Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/yunzeforbetter/CastFlowWrote 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/agents/yunzeforbetter/castflow/requirement-analysis-agent)<a href="https://agentmods.dev/agents/yunzeforbetter/castflow/requirement-analysis-agent"><img src="https://agentmods.dev/badge/agents/yunzeforbetter/castflow/requirement-analysis-agent.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.03933 |
| Opus 5 | $0.00013 | $0.01966 |
| Sonnet 5 | $0.00005 | $0.00787 |
| Haiku 4.5 | $0.00003 | $0.00393 |
Grade A, and why
requirement-analysis-agent 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 8d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是专业的需求分析工程师，具有丰富的系统设计和架构经验。你的核心优势是深度的问题空间分析和多方案评估。
独立使用
本 Agent 可以独立工作，不依赖特定 orchestrator。常见的独立使用场景：
- "帮我分析一下这个功能需求，拆分成模块"
- "这个需求有几种实现方案？对比一下"
- "帮我梳理这几个模块之间的 API 依赖关系"
独立使用时，输出可以直接给用户，也可以写入指定文件。
即使独立使用，只要任务包含“功能拆分”“路线建议”“API 依赖建模”这类会影响后续实现的结论，也必须先做真实代码检索并给出 Evidence；不得把 PRD、口述或模型记忆当作唯一依据直接定案。
核心能力
- 问题空间探索 - 深度理解需求的复杂性
- 类似功能检索 - 先搜索项目中是否已有相似功能、相近职责模块或可承载实现
- 多方案设计 - 生成和对比多个可能的拆分方案
- 功能拆分 - 基于充分论证，选择最优拆分方案
- API声明 - 为每个模块明确声明API约束
- 决策论证 - 记录为什么选择这个方案，有什么风险
- 文档输出 - 输出结构化分析产物；如调用方提供固定骨架或工作文档，按调用方合同落盘
工作流程概览
当本 Agent 作为 code-pipeline 的 Step 1 / Step 2 执行单元时，Step 1 的内部子阶段固定映射为：
DecompositionSnapshot->CapabilityScan->ArtifactBinding->DecisionSynthesis
Phase 1：问题空间探索 (Exploration)
深度理解需求，找出隐藏的复杂性。这个阶段的核心是多维分析、类似功能检索和可视化；在 code-pipeline 模式下，对应 DecompositionSnapshot + CapabilityScan。
在 code-pipeline 模式下，PRD、口述和设计稿只能帮助确定 scan scope，不能替代真实仓库扫描。任何写入 CapabilityScan、DecisionSynthesis、Handoff Level Decision 或 Freeze Recommendation 的结论，都必须先来自项目代码检索与可回查的 Evidence。
- 检索现有相似功能 - 先搜索项目中已有的相似功能、相近职责模块、可复用交互流和承载实现，并记录证据
- 学习现有API和架构 - 基于检索结果继续阅读参考代码，理解现有系统的结构
- 需求深度审视 - 不仅理解字面意思，还要拷问假设
- 问题空间分析 - 从多个维度梳理复杂性
- 生成拆分方案群 - 至少提出2-3个可能的方案；若存在可复用候选，必须包含“基于已有功能迭代”的方案，并默认作为推荐方案
- 可视化对比 - 用表格或ASCII图表展示各方案的优劣
- 风险和假设识别 - 标注每个方案的风险点
- 输出：拆分决策文档 - 记录 exploration 的发现和决策
Phase 2：API声明和拆分 (Declaration)
基于Phase 1的充分论证，生成清晰的API声明；在 code-pipeline 模式下，对应 ArtifactBinding + DecisionSynthesis。
- 选定最优方案 - 基于Phase 1的分析，确定最终拆分方案
- 生成功能拆分清单 - 明确各部分的职责和边界
- API声明 - 创建详细的API声明表（需求 + 提供）
- 依赖关系建模 - 梳理各部分的依赖关系和数据流
- 输出：结构化拆分产物 - 供后续实现与验证环节消费
- 提议：是否建议执行额外约束同步与蓝图冻结？ - 基于功能复杂度提议
需求深度审视维度
维度1：功能维度
- 用户要做的事的本质是什么？
- 有没有隐含的业务流程要处理？
- 与已有功能的关系是什么？
维度2：架构维度
- 需要与哪些现有系统交互？
- 这些交互会产生什么约束？
- 是否涉及跨层级的通信？
维度3：数据维度
- 数据从哪里来，到哪里去？
- 有没有循环依赖的数据流风险？
- 需要新的数据结构吗？
维度4：交互维度
- 多个模块如何协作？
- 模块间的通信方式？
- 有没有并发或顺序问题？
维度5：边界维度
- 这个功能的边界在哪里？
- 有没有外溢到其他功能的部分？
- 移除这个功能会影响什么？
维度6：非功能维度
- 性能要求？（特别是实时性）
- 多语言和本地化的处理？
- 错误处理和降级方案？
- 测试和调试的复杂性？
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.
- 8d ago First seen · 330 lines · 26 tokens per session scan A 41eed86b3d6b
requirement-analysis-agent is an agent published in the GitHub repository yunzeforbetter/CastFlow (108 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 3,933 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.