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.
npx agentmods add rules/silenceinsect/aidocxworkflow/stage_s2_breakdowngit clone --depth 1 https://github.com/SilenceInsect/AIDocxWorkFlowWrote 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/rules/silenceinsect/aidocxworkflow/stage_s2_breakdown)<a href="https://agentmods.dev/rules/silenceinsect/aidocxworkflow/stage_s2_breakdown"><img src="https://agentmods.dev/badge/rules/silenceinsect/aidocxworkflow/stage_s2_breakdown.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 | $0.00036 | $0.11847 |
| Opus 5 | $0.00018 | $0.05923 |
| Sonnet 5 | $0.00007 | $0.02369 |
| Haiku 4.5 | $0.00004 | $0.01185 |
Grade A, and why
STAGE_S2_BREAKDOWN 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 3d 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 — 807 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIDocxWorkFlow S2 — 需求拆解
独立阶段:可以单独调用。上游材料(S1.5 准出许可)审查合格后开始,失败写失败报告。
本版本核心升级:拆解深度从「Epic/Story」一层扩展到完整的需求对象级分解,为 S3 迭代规划和 S5/S6 测试用例设计提供充足的执行物料。
阶段入口
三阶段边界 SSOT:见
.cursor/rules/STAGE_S2_BREAKDOWN.mdc§阶段入口。
触发方式:/aidocx-s2-breakdown 或粘贴 S1.5 准出许可路径
前置材料(必须全部满足):
| 材料 | 来源 | 审查要求 |
|---|---|---|
| 终版需求.md | workflow_assets/<req_name>/<version>/「S1 需求评审」/终版需求.md |
存在且内容完整 |
| S1.5 准出许可 | workflow_assets/<req_name>/<version>/「S1 需求评审」/exit_permission.json |
存在且 can_proceed_to_s2 == true |
| clarification_checklist.md | workflow_assets/<req_name>/<version>/「S1 需求评审」/clarification_checklist.md |
状态为「已处理」 |
材料缺失或 can_proceed_to_s2 == false 时:生成失败报告,停止 S2。
S2 产出矩阵(6 大核心产出,v18.2 新增)
v18.2 新增:基于《游戏测试-需求拆解阶段完整产出明细》对齐 S2 产出规范。 本阶段所有产出为测试必出基线文档,是用例编写、测试执行、提测验收、bug判定的唯一依据。
产出1:需求全景模块拆解图(功能结构拆分)
核心目的:将整块业务需求,拆解为独立、可单独测试的子模块,解决"整体懂、局部漏"的问题,适配游戏玩法、活动、功能、付费、社交等所有场景。
标准拆解层级(四级颗粒度):业务需求 → 一级模块 → 二级功能 → 最小测试单元
一级模块:
- 客户端表现、服务端逻辑、数值配置、埋点统计、合规风控、兼容适配
输出形式:backlog.md / backlog.json,标注每个子模块归属端(客户端/服务端/配置/后台)
产出2:测试覆盖范围&排除范围清单(边界界定)
核心目的:明确哪些必须测、哪些不测、哪些复用旧版本逻辑,杜绝后期范围扩散、无效返工。
必覆盖范围(逐条落地)
- 新增功能:本次迭代全新开发的所有功能、交互、数值、弹窗
- 变更功能:旧功能修改的逻辑、数值、UI、触发条件、跳转规则
- 关联影响:被本次迭代联动的旧模块(如活动修改联动背包、邮件、战力计算)
- 异常场景:所有边界、中断、容错、并发、网络/设备异常场景
- 配套能力:埋点、日志、GM指令、后台配置、数据上报
明确排除范围(白纸黑字归档)
- 本次无变更的旧版稳定逻辑
- 非本次迭代的关联系统底层逻辑
- 策划明确暂不上线、灰度关闭的功能
- 研发标注本次不改动的代码模块
复用范围
- 可复用旧用例的模块、无需重复编写用例的功能,直接标注复用编号
产出3:全场景测试点拆解明细表(核心产出,最小测试颗粒度)
核心目的:把"自然语言需求"翻译成"可校验的测试点",100%对齐判定标准,是后续用例编写的唯一来源,无遗漏、无歧义。
标准字段(每条测试点必填):模块归属、需求原文、拆解测试点、校验维度、预期结果、测试类型、优先级、依赖条件
拆解覆盖的 8 大测试维度(游戏专用):
-
正常流程测试点:所有正向主流程,覆盖从入口、操作、执行、结果、收尾全链路,确保核心玩法可用。
-
边界数值测试点:最大值、最小值、临界值、0值、满值、溢出值、扣除不足、累计上限、次数上限、时间阈值。
-
异常操作测试点:快速连点、重复提交、中途取消、多操作并发、频繁切换页面、未满足条件强行触发。
-
环境/设备异常测试点:断网、弱网、切换网络、后台挂起、锁屏、闪退重启、内存不足、系统弹窗打断、机型适配。
-
数据一致性测试点:客户端&服务端数据同步、本地缓存&后台配置一致、跨账号/跨设备数据同步、重启数据保留/重置规则。
-
并发/多人场景测试点:多人同时操作、同账号多端登录、批量领取/消耗、跨服交互、排行榜并发计算。
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.
- 3d ago First seen · 807 lines · 36 tokens per session scan A 2a9a43e52a12
STAGE_S2_BREAKDOWN is a cursor rule published in the GitHub repository SilenceInsect/AIDocxWorkFlow (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 11,847 once invoked, about $0.0002 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 2026-08-31.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.