agentmods.dev

WhyBuddy: Instructions file for Kiro

.kiro/steering/task-autopilot-repo-alignment-2026-04-23.md

WhyBuddy task-autopilot-repo-alignment-2026-04-23.md is an instructions file for Kiro from xiaojilele-glitch/WhyBuddy. It costs 6,198 tokens per session, scanned A, original, MIT.

An alignment document that maps the task automation language onto the existing mission, workflow, runtime, decision, audit, and replay systems. It treats terms such as destination, route, drive state, takeover, and evidence as views of existing data rather than a separate system.

In plain words
What is it for?
Use it to plan compatible changes, connect user-facing task concepts to backend data, and guide work on routing, team coordination, human takeover, recovery, replay, and success measures.
Why use it?
It prevents new product names from replacing the software's established sources of truth. It also records what has been implemented and what still needs deeper runtime behavior.

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 →

not rated 380repo 1mo ago A scan 6,198 tokens original MIT
View source ↗ xiaojilele-glitch/WhyBuddy miantuan.ai
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-repo-alignment-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.

agentmods badge for WhyBuddy task-autopilot-repo-alignment-2026-04-23.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/task-autopilot-repo-alignment-2026-04-23/github.svg)](https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/task-autopilot-repo-alignment-2026-04-23)
Your own site
<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/task-autopilot-repo-alignment-2026-04-23"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/task-autopilot-repo-alignment-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.

agentmods 80×15 button for WhyBuddy task-autopilot-repo-alignment-2026-04-23.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/task-autopilot-repo-alignment-2026-04-23"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/task-autopilot-repo-alignment-2026-04-23.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,198 This file is loaded in full into every session.
When invoked 6,198 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 $0.06198 $0.06198
Opus 5.5 $0.02479 $0.02479
Sonnet 5.5 $0.01240 $0.01240
Haiku 4.5 $0.00620 $0.00620

Measured 1mo ago against content hash 59334035373c, 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-repo-alignment-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-repo-alignment-2026-04-23.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

任务自动驾驶与现有仓库对齐关系（2026-04-23）

2026-04-26 增补：Phase 1 已闭合

本文件原始判断仍然成立：task-autopilot 是现有 mission-first 主仓之上的产品投影层，不是第二套事实源。

但当前状态已经从“18 份 specs 待实现”推进为：

  • 18 / 18 specs 已完成并收口
  • 54 / 54 markdown 已完成
  • 345 / 345 顶层任务项已闭合
  • 602 / 602 raw checklist 已闭合
  • 第一条 compatibility-first 代码纵切已进入主线

当前已经落地的对齐锚点：

  • Mission -> Destination
    • shared/mission/autopilot.ts 的 parseMissionDestination() 与 MissionAutopilotSummary.destination
  • Workflow / Mission stage -> Route
    • autopilot route summary、candidate route、route selection / replan 字段
  • Runtime state -> Drive State
    • inferMissionAutopilotDriveState() 与 server projection
  • Decision / HITL -> Takeover
    • takeover summary、decision prompt、missing-info clarifications、operator actions
  • Runtime facts -> Evidence / Explanation
    • evidence timeline、correlation index、recommendation details、remaining steps

仍需保持的边界：

  • 不宣称开放域 L5。
  • 不把 projection 等同于完整 runtime 自动化。
  • 不以产品对象重命名替代 Mission / Workflow / Runtime 的事实主干。
  • 下一阶段重点应转向 runtime 行为深化：parser 版本化、route planner 自动编队、fleet orchestration、takeover governance、evidence replay trust chain 与 success metrics。

目的

这份文档用于回答一个实际问题：task-autopilot 的 18 份 specs，不应该被理解成“另起一套新的任务平台”，而应该被理解成对现有 mission-first 主仓的一层上位产品抽象。

本文重点说明三件事：

  1. task-autopilot 与现有 README、project-overview、Mission Runtime、workflow runtime、HITL、replay、audit、lineage、Web-AIGC 主线分别如何对齐。
  2. 哪些 specs 主要是在复用现有底座做“产品投影和界面收口”。
  3. 哪些 specs 虽然已有部分基础，但本质上仍属于待实现能力，不能写成“仓库已经完成”。

本文坚持一个前提：compatibility-first。

Compatibility-First 结论

1. task-autopilot 是上位叙事，不是第二套事实源

当前仓库的事实主干已经很明确：

  • README 与 README.zh-CN 把产品定位为 mission-first 的任务操作系统。
  • .kiro/steering/project-overview.md 把系统主干定义为办公室主壳、任务工作台、Mission Runtime、workflow runtime、replay / audit / lineage 与 Web-AIGC 主线能力的组合。
  • Mission Runtime、workflow runtime、HITL、replay、audit、lineage、Web-AIGC 都已经有各自的契约、路由、事件和测试证据。

因此，task-autopilot 更适合做成：

  • 产品层：Destination / Route / Drive State / Fleet / Takeover
  • 工程层：继续保留 mission / workflow / runtime / decision / replay / audit
  • 中间层：通过映射、投影、聚合和 UI 收口把两层连接起来

Read the full file on GitHub · 327 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 · 327 lines · 6,198 tokens per session scan A 59334035373c

Subscribe to this mod's changes

WhyBuddy task-autopilot-repo-alignment-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 6,198 tokens to every session, about $0.0248 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.

Building agentsPlanningaiai-agentai-agentsanthropicchatgptclaude
Related

WhyBuddy task-autopilot-repo-alignment-2026-04-23.md compared with instructions from other repositories

WhyBuddy task-autopilot-repo-alignment-2026-04-23.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
WhyBuddy task-autopilot-repo-alignment-2026-04-23.mdxiaojilele-glitch/WhyBuddyInstructions file3801mo agoMITA6,198Kiro
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode