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 skills/pingfanfan/hello-dsh/debug-systematicallynpx skills add pingfanfan/hello-dsh --skill debug-systematicallygit clone --depth 1 https://github.com/pingfanfan/hello-dshWhat 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 | $0.00051 | $0.01016 |
| Opus 5 | $0.00026 | $0.00508 |
| Sonnet 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 2d 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.
- 2d 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 (86 stars, last pushed 18d ago), licensed MIT. It adds 51 tokens to every session and 1,016 once invoked, about $0.0003 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 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…
wayfinder
把一个巨大的工作块(超过单个 agent 会话所能承载)规划为 issue tracker 上的一张共享决策 ticket 地图,并逐个解决这些 tickets,直到通往目的地的路线清晰可见。.
teach
在当前工作区内教会用户一项新技能或一个新概念。.
dsh-doc-standards
Use when writing, moving, reviewing, or auditing documentation in the deepseek-harness repo — choosing hierarchy and detail, separating tutorials from references, checking tutorial progression, trimming doc slop, responding to a verify-doc-budgets failure, or requests like "improve the docs", "audit the docs", "where…
teach
Teach the user a new skill or concept, within this workspace.
dsh-web-release
Release and publish the dsh-web monorepo (DSH Web GUI plugin family + skin collection) — bump all packages to one unified version, commit and tag (tags are cut from main after dev integration; dev is the integration branch), push the vX.Y.Z tag that triggers the GitHub Actions publish pipeline, and verify the npm…