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/goal_business_audit)<a href="https://agentmods.dev/rules/silenceinsect/aidocxworkflow/goal_business_audit"><img src="https://agentmods.dev/badge/rules/silenceinsect/aidocxworkflow/goal_business_audit.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 5.1 | $0.01007 | $0.01007 |
| Opus 5 | $0.00504 | $0.00504 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
GOAL_BUSINESS_AUDIT scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Goal Loop 业务审计规则(v1,适配 AIDocxWorkFlow)
适用对象:所有在
/goal-loop自治循环下产出的 FP / TP / TC / 验收文档。 触发位置:GoalLoop.audit() 调用前;产物落盘后由 hook 自动追加 system_reminder 提示。 规则 SSOT:本文件是项目级业务审计规则的唯一真相源;其他文件需引用本文件而非重复定义。 范围约束:本规则仅约束"由 goal-loop 驱动的产物";普通阶段产物遵守各自 STAGE_S*.mdc。
规则 1:FP 必须中性功能命名
禁止:场景化命名(如 FP-001 用户登录、FP-002 提现失败重试)
要求:使用"功能对象 + 行为动词"的中性命名(如 FP-001 身份验证、FP-002 资金回滚)
审计方式:
- 正则:
^FP-\d{3}\s+[一-龥]{2,10}$(中文 2-10 字,且不含"登录/失败/重试/异常"等场景词) - 命中场景词 → FAIL(AuditVerdict.judgement = "FAIL")
规则 2:禁止文本【】锚点冗余
禁止:用 【用户ID】、【金额】 等文本方括号引用上游字段
要求:所有溯源依赖结构化字段(obj_id / story_id / feature_point_id)
审计方式:
- 正则:
【[^】]+】在 TC 描述中每出现 1 次 → 警告 - 超过 3 次 → FAIL
规则 3:TP/TC/Excel 结构化映射
禁止:从 Markdown / Excel 文本中截取字段
要求:所有 TP / TC / Excel 列严格通过 ID 字段对齐(test_point_id / test_case_id / feature_point_id)
审计方式:
- 检查 JSON 是否含必填 ID 字段;缺失 → FAIL
- 检查 Excel 列名是否与 JSON schema 一致;不一致 → FAIL
规则 4:正反场景无语义冲突
禁止:EP_VALID(等价类有效)和 EP_INVALID(等价类无效)描述同一行为
要求:正反场景语义必须互补且互斥;EP_BOUNDARY_* 标注具体边界值
审计方式:
- 解析
test_point.test_point_type字段 EP_VALID与EP_INVALID的obj_id必须一致EP_BOUNDARY_*必须包含boundary_value数值字段
规则 5:L1 校验轻量化
禁止:L1 校验器进行文本格式校验(行尾空格 / 中英空格 / 标点风格) 要求:L1 仅校验:
- 必填字段存在
- 枚举值合法(status / priority / test_point_type)
- ID 格式(
TC-\d{4,6}/TP-\d{4,6}) - 跨文件 ID 引用一致
审计方式:
- L1 校验器代码中不含
re.search.*\s、re.match.*[,:]等文本格式正则 - L1 校验器代码中不含
.replace.*空格类清理逻辑
审计触发时机
| 阶段 | 触发方式 |
|---|---|
| Plan | GoalLoop.plan() 时枚举 FP 命名 → 规则 1 |
| Act | 写产物后调用 GoalLoop.audit() 逐条对比规则 2/3/4 |
| Audit | GoalLoop.audit() 内部自动跑规则 5(扫描 L1 校验器源码) |
不合规处置
任一规则 FAIL → AuditVerdict.judgement = "FAIL" → GoalLoop.iterate() 进入下一轮而非 achieved → 用户可通过 /pause-goal 暂停或 /clear-goal 终止。
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.
- 6d ago First seen · 74 lines · 1,007 tokens per session scan A 0316aa6e25c4
GOAL_BUSINESS_AUDIT is a cursor rule published in the GitHub repository SilenceInsect/AIDocxWorkFlow (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,007 tokens to every session, about $0.0050 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
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.