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/rendheaven/docbiz-dev-harness/final-testgit clone --depth 1 https://github.com/RendHeaven/DocBiz-Dev-HarnessWhat 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 | $0.00040 | $0.00664 |
| Opus 5 | $0.00020 | $0.00332 |
| Sonnet 5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
final-test 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.
What it actually says
最终测试用例规范（final-test）
养料：前端 front-feed（frontend-workflow §7）、后端 backend-feed（backend-workflow §养料）。本规则消费它们生成终测。
定位
- 养料 = 盲区素材，不写完整用例。
- test-cases.md = QA 可直接执行的用例（含常规交互），并把养料展开为步骤。
- 头部状态三选一：
AI 草案，待 QA 审定|QA 审定中|QA 执行完成
路径：features/yyyyMMdd-需求简称/_shared/final-test/test-cases.md
多次回归：test-cases-{N}.md（N≥2，先列目录防覆盖）
模板：final-test-template.md
触发
接口测试 + 养料稳定后生成草案；纯前端：阶段二 + front-feed 稳定即可。
数据来源
生成前扫描所有 {开发者标识}/ 子目录，收集：
- _shared/front-feed.md、backend-feed.md
- 各后端 2-exec/interface.md、3-review/review.md
- 各 4-interface-test/{N}.md、5-api-doc/front.md
- 各 plan（后端 1-plan、前端 1-ui-plan、3-api-plan）
- design-prototypes/ PRD/HTML
前端不产出 interface/front — 只读后端。
纯前端兜底
无后端子目录：用 4-api-exec/exec 中 DevTools 片段；头部标注 [纯前端需求] 接口素材来自 …。
必须章节
概述、分组用例（含来源标签）、接口验收、表单矩阵、角色矩阵、养料展开的跨流程/隐藏点、风险边界、迁移验证（如有）、回归矩阵、汇总、修订记录、覆盖度自检。
来源标签（必填）
[来源:相对路径#§3.1]、[来源:路径#CASE-2]、[来源:路径#L42]
禁止无定位的「来源:养料」。
AI 规则
禁止编造路径/字段；缺数据标 [待补:原因]。禁止照抄养料里的源码符号。多花名不可只读一人产物。
QA
审定 → 执行填结果 → 完成改状态；变更可新建 test-cases-N.md 做差量回归。
不应包含
源码路径、组件/类/方法名、技术栈实现细节。
全文：docs/testing.md
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 · 62 lines · 40 tokens per session scan A a08d11313307
final-test is a cursor rule published in the GitHub repository RendHeaven/DocBiz-Dev-Harness (2 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 664 once invoked, about $0.0002 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.