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/TashanGKD/tashan-cursor-skillsWrote 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/tashangkd/tashan-cursor-skills/bug-fix-tdd-guard)<a href="https://agentmods.dev/rules/tashangkd/tashan-cursor-skills/bug-fix-tdd-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/bug-fix-tdd-guard/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/tashangkd/tashan-cursor-skills/bug-fix-tdd-guard"><img src="https://agentmods.dev/badge/rules/tashangkd/tashan-cursor-skills/bug-fix-tdd-guard.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 | $0.00128 | $0.02155 |
| Opus 5 | $0.00064 | $0.01077 |
| Sonnet 5 | $0.00026 | $0.00431 |
| Haiku 4.5 | $0.00013 | $0.00215 |
Grade A, and why
bug-fix-tdd-guard 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 10d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TDD 修复约束（bug-fix-tdd-guard）
核心问题：修复 Bug 时最容易犯的错误：
- 猜测性修复（没复现就改代码）→ 假修复，Bug 还在
- 没有回归测试 → 同一个 Bug 几周后复活
- 借机重构 → 修一个出另一个
- 修完没更新追踪台 → 协调者不知道状态变了
触发条件
以下任一条满足，且任务为开发类（修复代码）：
- 对话上下文包含「修复Bug」「fix bug」「TC-XXX」「BUG-YYYYMMDD-NN」
- 当前任务来自 bug-fix-loop-coordinator 的 dispatch
- 用户说「修复追踪台里的XX」「帮我修一下TC-XXX」
- 开发角色激活时上下文有「P0修复」「P1修复」等字样
激活后立即执行（强制序列，不可跳过任何步骤）
Step F1 【先复现，不要动代码】
在本地/测试环境稳定复现该 Bug：
- 执行追踪台中记录的复现步骤
- 确认能稳定触发（不是偶发的flaky）
IF 无法复现：
→ 不要修改任何代码
→ 更新追踪台：「复现失败，更新复现步骤需要确认」
→ 告知 bug-fix-loop-coordinator：「TC-XXX 无法复现，需要更多信息」
→ 停止
Step F2 【写失败测试（RED）——在改代码之前】
编写能捕获到这个 Bug 的测试用例：
- 测试必须在修复前失败（证明捕获了问题）
- 测试粒度：尽量选单元测试或集成测试，不要写E2E（太慢，太脆）
- 测试命名：test_fix_TC_XXX_[bug描述简写]
运行测试，确认它失败：
IF 测试通过（没有失败）：
→ 说明测试没有捕获到Bug，重新设计测试
→ 不允许进入 Step F3
证明测试捕获到Bug后，继续。
Step F3 【写最小修复代码（GREEN）】
原则（来自调研文档 TECH-008）：
✅ 只改让测试通过所需的最少代码
✅ 只在明确需要修改的地方改动
❌ 禁止：借机重构无关代码
❌ 禁止：一次修复多个Bug（每个Bug独立执行）
❌ 禁止：修改超出该Bug影响范围的代码
写完后运行测试：
IF 测试仍然失败：
→ 检查修复逻辑，重新分析根因
→ 最多3次尝试，仍不通过则标记「需人工介入」
Step F4 【全量CI回归（必须通过才能继续）】
运行全量测试套件：
- Layer 0（无LLM）：所有单元测试 + 集成测试
- Layer 1（有LLM，时间允许时）：核心链路
IF 有其他测试失败（影响半径）：
→ 分析是否是本次改动引起
→ 是 → 修复相关代码，确保不破坏已有功能
→ 不是（flaky test）→ 记录，不阻止，继续
IF CI 全绿：继续 Step F5
Step F5 【更新技术问题追踪台（必须执行）】
Read: 项目群/[项目]/技术架构师/技术问题追踪台.md
将对应Bug条目的状态更新为：
「已修复（[日期]，修复说明：[一句话说明改了什么]，TDD证据：测试文件路径）」
IF 找不到对应条目：
→ 向 bug-fix-loop-coordinator 报告异常
Step F6 【向修复记录追加条目】
Append to: 项目群/[项目]/内部总控/修复记录.md
格式（见 bug-fix-loop-coordinator Step 3.5 的格式模板）：
- Bug ID
- 根因（一句话）
- 修复内容
- TDD证据（失败测试路径 + 通过证明）
- CI状态
Step F7 【通知协调者】
输出给 bug-fix-loop-coordinator：
「✅ TC-XXX 修复完成
- 失败测试：[测试路径]
- 修复文件：[文件路径]
- CI状态：全绿
- 追踪台已更新
等待回归测试验证。」
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.
- 10d ago First seen · 194 lines · 128 tokens per session scan A 90c0bb0d1d8b
bug-fix-tdd-guard is a cursor rule published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 128 tokens to every session and 2,155 once invoked, about $0.0006 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 2026-08-30.
Other cursor rules, from other repositories
fix-bug
Bug fix orchestrator — activeflow fixbug; reads specs/bugs/BUG-.md; chains investigate-bug, develop-tdd, validate-fix. Use when user reports a defect.
investigate-bug
Investigate a bug or issue by exploring the codebase to find root cause, then write a TDD-based fix plan to specs/bugs/BUG-.md. Use when user reports a bug, wants to investigate a problem, mentions "triage", or wants to plan a fix.
refactoring
Refactoring: systematic approach, extract/inline, guard clauses, early returns.
chaos
Failure injection mode — stress test implementations by simulating failures and hostile conditions.
tdd
Test-driven development — red-green-refactor cycle.
06-error-handling
Cursor rule "06-error-handling" from orbitalsonic/AndroidPilot, covering error handling, never, always, coroutines and validation.