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 skills add pingfanfan/hello-dsh --skill debug-systematicallygit clone --depth 1 https://github.com/pingfanfan/hello-dshWrote 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/skills/pingfanfan/hello-dsh/debug-systematically)<a href="https://agentmods.dev/skills/pingfanfan/hello-dsh/debug-systematically"><img src="https://agentmods.dev/badge/skills/pingfanfan/hello-dsh/debug-systematically/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/skills/pingfanfan/hello-dsh/debug-systematically"><img src="https://agentmods.dev/badge/skills/pingfanfan/hello-dsh/debug-systematically.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.01016 |
| Opus 5.5 | $0.00020 | $0.00406 |
| Sonnet 5.5 | $0.00010 | $0.00203 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
debug-systematically 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.
What it actually says
系统化排查
铁律：没有定位到根因之前，不允许修改代码。
绕过这条铁律的典型说法是"先试试这样改会不会好"。那不是排查，那是碰运气：它可能让症状消失而根因还在，然后在别处以更难查的形式复现。
四个阶段
阶段之间不可跳跃。当前阶段的产出不满足，就不能进入下一阶段。
一、复现
产出：一条能稳定触发问题的命令或步骤。
- 拿到确切的报错全文，不是转述
- 确认触发条件：什么输入、什么环境、什么时序
- 确认边界：什么情况下不发生——这条经常比"什么时候发生"信息量更大
- 如果无法稳定复现，先解决这个问题：找出是并发、缓存、时序还是环境差异
无法复现就无法验证修复。这个阶段偷懒，后面全是猜。
二、定位
产出：指出具体的文件和行，并能解释它为什么产生了观察到的现象。
- 从报错栈的最深处往外读，不是最外层
- 在怀疑点打印实际值，不要假设它是什么
- 二分缩小范围：注释掉一半、回退一半提交、禁用一半配置
- 对比正常与异常两条路径的差异
判断标准：你能不能预测"如果我改动 X，现象会变成 Y"？ 能，说明定位到了；不能，说明还在猜。
三、假设与验证
产出：一个被证据支持的根因陈述。
写成这个形式：
因为
<具体代码>在<具体条件>下会<具体行为>，所以出现<观察到的现象>。
然后主动证伪：如果这个假设成立，还应该能观察到什么？去验证那件事。只找支持证据是确认偏误。
常见的假根因：
- "可能是缓存问题" —— 哪个缓存？哪一行读的？
- "时序问题" —— 哪两个操作的顺序？怎么证明？
- "环境不一致" —— 具体哪个变量不同？
这些说法不含信息量，不能作为根因。
四、修复
产出：改动 + 能捕获这个回归的测试。
- 修根因，不修症状
- 先写一个当前会失败的测试，再修，看它变绿——顺序反了就无法证明测试有效
- 检查同类问题：同样的模式在别处是否也存在
- 确认没有引入新问题：跑完整测试，不是只跑相关的那个
常见陷阱
| 陷阱 | 表现 | 纠正 |
|---|---|---|
| 改了就好了 | 不知道为什么好了 | 回退改动确认它确实会复现，再改回来 |
| 加日志加到忘了目的 | 日志越来越多，问题没近 | 每加一条日志都要说清想验证什么假设 |
| 相信注释和文档 | 按文档说的推理 | 以代码实际行为为准，文档可能过期 |
| 相信测试全绿 | 测试通过就认为没问题 | 测试可能根本没覆盖这条路径 |
| 一次改多处 | 好了但不知道哪个起作用 | 一次只改一个变量 |
| 跳过复现 | 直接开始读代码找可疑点 | 先复现，否则无法验证 |
什么时候该停下来求助
- 同一个假设方向试了三次都不对 —— 换方向，或者说出来让别人看
- 定位到了但改不动（涉及不熟悉的子系统）—— 带着定位结论去问，比带着现象去问有效十倍
- 复现不了 —— 优先解决复现，而不是硬猜
求助时给出：复现步骤、已排除的可能、当前假设、卡住的具体点。
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 · 82 lines · 51 tokens per session scan A 34934d4bfcaa
debug-systematically is a skill published in the GitHub repository pingfanfan/hello-dsh (100 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,016 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
systematic-debugging
Diagnose failures from runtime evidence before editing code.
diagnosing-bugs-zh
A diagnostic workflow for difficult bugs and performance regressions, meaning cases where software behaves incorrectly or becomes slower after a change.
dsh-debug-session
A troubleshooting guide for DSH startup failures, inactive plugins, and broken sessions. It describes collecting logs, narrowing down causes, backing up configuration, and rolling back changes.
dsh-speed-up-perf
Use when investigating or optimizing DeepSeek Harness performance, designing realistic synthetic benchmarks or CI performance gates, profiling long Sessions or Web responsiveness, or turning performance PR evidence into measured behavior-preserving fixes.
dsh-ci-test-reliability
Design, review, and diagnose DeepSeek Harness tests and fixtures that can fail nondeterministically under CI concurrency, shared host resources, clocks, process-global state, subprocesses, network listeners, or asynchronous teardown. Use when adding or changing tests with those risks, investigating flaky CI, or…