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-frontend-experience-spec-roadmap-2026-04-26.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-frontend-experience-spec-roadmap-2026-04-26)<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/task-autopilot-frontend-experience-spec-roadmap-2026-04-26"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/task-autopilot-frontend-experience-spec-roadmap-2026-04-26/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-frontend-experience-spec-roadmap-2026-04-26"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/task-autopilot-frontend-experience-spec-roadmap-2026-04-26.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 | $0.02540 | $0.02540 |
| Opus 5.5 | $0.01016 | $0.01016 |
| Sonnet 5.5 | $0.00508 | $0.00508 |
| Haiku 4.5 | $0.00254 | $0.00254 |
Grade A, and why
WhyBuddy task-autopilot-frontend-experience-spec-roadmap-2026-04-26.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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Autopilot 前端体验落地 specs 路线图（2026-04-26）
背景
任务自动驾驶第一阶段 18 份 specs 已完成产品对象、路线、驾驶舱、runtime、治理与证据链的上层建模。当前前端已经具备首条可见化纵切，但仍存在一个核心落差：
文档与后端投影已经开始像“任务自动驾驶”，但用户进入前端时仍容易感知成“任务工作台 + 智能发起 + 详情面板”。
因此本轮新增 12 份前端体验落地 specs。它们不是替代原有 18 份 task-autopilot specs，而是把原有概念转成可执行、可验收、可测试的前端体验层。
本轮目标
- 把“输入目的地 -> 规划路线 -> 选择路线 -> 进入驾驶舱 -> 车队执行 -> 接管 -> 证据回放”变成前端主体验。
- 避免前端重新发明 Destination、Route、Fleet、Drive State、Takeover、Evidence 等概念。
- 在每份前端 spec 中明确引用原有
18份 specs 的概念来源。 - 在实现任务中加入对原
18份 specs 已落地代码缺陷的回补项，避免只写新 UI 不修旧链路。
12 份前端体验 specs
| 序号 | 新增 spec | 前端落地重点 | 主要引用的既有 specs |
|---|---|---|---|
| 1 | autopilot-launch-destination-input |
目的地输入、输入示例、缺失路标、附件影响 | destination-model-and-parser、mission-model-to-autopilot-model-mapping |
| 2 | autopilot-route-planning-overlay |
输入后弹出路线规划、路线比较、确认执行 | route-planner-and-route-model、route-recommendation-and-selection |
| 3 | autopilot-destination-card-and-goal-lock |
目的地卡片、目标锁定、目标变更影响 | destination-card-and-goal-summary、drive-state-and-replan-state-machine |
| 4 | autopilot-cockpit-three-column-layout |
左目的地路线、中执行、右接管证据三栏主界面 | autopilot-cockpit-information-architecture |
| 5 | autopilot-fleet-live-visualization |
Planner / Clarifier / Executor / Reviewer 等车队角色实时态 | fleet-organization-and-role-packaging、fleet-status-and-live-execution-view |
| 6 | autopilot-drive-state-timeline-and-replan |
驾驶状态时间线、偏航、重规划、下一步 | drive-state-and-replan-state-machine、autopilot-recovery-and-human-takeover-governance |
| 7 | autopilot-takeover-control-panel |
澄清、路线选择、审批、权限、预算、风险统一接管面板 | takeover-panel-and-decision-points、human-in-the-loop 相关底座 |
| 8 | autopilot-evidence-driving-recorder |
证据记录仪、路线事件、接管事件、replay/audit/artifacts 链接 | autopilot-evidence-replay-and-trust-chain |
| 9 | autopilot-mobile-and-responsive-cockpit |
桌面三栏、平板双栏、移动分段驾驶舱 | autopilot-cockpit-information-architecture |
| 10 | autopilot-visual-language-and-motion-system |
自动驾驶视觉 token、路线动效、状态动效、证据动效 | task-autopilot-core-concepts、autopilot-explainability-and-telemetry |
| 11 | autopilot-empty-state-and-onboarding |
示例目的地、首次引导、触发规则说明 | task-autopilot-platform-positioning、task-autopilot-levels-l1-to-l5 |
| 12 | autopilot-frontend-state-model-and-store |
draft / planning / projection 三层前端状态模型 | mission-model-to-autopilot-model-mapping、route-planner-and-route-model |
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 · 153 lines · 2,540 tokens per session scan A d61ece753a87
WhyBuddy task-autopilot-frontend-experience-spec-roadmap-2026-04-26.md is an instructions file published in the GitHub repository xiaojilele-glitch/WhyBuddy (380 stars, last pushed 1mo ago), licensed MIT. It adds 2,540 tokens to every session, about $0.0102 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-frontend-experience-spec-roadmap-2026-04-26.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| WhyBuddy task-autopilot-frontend-experience-spec-roadmap-2026-04-26.mdxiaojilele-glitch/WhyBuddy | Instructions file | 380 | 1mo ago | MIT | A | 2,540 | 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 |