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/task-autopilot-platform-narrative-2026-04-23.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/task-autopilot-platform-narrative-2026-04-23)<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/task-autopilot-platform-narrative-2026-04-23"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/task-autopilot-platform-narrative-2026-04-23/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/task-autopilot-platform-narrative-2026-04-23"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/task-autopilot-platform-narrative-2026-04-23.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 | $0.05111 | $0.05111 |
| Opus 5.5 | $0.02044 | $0.02044 |
| Sonnet 5.5 | $0.01022 | $0.01022 |
| Haiku 4.5 | $0.00511 | $0.00511 |
Grade A, and why
WhyBuddy task-autopilot-platform-narrative-2026-04-23.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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
任务自动驾驶平台总叙事(2026-04-23)
文档目的
本文用于为 SlideRule 提炼一版可直接复用的中文总叙事,供以下场景统一口径:
- README 与首页介绍
- 路演、演示与对外表达
- 对内汇报、产品定义与研发对齐
本文不试图重写现有技术事实,而是把当前已经存在的主仓能力,收束为一套更稳定、更容易传播的“任务自动驾驶平台”叙事。
一、结论先行
SlideRule 不应该再被描述为一个“聊天式 AI 演示项目”,也不只是一个“多 Agent 工作流工具”。
更准确的定义是:
它是一个面向 AI 任务交付的任务自动驾驶平台。用户输入的不再只是 prompt,而是目的地、约束与交付要求;系统输出的不再只是一段答案,而是一条可规划、可执行、可接管、可回放、可审计的任务闭环。
这一定义有三个关键含义:
- 产品主语从“对话”升级为“任务送达”。
- 平台主能力从“回答问题”升级为“规划路线、组织执行、管理风险、交付结果”。
- 用户体验主界面从“聊天窗口”升级为“驾驶舱”。
二、产品定位
1. 平台定位
SlideRule 的目标不是做一个更花哨的 chat UI,也不是把一组 Agent 能力堆成一个控制台,而是构建一个:
runtime-first、mission-first、evidence-backed 的任务自动驾驶平台。
其中三层含义分别是:
runtime-first:重点不是“如何画流程图”,而是“任务是否真的被执行、是否可恢复、是否可观测、是否可信”。mission-first:对用户暴露的核心对象不是 node、prompt 或 agent,而是任务、路线、进度、接管点与交付结果。evidence-backed:任何自动执行都不是黑箱;平台必须保留日志、产物、审计、血缘、回放与原因解释。
2. 一句话定义
任务自动驾驶平台,是把用户目标转成可规划路线、可组织车队、可在真实环境执行、可在关键节点请求接管、并可全程回放审计的 AI 任务系统。
3. 它解决的核心问题
传统 AI 产品大多停留在“会回答”,但企业与团队真正关心的是:
- 任务能否被稳定送达
- 过程中是否可见、可控、可接管
- 是否能连接真实工具、真实执行环境与真实交付物
- 出问题后是否能复盘、审计、追责与优化
任务自动驾驶平台回答的不是“模型会不会说”,而是:
这个任务能不能以可控风险到达目标。
4. 与“任务操作系统”口径的关系
现有 README 中的 “task operating system” 口径仍然成立,但它更偏底座描述。
可以这样理解两者关系:
任务操作系统:强调平台具备任务对象、运行时、执行器、回放、审计等基础设施。任务自动驾驶平台:强调用户价值与产品体验,即平台会帮用户规划路线、组织执行,并在边界处请求接管。
一句话说:
任务操作系统描述的是底层能力,任务自动驾驶平台描述的是上层产品承诺。
三、核心对象
为避免继续混用 chat、workflow、mission、agent 等多套叙事,建议对外统一为以下核心对象。
| 核心对象 | 产品含义 | 用户看到的是什么 | 当前主仓承接 |
|---|---|---|---|
Destination 目的地 |
用户真正想达成的目标状态,包含目标、约束、成功标准、交付要求 | “我要去哪、交付什么、受什么限制” | 当前主要由任务发起输入、/api/tasks、mission 创建参数承接 |
Route 路线 |
平台为达成目的地生成的执行方案,包含阶段、候选路径、风险点、时间与成本预估 | “为什么这样走、还有哪些备选” | 当前由 ExecutionPlan、workflow runtime definition、任务阶段与 operator 动作局部承接 |
Fleet 车队 |
为这条路线临时组织的角色、Agent、工具、技能与外部执行单元 | “谁在协同完成这件事” | 当前由动态组织、skills、MCP、A2A、guest agents、Web-AIGC 节点族共同承接 |
Drive State 驾驶态 |
任务当前处于理解、规划、执行、审核、阻塞、接管、重规划还是已送达 | “现在进行到哪一步了” | 当前由 mission 状态、workflow runtime 状态、operator state、executor 状态共同承接 |
Takeover Point 接管点 |
需要人类澄清、确认、审批、补充上下文或中止执行的边界点 | “什么时候需要我出手” | 当前由 HITL、selection、confirm_judge、param_collection、任务决策接口与 operator actions 承接 |
Evidence Pack 证据包 |
支撑任务可信交付的日志、产物、状态、审计、血缘、成本、回调记录 | “为什么我能相信这个结果” | 当前由 artifacts、telemetry、audit、lineage、executor callback、runtime events 承接 |
Replay 回放 |
对一次任务执行全过程的时间线、快照与证据复盘能力 | “这件事到底是怎么完成的” | 当前由 /api/replay、ReplayPage、snapshot/export/verify 链路承接 |
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 · 309 lines · 5,111 tokens per session scan A 548b01a06f5d
WhyBuddy task-autopilot-platform-narrative-2026-04-23.md is an instructions file published in the GitHub repository xiaojilele-glitch/WhyBuddy (380 stars, last pushed 1mo ago), licensed MIT. It adds 5,111 tokens to every session, about $0.0204 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 task-autopilot-platform-narrative-2026-04-23.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| WhyBuddy task-autopilot-platform-narrative-2026-04-23.mdxiaojilele-glitch/WhyBuddy | Instructions file | 380 | 1mo ago | MIT | A | 5,111 | Kiro |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |