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/amplifthq/oh-my-dsh/systematic-debuggingnpx skills add amplifthq/oh-my-dsh --skill systematic-debugginggit clone --depth 1 https://github.com/amplifthq/oh-my-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/amplifthq/oh-my-dsh/systematic-debugging)<a href="https://agentmods.dev/skills/amplifthq/oh-my-dsh/systematic-debugging"><img src="https://agentmods.dev/badge/skills/amplifthq/oh-my-dsh/systematic-debugging.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 | $0.00015 | $0.00156 |
| Opus 5 | $0.00008 | $0.00078 |
| Sonnet 5 | $0.00003 | $0.00031 |
| Haiku 4.5 | $0.00002 | $0.00016 |
Grade A, and why
systematic-debugging 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
Systematic debugging
- Reproduce the exact symptom with the smallest safe command.
- Capture the complete error, inputs, environment, and boundary where expected behavior diverges.
- Form one falsifiable hypothesis at a time and test it with focused instrumentation or an existing diagnostic.
- Follow values backward to the first incorrect state; do not patch the last visible exception unless it is the cause.
- Add or identify a regression check that fails for the original bug.
- Make the smallest causal fix, rerun the regression check, then run proportionate surrounding checks.
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 · 15 lines · 15 tokens per session scan A d0e2dbfaaa88
systematic-debugging is a skill published in the GitHub repository amplifthq/oh-my-dsh (14 stars, last pushed 7d ago), licensed MIT. It adds 15 tokens to every session and 156 once invoked, about $0.0001 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
bug
Use when the user reports a bug or asks to capture one — ask the minimal questions needed, then produce a structured bug report the team can act on.
dsh-troubleshoot
当 DeepSeek Harness 起不来、插件没加载、技能不见了、工具报 UNKNOWNTOOL、或出现"配置写了但没生效"这类静默失效时使用——按静默失效优先的顺序排查。.
error-handling
当需要设计错误处理、决定该抛还是该返回、写错误信息、或排查"出错了但没人知道"的问题时使用——按调用方是否需要区分处理来决定错误的结构。.
ask-good-questions
当需要在 GitHub Discussions、issue、社区或团队里提技术问题、报 bug、或帮别人改进他们的提问时使用——给出能被复现的最小信息集，避免"用不了"这类无效提问。.
debug-systematically
Skill "debug-systematically" from pingfanfan/hello-dsh, covering 系统化排查, 四个阶段, 一、复现, 二、定位 and 三、假设与验证.
perf-optimize
当需要优化性能、排查慢的原因、或判断某个优化值不值得做时使用——强制先测量再优化，禁止凭直觉猜瓶颈。.