site
<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.

agentmods 80×15 button for WhyBuddy platform-thesis.md

Your own site · 80×15
<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>
Per session 1,085 This file is loaded in full into every session.
When invoked 1,085 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 1mo ago against content hash cbde298186fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

.kiro/steering/platform-thesis.md · 105 lines

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:

  1. 保留 Cube 当前 mission / task / replay / audit 作为系统主记录
  2. 吸收 web-aigc 中可迁移的编排运行时契约
  3. 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
  4. 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.ts
  • web-aigc/src/pages/aigc/orchestration/designer/services/index.ts
  • web-aigc/src/pages/aigc/agent-monitoring/services/monitorApi.ts
  • web-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.ts
  • server/routes/tasks.ts
  • server/routes/replay.ts
  • server/routes/rag.ts
  • server/routes/voice.ts
  • server/routes/vision.ts
  • server/routes/knowledge.ts
  • server/routes/a2a.ts
  • server/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

Read the full file on GitHub · 105 lines

Changes

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.

  1. 1mo ago First seen · 105 lines · 1,085 tokens per session scan A cbde298186fd

Subscribe to this mod's changes

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.

Related

WhyBuddy platform-thesis.md compared with instructions from other repositories

WhyBuddy platform-thesis.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
WhyBuddy platform-thesis.mdxiaojilele-glitch/WhyBuddyInstructions file3801mo agoMITA1,085Kiro
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode