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_s1_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_s1_review)<a href="https://agentmods.dev/rules/silenceinsect/aidocxworkflow/stage_s1_review"><img src="https://agentmods.dev/badge/rules/silenceinsect/aidocxworkflow/stage_s1_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 | $0.03513 |
| Opus 5 | $0.00010 | $0.01757 |
| Sonnet 5 | $0.00004 | $0.00703 |
| Haiku 4.5 | $0.00002 | $0.00351 |
Grade A, and why
STAGE_S1_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 — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIDocxWorkFlow S1 — 需求评审
独立阶段：可以单独调用。丢入材料 → 审查材料 → 合格后开始评审产出，失败写失败报告。
阶段入口
三阶段边界 SSOT：见
.cursor/rules/STAGE_S1_REVIEW.mdc§阶段入口。
触发方式：/aidocx-s1-review + 需求文件（.docx / .md / .txt），不接受纯文本粘贴
触发方式：/aidocx-s1-review + 需求文件（.docx / .md / .txt），不接受纯文本粘贴
输入材料：
- 原始需求文件（.docx / .md / .txt）
- .docx 由
ai_workflow/stage_s1_input/run_s1_pipeline()自动转 md + 图片归档 + OCR，产物落raw/ - 无文件 / 不可解析 / 解析后正文 < 50 字 → 物料门禁失败，生成
fail_report_S1.md停止
物料门禁（前置条件，阻断）
| 检查项 | 要求 | 缺失时 |
|---|---|---|
| 需求文件 | 文件路径 / 附件存在 | 直接生成 fail_report_S1.md，不进评审 |
| 文档可解析 | .docx / .md / .txt 解析成功 |
同上 |
| 正文非空 | 解析后正文 ≥ 50 字 | 同上 |
核心任务
对需求文档进行质量闭环评审，核心是验证强付费项的 3 段完整性。
强付费项质量闭环 3 段（核心硬性产出）
识别规则：AI 识别到需求含 PURCHASE_STRONG 任意 1 类子项（发奖/排行/订单/兑换/VIP/战令）→ 必须在需求文本中找到 3 段：
| 段 | 含义 | 示例 |
|---|---|---|
| 程序自测点 | 程序自行验证的入口（GM 命令 / 测试脚本 / 沙盒） | "GM 命令 gm_grant_award 1001 给玩家发奖 1001 id 的道具" |
| 测试覆盖 | 列出该功能需覆盖的测试场景 | "覆盖：发奖成功 / 邮件未领取状态 / 重复领取拦截 / 服务端权威校验" |
| 策划验收 | 策划验收的方式（数值表比对 / 案例回放 / 抽检比例） | "策划在测试环境用 GM 命令抽检 10 个玩家背包，对照数值表" |
缺失判定：
- 3 段齐全 → ✅ PASS
- 缺 1 段 → 1 条 P0（SPECIAL_FLAG =
PURCHASE_STRONG） - 缺 2 段 → 2 条 P0（SPECIAL_FLAG =
PURCHASE_STRONG） - 缺 3 段 → 3 条 P0（SPECIAL_FLAG =
PURCHASE_STRONG）
S1.5 门禁：
SPECIAL_FLAG = PURCHASE_STRONG的 P0 必须全部答完才能can_proceed_to_s2 = true
PURCHASE_STRONG 6 类子项
| 子项 | 典型功能点 |
|---|---|
| 发奖 | 邮件 / 背包 / 资产生成 / 补发 / 补偿 |
| 排行 | 个人榜 / 团队榜 / 赛季榜 / 服务端权威榜 |
| 订单 | 充值 / 退款 / 对账 / 发票 / 风控拦截 |
| 兑换 | 商店 / 兑换码 / 补款 / 限时礼包 |
| VIP | VIP 等级 / 月卡 / 季卡 / 永久卡 / 状态机失效 |
| 战令 | 多档位发奖 / 经验计算 / 等级解锁 |
新评审维度（替代旧的 5 维度评分）
| 维度 | 权重 | 评审要点 |
|---|---|---|
| 质量闭环完整性 | 30% | 强付费项 3 段（程序自测点/测试覆盖/策划验收）是否完整 |
| 功能覆盖度 | 25% | 每个功能 F 是否都有对应的测试场景 |
| 可测试性 | 25% | 是否有 GM 命令/测试脚本/测试数据支撑 |
| 一致性 | 20% | 角色 / 功能 / 验收标准三层之间无矛盾 |
判决规则
| 总分 | 判决 | 后续动作 |
|---|---|---|
| ≥ 7.0 | PASS | 生成终版需求.md → 触发 S1.5 业务澄清 → 等待人工 feedback |
| 4.0 – 6.9 | NEEDS_REVISION | 输出修改建议，等待修订后重审 |
| < 4.0 | REJECT | 触发三步自问；若 Q1/Q2 回答"存在"或"有" → 回 LLM 迭代补充；若 Q1="不存在"+Q2="无"+Q3="不影响" → 允许放行，备案到 bypass_log.json |
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 · 345 lines · 19 tokens per session scan A 799dfdcce269
STAGE_S1_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 3,513 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.