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_s1.5-clarificationgit 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_s1.5-clarification)<a href="https://agentmods.dev/rules/silenceinsect/aidocxworkflow/stage_s1.5-clarification"><img src="https://agentmods.dev/badge/rules/silenceinsect/aidocxworkflow/stage_s1.5-clarification.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 | $0.00026 | $0.02623 |
| Opus 5 | $0.00013 | $0.01311 |
| Sonnet 5 | $0.00005 | $0.00525 |
| Haiku 4.5 | $0.00003 | $0.00262 |
Grade A, and why
STAGE_S1.5 Clarification 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 5d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIDocxWorkFlow Stage 1.5 — 需求澄清与准出
独立子阶段：S1 评审通过后、S2 需求拆解前执行。 S1.5 不可被缺省——S2 执行前必须有
exit_permission.json且can_proceed_to_s2 == true。 详见STAGE_S2_BREAKDOWN.mdc前置材料门禁。
阶段定位
S1 需求评审（AI：发现问题）
↓ S1 产出 clarification_checklist.md（含 P0/P1/P2 未闭环问题）
S1.5 需求澄清（人工：给出决策）
↓ S1.5 产出 exit_permission.json（含 can_proceed_to_s2 判定）
S2 需求拆解（AI：执行拆解）
三阶段 SSOT：各阶段边界在 rule 文件中具体定义：
- S1：
.cursor/rules/STAGE_S1_REVIEW.mdc§阶段入口 - S1.5：
.cursor/rules/STAGE_S1.5 Clarification.mdc§阶段定位 - S2：
.cursor/rules/STAGE_S2_BREAKDOWN.mdc§阶段入口
S1.5 本质：人工决策阶段——S1 评审结论中未闭环的问题（P0/P1/P2），由人工给出决策，AI 将决策落档并生成准出许可。
S1.5 不生产新知识，只归档人工决策。所有 AI 评审产出的文档（S1 的 gm_commands.md / test_coverage.md / planning_acceptance.md 等）不经过 S1.5，直接进入 S2。
阶段入口
触发：/aidocx-s1-5-clarification，或用户填写完 clarification_checklist.md 后告知 AI。
前置物料（S1 产出 = S1.5 输入）
S1.5 只验收 3 份 S1 产出。其余 S1 产出（gm_commands.md / test_coverage.md 等）直接进入 S2，不经过 S1.5。
交互原则：clarification_checklist 以人工填写为主；空白 / 占位内容由 LLM 补齐（标注 [LLM 推导]）。
| # | 物料 | 路径 | S1.5 用途 |
|---|---|---|---|
| 1 | clarification_checklist.md |
workflow_assets/<req_name>/<version>/「S1 需求评审」/ |
唯一验收对象：人工填写 P0/P1/P2 处理方案；LLM 补齐缺口 |
| 2 | 终版需求.md（草稿） |
workflow_assets/<req_name>/<version>/「S1 需求评审」/ |
S1.5 完善后的输出（S1.5 修改它） |
| 3 | review_report.md |
workflow_assets/<req_name>/<version>/「S1 需求评审」/ |
S1.5 参考，不验收（AI 产出） |
输入审查（门禁前置）
| 检查项 | 要求 | 缺失时 |
|---|---|---|
| clarification_checklist.md 存在 | 文件存在且 P0 项非空 | 提示用户先完成 S1 |
| P0 项已填写 | P0 100% 填写 | can_proceed_to_s2 = false，S2 阻塞 |
| 处理方案有效 | 处理方案不为空 / 不为占位文字 | 提示用户填写具体决策 |
强付费项闭环：S1 识别的强付费项 3 段（程序自测点/测试覆盖/策划验收）缺失，以 P0 项写入 clarification_checklist。S1.5 验收 P0（含强付费项 P0）即完成闭环。 S1.5 不再重复检查强付费项 3 段（S1 已检查，S1.5 只检查 P0 是否填完）。
核心职责
- 完善终版需求.md：基于人工填写的处理方案，补充缺失的业务规则
- 生成准出许可（exit_permission.json）：输出质量评价和准出判定，供 S2 读取
- 更新 clarification_checklist.md 状态：标记为已处理
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.
- 5d ago First seen · 226 lines · 26 tokens per session scan A 8feebeae8db5
STAGE_S1.5 Clarification is a cursor rule published in the GitHub repository SilenceInsect/AIDocxWorkFlow (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 2,623 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-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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.