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-implementation-waves-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-implementation-waves-2026-04-23)<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/task-autopilot-implementation-waves-2026-04-23"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/task-autopilot-implementation-waves-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-implementation-waves-2026-04-23"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/task-autopilot-implementation-waves-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 | $0.05643 | $0.05643 |
| Opus 5.5 | $0.02257 | $0.02257 |
| Sonnet 5.5 | $0.01129 | $0.01129 |
| Haiku 4.5 | $0.00564 | $0.00564 |
Grade A, and why
WhyBuddy task-autopilot-implementation-waves-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 — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
任务自动驾驶实现波次（2026-04-23）
2026-04-26 增补：Wave 1 已完成，进入 runtime 深化
截至 2026-04-26，Task Autopilot 第一阶段已经从“规格拆分”推进到“可验证基线闭环”：
18 / 18份 task-autopilot specs 已闭合，54 / 54份 markdown、345 / 345顶层核心任务项、602 / 602raw checklist 项均已完成。Wave 1的语义契约与投影基线已落地：shared/mission/autopilot.ts、parseMissionDestination()、服务端Mission -> Destination / Route / Drive State / Takeoverprojection、客户端tasks-storenormalize 已形成兼容优先的纵切。Wave 3已有最小驾驶舱消费切片：TaskAutopilotPanel能在任务详情侧消费 destination、route、drive state、takeover、fleet 与 evidence 摘要。- 当前闭环不等于开放域 L5，也不表示 runtime 已经具备完全无人值守自动编队；它表示第一阶段读模型、投影链路、任务面展示和测试直证已经对齐。
- 下一阶段应继续推进
Wave 2 / Wave 4：runtime orchestration、takeover bridge、replan record、fleet snapshot、evidence / replay / metrics 闭环，而不是继续新增大批 specs。
进度总览以 docs/task-autopilot-18-spec-progress-overview-2026-04-24.svg 为准；闭环说明见 .kiro/steering/task-autopilot-phase-1-closure-2026-04-26.md。
目的
这份文档不是重复 18 份 task-autopilot specs 的摘要，而是把它们收敛成当前主仓可执行的代码落地顺序。
目标是回答四个实现问题：
- 先把哪些对象和投影落到代码里，才能避免后续 UI 和 runtime 各写各的。
- 哪些能力应当复用现有
mission / workflow / replay / audit / lineage基座，而不是新起一套“autopilot 后台”。 - 哪些代码区域最适合承接
Destination / Route / Drive State / Fleet / Takeover。 - 每一波做到什么程度，就可以被认为已经从 spec 进入了“可验证实现”。
实施原则
- 兼容优先，不建议第一波就大规模把
mission / workflow / runtime重命名成destination / route / drive-state。 - 先做共享契约与投影，再做 runtime 控制语义，再做驾驶舱 UI，最后做证据链、回放与指标闭环。
- 优先复用现有任务域与主线观测能力：
server/tasks/*、server/core/workflow-runtime-engine.ts、server/routes/tasks.ts、server/routes/replay.ts、server/routes/audit.ts、server/routes/lineage.ts、client/src/components/tasks/*。 - 每一波都要形成端到端最小闭环，至少包含：共享字段定义、服务端投影、前端消费或测试验证三者中的两项，不能只停留在类型声明。
- 所有“解释”“风险”“置信度”“证据”都必须能回指真实事实来源；若只是前端推断，必须明确标注为推断，不得伪装成 runtime 已确认事实。
当前实现锚点
18 份 specs 的落地并不是从零开始，当前主仓已经有可复用的承载面：
- 共享契约与投影：
shared/mission/autopilot.ts、shared/mission/contracts.ts、shared/mission/projection.ts、shared/mission/api.ts、shared/mission/socket.ts、shared/workflow-domain.ts、shared/workflow-runtime.ts - 任务运行时与编排：
server/tasks/mission-runtime.ts、server/core/mission-orchestrator.ts、server/tasks/mission-operator-service.ts、server/tasks/mission-decision.ts - projection 与 API：
server/tasks/mission-projection.ts、server/routes/tasks.ts、server/routes/workflows.ts - runtime 与可观测桥接：
server/core/workflow-runtime-engine.ts、server/core/web-aigc-runtime-observability.ts - 回放、审计、血缘：
server/routes/replay.ts、server/replay/*、server/audit/*、server/lineage/* - 前端任务承载面：
client/src/lib/mission-client.ts、client/src/lib/tasks-store.ts、client/src/components/tasks/TaskAutopilotPanel.tsx、client/src/components/tasks/*、client/src/pages/tasks/* - 前端 replay / telemetry 承载面：
client/src/lib/replay/*、client/src/lib/browser-telemetry-store.ts、client/src/components/replay/*、client/src/components/permissions/AuditTimeline.tsx、client/src/components/lineage/*
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 · 390 lines · 5,643 tokens per session scan A f6bdda236827
WhyBuddy task-autopilot-implementation-waves-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 5,643 tokens to every session, about $0.0226 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-implementation-waves-2026-04-23.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| WhyBuddy task-autopilot-implementation-waves-2026-04-23.mdxiaojilele-glitch/WhyBuddy | Instructions file | 380 | 1mo ago | MIT | A | 5,643 | 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 |