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_s7_reviewgit 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_s7_review)<a href="https://agentmods.dev/rules/silenceinsect/aidocxworkflow/stage_s7_review"><img src="https://agentmods.dev/badge/rules/silenceinsect/aidocxworkflow/stage_s7_review.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 | $0.00019 | $0.07117 |
| Opus 5 | $0.00010 | $0.03558 |
| Sonnet 5 | $0.00004 | $0.01423 |
| Haiku 4.5 | $0.00002 | $0.00712 |
Grade A, and why
STAGE_S7_REVIEW 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 4d 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 — 549 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIDocxWorkFlow S7 — 用例审查
独立阶段：可以单独调用。上游材料（S6 test_cases.json + coverage/omission 账本）审查合格后开始，失败写失败报告。
阶段入口
触发方式：/aidocx-s7-review 或粘贴 S6 test_cases.json
前置材料（必须全部满足）：
| 材料 | 来源 | 审查要求 |
|---|---|---|
| S6 test_cases.json | workflow_assets/<req_name>/<version>/「S6 测试用例生成」/test_cases.json |
存在且用例数量 > 0 |
| S5 test_points.json（必须读取） | workflow_assets/<req_name>/<version>/「S5 测试点生成」/test_points.json |
存在则用于覆盖率计算 |
| S4 business_flow.md（必须读取） | workflow_assets/<req_name>/<version>/「S4 流程图导出」/business_flow.md |
用于 S4 风险点覆盖率计算 |
| coverage_ledger.json | workflow_assets/<req_name>/<version>/「S6 测试用例生成」/coverage_ledger.json |
覆盖缺口事实源 |
| omission_ledger.json | workflow_assets/<req_name>/<version>/「S6 测试用例生成」/omission_ledger.json |
豁免/人工复核事实源 |
前置材料缺失时：生成失败报告，停止 S7。
§1.4 LLM 必读材料（阶段前置）
审查前，必须先读取以下全部材料。禁止凭印象直接生成审查报告。
| # | 材料 | 路径 | 读取原因 |
|---|---|---|---|
| 1 | 8 模块总表 | .cursor/MODULES.md（§1 总表） |
覆盖率按模块统计；审查员 B 的 module_coverage 以 8 模块为分母 |
| 2 | 模块边界区分 | .cursor/MODULES.md（§4 各模块 O_boundary.md） |
判断 TP 模块归属是否正确；HINT vs UI 是最高误标区 |
| 3 | S6 test_cases | workflow_assets/<req_name>/<version>/「S6 测试用例生成」/test_cases.json |
审查对象 |
| 4 | S5 test_points（必须读取） | workflow_assets/<req_name>/<version>/「S5 测试点生成」/test_points.json |
S4 风险点覆盖率对比基准 |
| 5 | S4 business_flow（必须读取） | workflow_assets/<req_name>/<version>/「S4 流程图导出」/business_flow.md |
S4 风险点全量覆盖（100%）是硬约束，不是拍脑袋 |
核心原则
🚨 强制阅读指令（MANDATORY）：S7 阶段采用账本驱动模式——脚本只输出事实数字，LLM 按业务实际写建议。
- 全阶段质量门禁 SSOT：
DESIGN_AND_EXECUTION_STANDARDS.mdc§2.3（仅作全阶段速查，S7 当前实际门禁见本节）- 执行 S7 前必须读本节 +
aidocx-s7-review/SKILL.md§3（审查员分工）。- 变更历史见
CHANGELOG.md。
S7 质量门禁：无硬阈值
S7 阶段不设硬指标（不强制"覆盖率=100% = PASS"），但必须消费 coverage/omission 账本。 脚本只输出事实数字，LLM 按业务实际写建议。 真实业务有取舍，LLM 审查员按业务实际给出判断。
禁止出现的行为：
- ❌ 用脚本覆盖率数字直接判定 PASS / FAIL
- ❌ 设置"覆盖率 ≥85% = 通过"之类的硬阈值
- ❌ 用覆盖率数字替代 LLM 的语义审查
- ❌ 在报告结构中保留"整体判决：PASS / FAIL"行
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.
- 4d ago First seen · 549 lines · 19 tokens per session scan A 41d919870d92
STAGE_S7_REVIEW is a cursor rule published in the GitHub repository SilenceInsect/AIDocxWorkFlow (2 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 7,117 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 2026-08-31.
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.