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/web-aigc-live-agent-dashboard.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/web-aigc-live-agent-dashboard)<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/web-aigc-live-agent-dashboard"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/web-aigc-live-agent-dashboard/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/web-aigc-live-agent-dashboard"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/web-aigc-live-agent-dashboard.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 | $0.04527 | $0.04527 |
| Opus 5.5 | $0.01811 | $0.01811 |
| Sonnet 5.5 | $0.00905 | $0.00905 |
| Haiku 4.5 | $0.00453 | $0.00453 |
Grade A, and why
WhyBuddy web-aigc-live-agent-dashboard.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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web-AIGC 后台智能体实时看板
更新时间：2026-04-22
状态口径：按当前各 worktree 的真实落盘情况、已收到的子智能体完成通知、以及本轮并发池补位结果汇总。
阶段切换
当前已经从“第一段薄切片并发开发”切换到“第二阶段主仓库集成”。
这一阶段的重点不再是继续开更多分线，而是：
- 把已经完成首刀的 10 条线按顺序并回主仓库
- 先做低冲突、已成形能力的正式合流
- 再收 platform-b / platform-a / platform-c 三条平台主干
- 最后处理高风险的治理、RAG 风险动作与热路由冲突
为什么输入框里只看到 2 个
输入框上方的“后台智能体”区域，显示的不是“本轮所有曾经启动过的智能体”，而是当前界面里仍然保持可见、可继续 @、或正处于等待下一条指令状态的少数线程。
因此下面这些情况通常不会继续显示在输入框里：
- 已完成并被回收关闭的智能体
- 已完成但不再处于“等待指示”状态的线程
- 仍在后台运行、但没有进入当前输入框快捷显示列表的线程
如果要看全量状态，不要只看输入框上方那 2 个，而要看这份看板。
总体进度
- 功能线总数：
10 - 已全部起刀并有代码落盘：
10 / 10 - 已完成第一段可用薄切片：
10 / 10 - 已并入主仓并完成定向验证的能力线：
4 / 10 - 已并入主仓并完成定向验证的平台底座薄切片：
2 / 3 - 已进入第二阶段主线集成：
是 - 当前主要共性阻塞：多数
worktree缺少完整本地依赖，导致很多线只能做到“代码完成 + 测试补齐”，但无法正式跑vitest/tsc
其中当前已经在主仓完成落地并通过验证的是：
multimodal-outputcontent-processingcontrolflowplatform-a的低风险 runtime / graph projection 兼容底座platform-b的 mission / session / projection links 主干
最新后台只读结论
可优先合流
multimodal-outputcontent-processingcontrolflow
平台主干建议顺序
platform-bplatform-aplatform-c
需要对账式收口
tools-and-agentsrisk-actions
说明：
- 这两条线在主仓库里已经出现了部分先行兼容改动，后续要以主仓库当前状态为准做补差，而不是整分支机械搬运。
后置的中高冲突能力
hitl-sessiondialogue-qa
全量执行面
| 能力线 | Worktree | 分支 | 当前状态 | 验证状态 | 最近产出 |
|---|---|---|---|---|---|
| main-control | sliderule-web-aigc-0-main-control |
chore/web-aigc-main-control |
总控保留 | 不适用 | 不承担功能开发 |
| platform-a | sliderule-web-aigc-1-platform-a |
feat/web-aigc-platform-a |
已并入主仓底座薄切片并验证通过 | runtime / graph projection 定向测试通过，node --run check 已通过 |
统一 workflow domain/runtime、runtime routes、server/shared tests |
| platform-b | sliderule-web-aigc-2-platform-b |
feat/web-aigc-platform-b |
已并入主仓底座薄切片并验证通过 | mission-store、mission-routes 与相关 workflow 回归测试通过，node --run check 已通过 |
mission/session projection links、/api/tasks/:id/projection、/api/tasks/:id/session |
| platform-c | sliderule-web-aigc-3-platform-c |
feat/web-aigc-platform-c |
已完成首刀，待后续收口 | 测试文件已补，正式运行受依赖阻塞 | governance gate、permission audit 镜像主审计链、/api/audit |
| dialogue-qa | sliderule-web-aigc-4-dialogue-qa |
feat/web-aigc-dialogue-qa |
已完成首刀，待后续收口 | 测试文件已补，正式运行受依赖阻塞 | llm/dialogue 与 knowledge_qa 兼容执行入口 |
| hitl-session | sliderule-web-aigc-5-hitl-session |
feat/web-aigc-hitl-session |
已完成首刀，待后续收口 | 测试文件已补，正式运行受依赖阻塞 | DecisionPanel、DecisionHistory、mission client、decision metadata |
| content-processing | sliderule-web-aigc-6-content-processing |
feat/web-aigc-content-processing |
已并入主仓并验证通过 | 4 个路由兼容测试通过，node --run check 已通过 |
document_search + fragment_search RAG adapter |
| multimodal-output | sliderule-web-aigc-7-multimodal-output |
feat/web-aigc-multimodal-output |
已并入主仓并验证通过 | 10 个测试通过，node --run check 已通过 |
OCR provider、vision output artifact、POST /api/vision/ocr、下载接口 |
| tools-and-agents | sliderule-web-aigc-8-tools-and-agents |
feat/web-aigc-tools-and-agents |
已完成首刀，待后续收口 | 测试文件已补，正式运行受依赖阻塞 | auto_agent adapter、/api/a2a/auto-agent、skills/guest-agents execute |
| controlflow | sliderule-web-aigc-9-controlflow |
feat/web-aigc-controlflow |
已并入主仓并验证通过 | 图投影定向测试通过，node --run check 已通过 |
start / variable_assignment / condition / end controlflow adapter |
| risk-actions | sliderule-web-aigc-10-risk-actions |
feat/web-aigc-risk-actions |
已完成首刀，待后续收口 | 测试文件已补，正式运行受依赖阻塞 | vector_insert risk action route、adapter、database checker、RAG ingest 接线 |
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 · 291 lines · 4,527 tokens per session scan A b4a6c1a08b23
WhyBuddy web-aigc-live-agent-dashboard.md is an instructions file published in the GitHub repository xiaojilele-glitch/WhyBuddy (380 stars, last pushed 1mo ago), licensed MIT. It adds 4,527 tokens to every session, about $0.0181 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 web-aigc-live-agent-dashboard.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| WhyBuddy web-aigc-live-agent-dashboard.mdxiaojilele-glitch/WhyBuddy | Instructions file | 380 | 1mo ago | MIT | A | 4,527 | 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 |