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.
git 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/s1_workload_estimation)<a href="https://agentmods.dev/rules/silenceinsect/aidocxworkflow/s1_workload_estimation"><img src="https://agentmods.dev/badge/rules/silenceinsect/aidocxworkflow/s1_workload_estimation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/silenceinsect/aidocxworkflow/s1_workload_estimation"><img src="https://agentmods.dev/badge/rules/silenceinsect/aidocxworkflow/s1_workload_estimation.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.04721 | $0.04721 |
| Opus 5.5 | $0.01888 | $0.01888 |
| Sonnet 5.5 | $0.00944 | $0.00944 |
| Haiku 4.5 | $0.00472 | $0.00472 |
Grade A, and why
S1_WORKLOAD_ESTIMATION 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 1mo 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 — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
测试工作量排期预估单 — 方法论规范
适用范围：S1 需求评审阶段的"测试工作量排期预估单"产出规范 编号：S1-WE-001（Workload Estimation Method） 版本：v1.1 依据：基于资深测试评审标准 + AIDocxWorkFlow 8 模块体系
0. 输入来源（v18.1 新增）
v18.1 新增：明确本方法论的输入材料来源，支持从人工澄清目录读取。
可选输入来源：
| 来源 | 路径 | 说明 |
|---|---|---|
| 人工澄清 | resource/<req_name>/<version>_clarification.xlsx |
优先级最高，若存在则优先读取其中的工时相关说明 |
| 原始需求 | resource/<req_name>/<version>_raw.<ext> |
核心输入，基于需求内容评估工时 |
流程：S1 执行时优先从
resource/<req_name>/<version>_clarification.xlsx读取人工澄清内容（如有）。若无人工澄清文件，直接基于原始需求文档评估。
1. 核心概念
1.1 什么是测试工作量排期预估单
对需求文档拆解测试范围后，精准评估工时产出的文档，包含：
- 模块拆分 — 按业务域/系统划分测试范围
- 工时评估 — 各类测试类型的工时估算
- 风险缓冲 — 预留的缓冲时间
- 阻塞项标注 — 前置依赖导致的无法提前介入项
- 交付里程碑 — 时间节点与准入标准
1.2 与其他产出的关系
| 产出 | 关系 |
|---|---|
review_issues.md |
记录需求问题，本文档基于已澄清的需求评估工时 |
edge_cases.md |
边界异常场景清单，影响工时估算的复杂度系数 |
entry_criteria.md |
提测准入标准，影响里程碑的"准入条件" |
workload_estimation.md |
本文档，产出工时与里程碑 |
2. 模块拆分规则
2.1 标准模块分类
基于 AIDocxWorkFlow 8 模块体系 + 游戏行业通用分类
| 模块分类 | 说明 | 对应 AIDocxWorkFlow 模块 |
|---|---|---|
| 主线玩法 | 核心游戏循环、主线任务、主线副本 | BIZ + SPECIAL |
| 活动系统 | 限时活动、节日活动、运营活动 | BIZ + LINK |
| 充值付费 | 支付流程、订单、对账、退款 | BIZ + LINK（第三方） |
| 社交系统 | 好友、公会、聊天、组队 | BIZ + LINK |
| 背包系统 | 道具存取、仓库、整理 | BIZ + SPECIAL |
| 战斗系统 | 战斗逻辑、技能、伤害计算 | BIZ |
| UI/UE | 界面交互、动效、适配 | UI + HINT |
| 配置系统 | Excel 配置、数值调整、热更 | CONFIG |
| 辅助系统 | GM 工具、日志、监控 | UTIL + LOG |
| 合规系统 | 防沉迷、实名、版号 | SPECIAL + LOG |
2.2 模块拆分决策树
需求包含哪些系统？
├── 有充值/付费 → "充值付费" 模块
├── 有活动/运营 → "活动系统" 模块
├── 有社交/好友/公会 → "社交系统" 模块
├── 有道具/仓库/背包 → "背包系统" 模块
├── 有战斗/技能 → "战斗系统" 模块
├── 有核心玩法/任务/副本 → "主线玩法" 模块
├── 有界面/交互/动效 → "UI/UE" 模块
└── 有配置表/数值 → "配置系统" 模块
2.3 模块拆分输出格式
## 2.1 模块拆分
| # | 模块名称 | 涉及 Epic | 复杂度 | 优先级 |
|---|----------|-----------|--------|--------|
| 1 | 主线玩法 | BIZ-MAINLINE-001 | 高 | P0 |
| 2 | 充值付费 | BIZ-PURCHASE-001 | 高 | P0 |
| 3 | 活动系统 | BIZ-EVENT-001 | 中 | P1 |
| 4 | 背包系统 | BIZ-INVENTORY-001 | 中 | P1 |
| 5 | UI/UE | UI-001 | 低 | P2 |
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.
- 1mo ago First seen · 409 lines · 4,721 tokens per session scan A f25866baa663
S1_WORKLOAD_ESTIMATION is a cursor rule published in the GitHub repository SilenceInsect/AIDocxWorkFlow (2 stars, last pushed 2mo ago), licensed MIT. It adds 4,721 tokens to every session, about $0.0189 per session on Opus 5.5. 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
20-testing-generated-and-structure
Testing expectations, generated-file boundaries, and CLI structure contract.
fuzzing
Fuzzing setup and guidelines for skia-rs.
testing-and-quality
The testcomprehensive.py provides systematic testing of all 31 MCP tools.
smoke-monkey-tester
Smoke tests for core functionality and monkey/chaos tests aiming to break the system with randomized inputs. / TR: Sistemin temel fonksiyonlarını kontrol eden smoke testler ve rastgele girdilerle sistemi çökertmeyi hedefleyen monkey/chaos testleri.
testing
Testing conventions for Ion Design System using Jest and Angular Testing Library.
pre-flight-check
Mandatory fail-fast quality gate — run Typecheck, Lint, Test, and Security Audit sequentially before declaring any task done or committing code.