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/design_and_execution_standardsgit 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/design_and_execution_standards)<a href="https://agentmods.dev/rules/silenceinsect/aidocxworkflow/design_and_execution_standards"><img src="https://agentmods.dev/badge/rules/silenceinsect/aidocxworkflow/design_and_execution_standards.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 | $0.13646 | $0.13646 |
| Opus 5 | $0.06823 | $0.06823 |
| Sonnet 5 | $0.02729 | $0.02729 |
| Haiku 4.5 | $0.01365 | $0.01365 |
Grade A, and why
DESIGN_AND_EXECUTION_STANDARDS 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 — 898 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIDocxWorkFlow 全局执行约束与跨阶段决策
适用对象：所有阶段 模块定义：
.cursor/MODULES.md（项目级唯一真相源） 各阶段规范：.cursor/rules/STAGE_S*.mdc（阶段完整定义，含必读材料 + push 块 + 质量门禁） 各阶段技能：.cursor/skills/aidocx-*/SKILL.md（阶段执行入口）
维护规范
| 职责 | 文件 |
|---|---|
| 模块定义/边界/枚举/种子 TP / O_boundary | .cursor/MODULES.md + knowledge/public/module_templates/<MODULE>/ |
| 阶段规范/必读材料/push 块/质量门禁/产出格式 | .cursor/rules/STAGE_S*.mdc |
| 技能操作/执行入口/必读材料清单/push 块 | .cursor/skills/aidocx-*/SKILL.md |
| 本文件 | 跨阶段判决/跨模块规则/is_assumed/全局违规认定 |
0.1 版本控制分层原则
本节是项目级 Git 资产分类的 SSOT——每类资产列具体路径 + 对应
.gitignore行号 + 强制验证命令。仅写抽象名词（"过程资产""项目级知识库"）的条款作废，必须可机械对照。
0.1.1 资产分类表（路径 + .gitignore 模式锚点）
锚点选择：本表用
.gitignore模式文本（如*.jsonl/knowledge/project_local//feedback_logs/）作为锚点，不用行号——
- 行号会随
.gitignore任意编辑漂移，今天第 91 行明天可能第 95 行- 模式文本是
.gitignore文件本身的语义内容，人本可审查：肉眼 grep 一行即可对照- 自动化验证用
git check-ignore -v（输出.gitignore:N:<模式> <路径>），行号只是机器附带输出本表同步铁律：改
.gitignore后必须重跑grep -nF "<模式>" .gitignore验证锚点仍在；若改模式文本，本表同步改；若删模式，删表行。
| 资产类别 | 具体路径 | Git 归属 | .gitignore 模式锚点 |
验证命令 |
|---|---|---|---|---|
| 功能代码 | ai_workflow/*.py（非 pycache） |
入 | 无显式模式（依赖默认） | git check-ignore ai_workflow/test.py → NOT IGNORED |
| 测试代码 | tests/*.py |
入 | 无显式模式 | 同上 |
| 规则治理资产 | .cursor/rules/*.mdc / .cursor/skills/*/SKILL.md / .cursor/MODULES.md / .cursor/hooks/*.py |
入 | 无显式模式 | 同上 |
| 公共知识库 | knowledge/public/**（仅 .json / .md 等非录制类） |
入 | 无显式模式（依赖默认 + *.jsonl 反向排除） |
git check-ignore knowledge/public/test_point_library/tp_library.db → NOT IGNORED |
| 过程录制 jsonl | 所有 *.jsonl 文件——包括 feedback_logs/*.jsonl / workflow_assets/**/*.jsonl / knowledge/project_local/**/*.jsonl |
不入 | *.jsonl |
git check-ignore -v knowledge/public/goal_loop/x.jsonl → .gitignore:N:*.jsonl ...（即使在 public/ 下也命中） |
| 项目级知识库 | knowledge/project_local/** |
不入 | knowledge/project_local/ |
git check-ignore -v knowledge/project_local/foo.md → .gitignore:N:knowledge/project_local/ ... |
| 本地输入材料 | resource/<req_name>/** |
不入 | resource/ |
git check-ignore -v resource/foo.md → .gitignore:N:resource/ ... |
| 单次需求过程资产 | workflow_assets/<req_name>/<version>/「S*」/** |
不入 | workflow_assets/* |
git check-ignore -v workflow_assets/foo/v1.0/test.md → .gitignore:N:workflow_assets/* ... |
| 阶段上下文包 | workflow_assets/**/stage_context.md / stage_context.json / read_ack.json |
不入 | workflow_assets/**/*.stage_context.md / workflow_assets/**/stage_context.json / workflow_assets/**/read_ack.json |
git check-ignore -v workflow_assets/foo/v1.0/「S5」/stage_context.md → .gitignore:N:workflow_assets/**/stage_context.md ... |
| 运行反馈日志 | feedback_logs/** + *.log |
不入 | feedback_logs/ + *.log |
git check-ignore -v feedback_logs/foo.log → .gitignore:N:feedback_logs/ ... |
| 治理档 | governance/**（方案/INDEX/归档） |
不入 | governance/ |
git check-ignore -v governance/foo.md → .gitignore:N:governance/ ... |
| CHANGELOG | CHANGELOG.md（本地迭代历史） |
不入 | CHANGELOG.md |
git check-ignore -v CHANGELOG.md → .gitignore:N:CHANGELOG.md ... |
| Goal loop 过程资产 | .goal-log-db/ + workflow_assets/goals/ |
不入 | .goal-log-db/ + workflow_assets/goals/ |
git check-ignore -v .goal-log-db/foo.db → .gitignore:N:.goal-log-db/ ... |
| 本地 secrets / 配置 | .env / .env.local / secrets.json / .cursor/private/ |
不入 | .env / .env.local / secrets.json / .cursor/private/ |
git check-ignore -v .env → .gitignore:N:.env ... |
| 构建/缓存产物 | __pycache__/ / *.pyc / .pytest_cache/ / dist/ / build/ 等 |
不入 | __pycache__/ / *.pyc / *.egg-info/ / .pytest_cache/ 等 |
git check-ignore -v ai_workflow/__pycache__/x.cpython-39.pyc → .gitignore:N:__pycache__/ ... |
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 · 898 lines · 13,646 tokens per session scan A bc4067348ddb
DESIGN_AND_EXECUTION_STANDARDS is a cursor rule published in the GitHub repository SilenceInsect/AIDocxWorkFlow (2 stars, last pushed 1mo ago), licensed MIT. It adds 13,646 tokens to every session, about $0.0682 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.