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_s8_self_iterationgit 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_s8_self_iteration)<a href="https://agentmods.dev/rules/silenceinsect/aidocxworkflow/stage_s8_self_iteration"><img src="https://agentmods.dev/badge/rules/silenceinsect/aidocxworkflow/stage_s8_self_iteration.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 | $0.05353 |
| Opus 5 | $0.00010 | $0.02677 |
| Sonnet 5 | $0.00004 | $0.01071 |
| Haiku 4.5 | $0.00002 | $0.00535 |
Grade A, and why
STAGE_S8_SELF_ITERATION 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 — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIDocxWorkFlow S8 — 自迭代
独立阶段：可以单独调用。上游材料（S7 review_report.json / review_snapshot.json）审查合格后开始，失败写失败报告。
阶段入口
触发方式：/aidocx-s8-self-iteration 或粘贴 S7 审查报告
前置材料（必须全部满足）：
| 材料 | 来源 | 审查要求 |
|---|---|---|
| S7 审查报告 | workflow_assets/<req_name>/<version>/「S6 测试用例生成」/review_report.json |
必须存在 |
| S5 test_points.json（必须读取） | workflow_assets/<req_name>/<version>/「S5 测试点生成」/test_points.json |
用于 S4 覆盖率分析 |
| S6 test_cases.json | workflow_assets/<req_name>/<version>/「S6 测试用例生成」/test_cases.json |
用于 S6 层缺陷追溯 |
| S4 business_flow.md（必须读取） | workflow_assets/<req_name>/<version>/「S4 流程图导出」/business_flow.md |
用于风险点提取 |
| 执行反馈日志（可选） | workflow_assets/feedback_logs/ |
存在则作为深度分析数据 |
前置材料缺失时：生成失败报告，停止 S8。
§1.4 LLM 必读材料（阶段前置）
开始根因分析前，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） |
缺陷根因最终落到模块 × 类型的组合；缺陷模式按模块统计 |
| 2 | 模块边界区分 | .cursor/MODULES.md（§4 各模块 O_boundary.md） |
判断 S5 TP 模块归属是否正确；根因分析的起点 |
| 3 | S7 review_report（必须读取） | workflow_assets/<req_name>/<version>/「S6 测试用例生成」/review_report.json |
所有审查结论的来源；按 reviewer_a / reviewer_b / recommendations 结构追溯 |
| 4 | S5 test_points（必须读取） | workflow_assets/<req_name>/<version>/「S5 测试点生成」/test_points.json |
S5 层缺陷追溯的起点 |
| 5 | S4 business_flow（必须读取） | workflow_assets/<req_name>/<version>/「S4 流程图导出」/business_flow.md |
异常决策树和风险点清单是 S5 缺 TP 的根因来源 |
| 6 | S6 test_cases | workflow_assets/<req_name>/<version>/「S6 测试用例生成」/test_cases.json |
S6 层缺陷追溯的参考 |
核心原则
🚨 强制阅读指令（MANDATORY）：S8 阶段输出判定（不输出建议）——以「风险点覆盖」为核心指标，从 S4→S5→S6→S7 链路推理根因。
- 全阶段质量门禁 SSOT：
DESIGN_AND_EXECUTION_STANDARDS.mdc§2.3（仅作全阶段速查，S8 当前实际门禁见本节）- 执行 S8 前必须读本节 +
aidocx-s8-self-iteration/SKILL.md。- 变更历史见
CHANGELOG.md。
S8 的核心使命：从 S4 → S5 → S6 → S7 链路推理根因，以「风险点覆盖」为核心指标，产出缺陷模式分析和 Prompt 改进建议，并将经验归档到知识库。
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 · 417 lines · 19 tokens per session scan A 471dae6586f6
STAGE_S8_SELF_ITERATION 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 5,353 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.