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-spec-execution-matrix.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-spec-execution-matrix)<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/web-aigc-spec-execution-matrix"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/web-aigc-spec-execution-matrix/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-spec-execution-matrix"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/web-aigc-spec-execution-matrix.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 | $0.05330 | $0.05330 |
| Opus 5.5 | $0.02132 | $0.02132 |
| Sonnet 5.5 | $0.01066 | $0.01066 |
| Haiku 4.5 | $0.00533 | $0.00533 |
Grade A, and why
WhyBuddy web-aigc-spec-execution-matrix.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.
This is a copy
81% identical to WhyBuddy current-state.md — 985 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 650 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web-AIGC 迁移 Spec 执行矩阵
文档目标
本文用于说明当前保留下来的 58 个 web-aigc 迁移 spec,哪些可以并行执行,哪些必须先收口,哪些适合先做文档、后做实现,以及在代码阶段应如何组织并发,避免多人或多线程同时改同一层抽象导致反复返工。
适用范围
本文覆盖以下文档集合:
6个平台级 spec:web-aigc-platform-*52个节点级 spec:web-aigc-node-*
总计 58 个 spec 目录,每个目录均包含:
requirements.mddesign.mdtasks.md
核心结论
这 58 个 spec:
- 可以并行推进
- 但不能无依赖地
58个一起平铺执行 - 最合理的方式是“平台先收口一轮,节点按能力簇并行”
如果是文档推进:
- 并行度可以做到
70% - 80%
如果是代码推进:
- 推荐并发度控制在
8 - 12条工作流 - 不建议按
58个 spec 一起开工
2026-04-23 主线接线校准
需要明确:
58 / 58份web-aigcspecs 与238 / 238个顶层任务已全部完成,这是已经封板的事实。- 本文保留的 L0-L5 分层、能力簇和波次,主要用于说明“后续主线增强如何分批并行收口”,不再表示 spec 完成度。
- 2026-04-23 主线已确认新增接线:
server/index.ts已挂载robot-reply、open-page、mcp、open-dashboard、web-search、web-qa、get-location-info、get-device-info、vector-update、vector-delete等入口;server/routes/workflows.ts已挂载open-report子路由,并承载/api/workflows/:id/runtime/run、/api/workflows/:id/runtime/retry、/api/workflows/:id/runtime/escalate的 workflow runtime governance 控制链路;RAGvectorStore已通过ragDeps暴露给/api/rag、向量治理与风险动作路由。 - 因此,文中“优先实现”“延后”“空白项”等表述,都应理解为主线补线优先级,不等同于“未启动”或“spec 未完成”。
执行原则
原则 1:先平台,后节点
6 个平台级 spec 是 52 个节点 spec 的上位约束,必须先形成第一轮统一结论,否则节点级实现会反复返工。
原则 2:按能力簇并行,不按单节点乱并行
节点级 spec 看似有 52 个,但真正落地时应该按能力簇推进,而不是 52 个节点平铺推进。
原则 3:文档并行度高于代码并行度
文档阶段只要术语、状态、接口归一,很多组可以同时写;代码阶段则受共享文件、共享接口、共享状态机影响更大。
原则 4:共享写入范围必须隔离
同一批并行工作如果都要改:
shared契约server/core/workflow-engine.tsserver/routes/workflows.tsserver/routes/tasks.ts
那么冲突概率会急剧上升,必须分批。
分层执行模型
建议把 58 个 spec 的推进拆成 5 层。
L0:术语与契约收口层
这是所有并行工作的前置层,不是大量写代码,而是先把语言统一。
包含:
- 图定义、图版本、图实例、节点执行记录、边跳转记录等术语
- 状态映射
- 输入输出契约命名
- replay / audit / session / mission 的挂接关系
主要依赖:
web-aigc-platform-domain-model
并发建议:
- 低并发
1 - 2条工作流即可
L1:平台骨架层
这是第一批可以并行但不能失控并行的层。
包含:
web-aigc-platform-domain-modelweb-aigc-platform-runtime-engineweb-aigc-platform-mission-projectionweb-aigc-platform-session-instanceweb-aigc-platform-observability-auditweb-aigc-platform-security-governance
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 · 650 lines · 5,330 tokens per session scan A 8d6d0536a218
WhyBuddy web-aigc-spec-execution-matrix.md is an instructions file published in the GitHub repository xiaojilele-glitch/WhyBuddy (380 stars, last pushed 1mo ago), licensed MIT. It adds 5,330 tokens to every session, about $0.0213 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 81% identical to WhyBuddy current-state.md, differing in 985 lines, and is treated as a copy.
WhyBuddy web-aigc-spec-execution-matrix.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| WhyBuddy web-aigc-spec-execution-matrix.mdxiaojilele-glitch/WhyBuddy | Instructions file | 380 | 1mo ago | MIT | A | 5,330 | Kiro |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |