What is WhyBuddy task-autopilot-spec-roadmap-2026-04-23.md?

A roadmap for developing the task automation platform in stages. It proposes groups of technical specifications covering product concepts, the task interface, the execution engine, safety controls, and connections to existing AI workflow features.

Use it to decide what to design first, estimate documentation scope, and sequence work from product concepts through runtime behavior and safety boundaries.

It helps the team choose a workable amount of planning before implementation. The staged options avoid both vague plans and an unnecessarily large set of documents.

How xiaojilele-glitch/WhyBuddy configures Kiro

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/task-autopilot-spec-roadmap-2026-04-23.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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/task-autopilot-spec-roadmap-2026-04-23/github.svg)](https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/task-autopilot-spec-roadmap-2026-04-23)

Your own site

<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/task-autopilot-spec-roadmap-2026-04-23"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/task-autopilot-spec-roadmap-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/task-autopilot-spec-roadmap-2026-04-23"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/task-autopilot-spec-roadmap-2026-04-23.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,988 This file is loaded in full into every session.

When invoked 4,988 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.

Model	Per session	Once invoked
Fable 5.1	$0.04988	$0.04988
Opus 5.5	$0.01995	$0.01995
Sonnet 5.5	$0.00998	$0.00998
Haiku 4.5	$0.00499	$0.00499

Measured 1mo ago against content hash 59352f447179, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

WhyBuddy task-autopilot-spec-roadmap-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.

.kiro/steering/task-autopilot-spec-roadmap-2026-04-23.md · 684 lines

How it starts

The opening of the file, as written. The whole thing — 684 lines — stays where its author put it; the contents beside it link to each section on GitHub.

任务自动驾驶 specs 路线图（2026-04-23）

背景

SlideRule 当前已经不是一个单纯的“聊天式 Agent 演示项目”，而是一个具备以下底座能力的任务操作系统：

mission-first 的主界面与任务工作台
十阶段工作流引擎与 Mission Runtime
review / audit / revision / verify 闭环
replay / lineage / evidence / telemetry 可观察能力
Web-AIGC 58 / 58 specs 封板基线与主服务主线接线
A2A、Guest Agent、Swarm、真实执行器、浏览器预演运行时

在这个基础上，将产品叙事从“任务操作系统”进一步升级为“任务自动驾驶平台”是成立的。用户不再只是给出 prompt，而是输入一个“目的地”；系统不再只返回答案，而是自动规划路线、组建车队、执行、澄清、调整，并在必要时请求人工接管。

本文件用于回答一个具体问题：

如果沿“任务自动驾驶”方向继续推进，建议拆出多少 specs，分别是什么，先后顺序如何。

结论

结合当前仓库已有的 spec 粒度、Web-AIGC 的高颗粒拆分经验，以及这次“任务自动驾驶”涉及产品、交互、runtime、治理多层联动的特点，建议按三档规模评估：

规模	建议份数	适用目标
最小验证版	`8 ~ 12`	先验证产品叙事是否成立，支撑一版概念原型与 README / steering 升级
标准产品化版	`15 ~ 22`	形成完整产品定义、概念模型、驾驶舱 IA、runtime 映射与治理边界
平台完整版	`28 ~ 36`	深入到 route、状态机、风险评估、车队编组、回放驾驶时间线、证据链等平台级细拆

建议第一阶段以 18 份 specs 为主线推进。

原因：

少于 10 份会过粗，后面容易回退成大而空的产品文案；
一上来做 30+ 份会过早进入文档膨胀；
18 份刚好能覆盖“产品定位 + 概念模型 + 驾驶舱交互 + runtime 接线 + 治理边界 + Web-AIGC 节点映射”六个核心维度。

如果每份 spec 仍采用当前项目标准三件套：

requirements.md
design.md
tasks.md

那么第一阶段文档体量约为：

1 份总路线图（本文件）
18 × 3 = 54 份 spec markdown
总计约 55 份核心文档

这个规模与此前 Web-AIGC 58 份 specs 的体量接近，符合当前仓库的文档与推进习惯。

拆分原则

1. 先抽象产品对象，再改造底层 runtime

不建议一开始就把底层代码里的 mission / workflow / task 统一重命名成 destination / route / drive-state。更稳妥的做法是：

产品层引入新的用户态对象
runtime 层先做映射与投影
确认概念稳定后，再判断是否需要深度改名或重构

2. 不直接向用户暴露 50+ 节点

对外层应抽象成：

目的地
推荐路线
当前车队
驾驶状态
接管点

底层节点仍然保留在内部编排与能力映射层。

3. 先做“产品自动驾驶”，后做“平台全自动”

第一阶段不追求开放域 L5 自动执行，而是明确：

哪些任务可以自动规划
哪些阶段必须接管
哪些路线只适用于限定场景

4. 复用现有 mission-first 底座

优先复用现有：

mission-runtime
workflow-engine
human-in-the-loop
task-runtime-visibility-v1
office-task-cockpit
replay-and-debug-surface-v1
audit-chain
data-lineage-tracking
web-aigc-platform-*

避免重复造平台底座。

当前执行状态（2026-04-26）

本路线图已经完成第一阶段闭环，当前状态如下：

Read the full file on GitHub · 684 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.

1mo ago First seen · 684 lines · 4,988 tokens per session scan A 59352f447179

Subscribe to this mod's changes

WhyBuddy task-autopilot-spec-roadmap-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 4,988 tokens to every session, about $0.0200 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.

Planning Project management ai ai-agent ai-agents anthropic chatgpt claude

WhyBuddy task-autopilot-spec-roadmap-2026-04-23.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
WhyBuddy task-autopilot-spec-roadmap-2026-04-23.mdxiaojilele-glitch/WhyBuddy	Instructions file	380	1mo ago	MIT	A	4,988	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

WhyBuddy: Instructions file for Kiro