agentmods.dev

WhyBuddy: Instructions file for Kiro

.kiro/steering/execution-plan.md

WhyBuddy execution-plan.md is an instructions file for Kiro from xiaojilele-glitch/WhyBuddy. It costs 12,005 tokens per session, scanned A, original, MIT.

A project execution plan that orders specifications by dependency and records their implementation status. It includes a current snapshot of completed modules, open work, and repository size.

In plain words
What is it for?
Use it for roadmap sequencing, dependency checks, progress tracking, and locating completed project areas. It is a planning reference, not a runtime feature.
Why use it?
It helps teams choose what to build next instead of treating hundreds of specifications as an unordered list. The status snapshot also makes older planning information easier to compare with current progress.

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 →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is git worktree add ../cpo-L01-demo-data feat/L01-demo-data-engine.

not rated 380repo 1mo ago A scan 12,005 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/execution-plan.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 execution-plan.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/execution-plan/github.svg)](https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/execution-plan)
Your own site
<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/execution-plan"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/execution-plan/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 execution-plan.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/execution-plan"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/execution-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12,005 This file is loaded in full into every session.
When invoked 12,005 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 $0.12005 $0.12005
Opus 5.5 $0.04802 $0.04802
Sonnet 5.5 $0.02401 $0.02401
Haiku 4.5 $0.01201 $0.01201

Measured 1mo ago against content hash 2105caf93027, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

WhyBuddy execution-plan.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/execution-plan.md · 637 lines

How it starts

The opening of the file, as written. The whole thing — 637 lines — stays where its author put it; the contents beside it link to each section on GitHub.

inclusion: auto

inclusion: auto

Specs 执行顺序与依赖分析

总览

截至 2026-05-28，.kiro/specs 共 287 个目录（requirements.md 285 / design.md 286 / tasks.md 286 / bugfix.md 3），Tasks checkbox 勾选率 7,887 / 8,806（89.6%）。前三层主线与补充 spec holographic-ui 已基本落地，workflow-artifacts-display 已完成功能开发、待最终检查点；任务控制台补完主线与信息架构收口主线已完成，办公室主壳与统一智能发起入口已进入收口阶段，launch-operator-surface-convergence 已完成开发与自动化验证、仅剩桌面手测，最新一轮已补中央底部统一发起框回归、右侧 Launch 说明位收束与墙面 Mission Control HUD 遮挡修复，当前新增规划重点继续转向桌面端首屏体验收束与后墙场景化监控设备推进，平台层能力（L31-L38）仍待环境就绪。

维护说明：本文件保留原始执行顺序与依赖分析，供追溯和继续排期使用；若与旧段落的历史口径冲突，以本节快照为准。

已完成归档模块

  • P00 workflow-engine — 十阶段工作流引擎
  • P01 dynamic-organization — 动态组织生成
  • P02 memory-system — 三级记忆系统
  • P03 evolution-heartbeat — 自进化与心跳
  • P04 mission-runtime — Mission 任务域（核心部分）
  • P05 feishu-bridge — 飞书集成
  • P06 browser-runtime — 纯前端运行时
  • P07 frontend-3d — 3D 场景与前端

当前维护快照（2026-04-15）

  • 体量快照（2026-05-28）：TypeScript / TSX 2,130 文件 / ~545,000 行；Markdown 1,074 份；测试文件 866 份，其中 server/tests 362 份；Git 跟踪文件 5,152 份，Git 提交 748 次。
  • 已合并主线：阶段 0、第一层、第二层和第三层链路均已实现并合并。
  • 已完成补充 spec：ai-enabled-sandbox、executor-integration、holographic-ui。
  • workflow-artifacts-display 已完成功能开发：Artifact API、tasks-store 扩展、ArtifactListBlock / ArtifactPreviewDialog、WorkflowPanel / TaskDetailView 集成与 Socket 联动均已落地；当前仅剩 tasks.md 中最终检查点未勾选。
  • 历史尾项：mission-runtime、multi-modal-vision、nl-command-center、state-persistence-recovery 仍有少量未勾选任务，属于补测或收尾项。
  • 新增近端主线：mission-cancel-control、mission-operator-actions、task-detail-operations-first、execution-language-refresh、mission-ui-polish 已完成。
  • 新增下一波规划：navigation-convergence、task-hub-convergence、api-fallback-empty-states、workflow-panel-decomposition、scene-agent-interaction、workspace-visual-unification 已完成并合并到 main。
  • office-task-cockpit 已进入收口阶段，桌面端办公室主壳、三栏驾驶舱、右侧上下文 tab 与统一智能发起入口已落地；2026-04-21 已恢复中央底部统一发起框为单一主入口，并将右侧 Launch 收束为说明区，剩余桌面兼容回归与手测。
  • task-os-home-redesign-v1 已补一处桌面断点稳定性修正：为 office-cockpit-splitter 的 panel 增加 min-width:0 / min-height:0，避免 1280+ 下横向溢出导致布局抖动（2026-04-20）。
  • launch-operator-surface-convergence 已完成第一阶段实现：UnifiedLaunchComposer 已恢复为中央底部任务操作 rail 的唯一主发起入口，OfficeTaskCockpit.tsx / TasksPage.tsx 已完成接线，TasksCockpitDetail 首屏独立任务操作卡与右侧 Launch 已收束为建议与依据区；自动化回归已补 OfficeTaskCockpit.test.tsx，tasks.md 当前仅剩 7.4 桌面端与窄宽度手动验证未勾选。
  • office-cockpit-first-screen-refresh 已进入近端规划，作为 office-task-cockpit 的后续桌面首屏体验收口项，聚焦“克制驾驶舱 + 主次分层”。
  • office-wall-display-redesign 已进入近端规划，作为 scene-mission-fusion、sandbox-live-preview 与 office-task-cockpit 的后续墙面监控屏改造项，聚焦把后墙升级为“终端 / 任务 / 浏览器”三分区显示器；其中 2026-04-21 已先修复 MissionWallTaskPanel 紧凑 HUD 底部内容被遮挡的问题。
  • 待启动：i18n-cleanup、第四层 L31-L38，以及尚未补 tasks.md 的 frontend-demo-mode。
  • 工程健康：npm run check 当前存在 30 个 TypeScript 错误，属于需要单独收敛的基线欠账。

Read the full file on GitHub · 637 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 · 637 lines · 12,005 tokens per session scan A 2105caf93027

Subscribe to this mod's changes

WhyBuddy execution-plan.md is an instructions file published in the GitHub repository xiaojilele-glitch/WhyBuddy (380 stars, last pushed 1mo ago), licensed MIT. It adds 12,005 tokens to every session, about $0.0480 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.

PlanningProject managementaiai-agentai-agentsanthropicchatgptclaude
Related

WhyBuddy execution-plan.md compared with instructions from other repositories

WhyBuddy execution-plan.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
WhyBuddy execution-plan.mdxiaojilele-glitch/WhyBuddyInstructions file3801mo agoMITA12,005Kiro
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode