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-parallel-execution-master-plan.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-parallel-execution-master-plan)<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/web-aigc-parallel-execution-master-plan"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/web-aigc-parallel-execution-master-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.
<a href="https://agentmods.dev/instructions/xiaojilele-glitch/whybuddy/web-aigc-parallel-execution-master-plan"><img src="https://agentmods.dev/badge/instructions/xiaojilele-glitch/whybuddy/web-aigc-parallel-execution-master-plan.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 | $0.05815 | $0.05815 |
| Opus 5.5 | $0.02326 | $0.02326 |
| Sonnet 5.5 | $0.01163 | $0.01163 |
| Haiku 4.5 | $0.00581 | $0.00581 |
Grade A, and why
WhyBuddy web-aigc-parallel-execution-master-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.
This is a copy
92% identical to WhyBuddy current-state.md — 1,038 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 — 703 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web-AIGC 58 Spec 并行执行总计划
文档目标
本文用于把当前保留的 58 个 web-aigc 迁移 spec,组织成一套可以真正并行推进的执行方案。
目标不是把 58 个 spec 同时散开乱做,而是:
- 尽可能提高并行度
- 尽量避免共享文件冲突
- 让多 Agent / 多工作流 / 多 worktree 可以稳定推进
- 让
sliderule在迁移过程中持续保持可集成、可回归、可收口
范围
当前范围固定为:
6个平台级 spec52个节点级 spec
总计 58 个 spec 目录,每个目录包含:
requirements.mddesign.mdtasks.md
一页结论
结论先说清楚:
- 这
58个 spec 可以并行做。 - 但不能按
58个单点同时编码。 - 正确方式是“平台先收口一轮,节点按能力簇并行,最后集中联调与治理补齐”。
- 对于一台
20核、32G内存的机器,推荐:- 文档 / 设计阶段并发:
10 - 12个 Agent - 骨架编码阶段并发:
8 - 10个 Agent - 集成联调阶段并发:
3 - 4个 Agent
- 文档 / 设计阶段并发:
- 夜间自动推进时,最理想的组织方式是:
1个主控 Agent3个平台 Agent6个节点能力簇 Agent1个集成 / 回归 Agent
换句话说:
- 不是
58个 Agent 一起冲 - 而是
10 - 11个有边界的 Agent 并行推进
基本判断
真实结构不是 58 个“节点”
当前保留集合其实是:
52个节点 spec6个平台 spec
所以执行时必须区分:
- 平台骨架
- 节点能力
- 高风险动作
- 最终集成与治理
扩展性来自统一执行骨架,而不是 spec 数量
真正的扩展性来自以下 6 个统一点:
- 统一领域模型
- 统一节点输入输出契约
- 统一图运行时状态机
- 统一实例 / 会话 / 任务投影
- 统一 replay / audit / lineage
- 统一 permissions / security gate
如果这些不先收口,哪怕并行写了很多节点,也只会形成一堆局部实现。
当前代码层高冲突区域
以下文件或模块属于并行期的共享热点,必须严格控制 ownership:
shared/workflow-runtime.tsshared/workflow-kernel.tsshared/workflow-input.tsshared/mission/contracts.tsshared/audit/contracts.tsshared/permission/contracts.tsserver/core/workflow-engine.tsserver/core/mission-orchestrator.tsserver/routes/workflows.tsserver/routes/tasks.tsserver/routes/replay.tsserver/routes/audit.tsserver/routes/permissions.tsserver/routes/lineage.tsserver/routes/rag.tsserver/routes/knowledge.tsserver/routes/voice.tsserver/routes/vision.tsserver/routes/a2a.ts
执行原则:
- 上述文件必须单写者优先,不允许多个 Agent 同时直接改同一热点文件。
- 节点适配优先向外围新增模块扩展,尽量减少反复改内核。
- 所有共享契约改动先经过平台主干收口,再放给节点 Agent 跟进。
推荐总并发度
按当前机器配置和仓库体量,推荐如下:
| 阶段 | 推荐并发 | 说明 |
|---|---|---|
| 文档归一 | 10-12 Agent | CPU 压力低,可高并发 |
| 接口与契约设计 | 6-8 Agent | 开始有共享定义,需主控收口 |
| 骨架编码 | 8-10 Agent | 并发高但必须分 ownership |
| 联调集成 | 3-4 Agent | 需要顺序收敛 |
| 回归 / 收尾 | 2-3 Agent | 统一补测试和治理 |
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 · 703 lines · 5,815 tokens per session scan A 0ee3757112b8
WhyBuddy web-aigc-parallel-execution-master-plan.md is an instructions file published in the GitHub repository xiaojilele-glitch/WhyBuddy (380 stars, last pushed 1mo ago), licensed MIT. It adds 5,815 tokens to every session, about $0.0233 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to WhyBuddy current-state.md, differing in 1,038 lines, and is treated as a copy.
WhyBuddy web-aigc-parallel-execution-master-plan.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| WhyBuddy web-aigc-parallel-execution-master-plan.mdxiaojilele-glitch/WhyBuddy | Instructions file | 380 | 1mo ago | MIT | A | 5,815 | 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 |