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/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_s4_flowchart)<a href="https://agentmods.dev/rules/silenceinsect/aidocxworkflow/stage_s4_flowchart"><img src="https://agentmods.dev/badge/rules/silenceinsect/aidocxworkflow/stage_s4_flowchart/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/rules/silenceinsect/aidocxworkflow/stage_s4_flowchart"><img src="https://agentmods.dev/badge/rules/silenceinsect/aidocxworkflow/stage_s4_flowchart.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 | $0.00021 | $0.06074 |
| Opus 5.5 | $0.00008 | $0.02430 |
| Sonnet 5.5 | $0.00004 | $0.01215 |
| Haiku 4.5 | $0.00002 | $0.00607 |
Grade A, and why
STAGE_S4_FLOWCHART 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 — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIDocxWorkFlow S4 — 流程图导出
独立阶段：可以单独调用。上游材料（S2 backlog + S3 prototype）审查合格后开始，失败写失败报告。
⚠️ 模块定义见
.cursor/MODULES.md（项目级唯一真相源）。 本文件不重写 8 模块表。
阶段入口
触发方式：/aidocx-s4-flowchart 或粘贴 S2 backlog + S3 prototype
前置材料（必须全部满足）：
| 材料 | 来源 | 审查要求 | 缺失时 |
|---|---|---|---|
| S2 backlog.md | workflow_assets/<req_name>/<version>/「S2 需求拆解」/backlog.md |
存在且含 Epic/Story | 写 fail_report_S4.md 停止 |
| S2 backlog.json | 同上目录 | summary.epic_count ≥ 1 + 每 Epic ≥ 1 Story + epic.module 从 8 模块取值 |
写 fail_report_S4.md 停止 |
| S1.5 exit_permission.json | workflow_assets/<req_name>/<version>/「S1 需求评审」/exit_permission.json |
can_proceed_to_s2 == true（防御性核查） |
警告，不阻断 |
| S3 prototype.md（必须读取） | workflow_assets/<req_name>/<version>/「S3 原型导出」/prototype.md |
存在则消费 PAGE-XXX 节点 |
警告，不阻断 |
材料缺失时：生成失败报告，停止 S4。
§1.4 LLM 必读材料（阶段前置）
生成流程图前，必须先读取以下全部材料。禁止凭印象直接生成。
| # | 材料 | 路径 | 读取原因 |
|---|---|---|---|
| 1 | 8 模块总表 | .cursor/MODULES.md（§1 总表） |
Epic 的模块前缀决定该 Epic 的主测试域 |
| 2 | 模块边界区分 | .cursor/MODULES.md（§4 各模块 O_boundary.md） |
异常决策树的叶子节点归属模块；防止把 BIZ 异常归成 UI |
| 3 | S2 backlog | workflow_assets/<req_name>/<version>/「S2 需求拆解」/backlog.md |
Story/OBJ 是流程图生成的核心输入 |
| 4 | S3 prototype | workflow_assets/<req_name>/<version>/「S3 原型导出」/prototype.md |
页面原型是流程节点的来源；S4 是 S5 EXCEPTION 类型 TP 的核心输入 |
核心任务（4 类产出，缺一不可）
为每个 Epic 生成：
- Mermaid 业务流程图（Flowchart）— 主流程
- Mermaid 时序图（Sequence Diagram）— 关键系统调用链路
- 异常/错误决策树（Flowchart / 文本）— 异常路径 + 回滚
- 风险点清单（表格 + s4_reference 唯一 ID）— S7 100% 覆盖率硬约束来源
4 类可机检 ID
S7 审查员 B 强依赖 S4 的可机检 ID——风险点 100% 覆盖率、异常树叶子节点覆盖率。
| 编号格式 | 含义 | 命名规范 | 示例 |
|---|---|---|---|
R-{NNN} |
风险点 ID（全局顺序） | 3 位 0 填充，按 Epic 顺序 + 风险发现顺序 | R-001 / R-018 |
R-{EpicID}-{NN} |
风险点按 Epic 局部 ID | Epic ID + 2 位 0 填充 | R-BIZ-PURCHASE-01 |
S4-{EpicID}-{seq}.{N} |
异常树叶子节点 | Epic ID + 异常分支顺序 | S4-BIZ-PURCHASE-1.3.2 |
S4-{EpicID}-F{N} |
流程图分支节点 | Epic ID + 流程节点顺序 | S4-BIZ-PURCHASE-F03 |
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 · 417 lines · 21 tokens per session scan A b2a660936a7e
STAGE_S4_FLOWCHART is a cursor rule published in the GitHub repository SilenceInsect/AIDocxWorkFlow (2 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 6,074 once invoked, about $0.0001 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 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).