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/arlenjim/claude-code-for-non-coders/scientific-debuggingnpx skills add Arlenjim/claude-code-for-non-coders --skill scientific-debugginggit clone --depth 1 https://github.com/Arlenjim/claude-code-for-non-codersWrote 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/arlenjim/claude-code-for-non-coders/scientific-debugging)<a href="https://agentmods.dev/skills/arlenjim/claude-code-for-non-coders/scientific-debugging"><img src="https://agentmods.dev/badge/skills/arlenjim/claude-code-for-non-coders/scientific-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 | $0.00042 | $0.01390 |
| Opus 5 | $0.00021 | $0.00695 |
| Sonnet 5 | $0.00008 | $0.00278 |
| Haiku 4.5 | $0.00004 | $0.00139 |
Grade A, and why
scientific-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 5d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scientific debugging
A bug is a gap between what you observe and what you expected. Debugging it means explaining that gap with a proven cause — not making it disappear. A symptom that vanishes without explanation is not a fixed bug, it's a hidden bug.
1. Before searching: pin down the facts
Write the gap in one factual sentence. "When I do X, I observe Y; I expected Z." If you can't fill in all three slots, you don't have a bug yet — you have an impression. Go get the three first.
Reproduce before explaining. Until you have triggered the bug yourself, you're working on a story, not a fact. A bug you can't reproduce can't be fixed — it gets trapped (logs, instrumentation) until it becomes reproducible.
Shrink the reproduction to the minimum. Remove everything that can be removed while the bug persists: data, steps, options, dependencies. Every element removed without making the bug disappear is exonerated; every element whose removal makes the bug disappear is a suspect. The minimal reproduction IS already half the diagnosis.
Read the error message literally. Word for word, including the file name, the line number, the error code, and the first error in the stack — not the last one, which is often just a consequence. The classic trap: reading what you expect the error to say instead of what it says. If a term in the message is unknown to you, look it up before forming any hypothesis.
Establish "since when". Did it ever work? If so, what changed between when it worked and now — code, dependency, environment, data, configuration? A regression is searched for in the delta, not in the whole system.
2. Searching: hypotheses and bisection
Form hypotheses BEFORE touching the code. Two or three plausible causes, each written with its testable prediction: "if it's A, then by doing T I should observe O". A hypothesis without a prediction is not a hypothesis, it's an intuition — unusable.
Test the cheapest hypothesis first, not the most seductive one. A hypothesis eliminated in 30 seconds beats a brilliant hypothesis that needs an hour of setup.
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.
- 5d ago First seen · 63 lines · 42 tokens per session scan A d811caf39495
scientific-debugging is a skill published in the GitHub repository Arlenjim/claude-code-for-non-coders (10 stars, last pushed 18d ago), licensed MIT. It adds 42 tokens to every session and 1,390 once invoked, about $0.0002 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 skills, from other repositories
prismstack
Prismstack — Domain Stack Builder. 10 個互動式 skill 把 gstack 方法論遷移到任何領域。 從規劃到搭建到持續迭代的完整工具鏈。 When you notice the user is at these stages, suggest the appropriate skill: User wants to build a domain skill stack → suggest /domain-plan User says "我做 X 領域", "幫我建一套 skill", "規劃" → suggest /domain-plan User has existing skills…
domain-plan
為目標領域推導完整的 gstack skill map + workflow + artifact flow。 Trigger: 用戶說「我做 X 領域」、「幫我規劃 skill」、「我想建一套 domain stack」。 Do NOT use when: 已經有 skill map，要搭建（用 /domain-build）。 Do NOT use when: 要加單一 skill（用 /skill-gen）。 上游：無（入口 skill）。 下游：/domain-build。 產出：skill-map-{datetime}.md + workflow-graph-{datetime}.md.
skill-check
Prismstack 的品質審查 meta-skill。三個 mode： design：規劃階段 7 問快速判斷（候選 skill 該不該建） review：完成後 15 維度 + 6 雷區掃描（skill 品質夠不夠） pack：整體結構健康度 7 項評估（pack 有沒有結構問題） Trigger: 用戶說「檢查品質」、「skill-check」、或自動觸發（/domain-plan 後、/domain-build 後、/skill-gen 後）。 Do NOT use when: 要改 skill 內容（用 /skill-edit）。.
super-guide
Prismstack 超級引導員 — 實戰教練。 Trigger: 用戶不知道下一步、想學串 pipeline、卡關倦怠、想理解 skill 原理、 問「怎麼用」「為什麼這樣設計」「怎麼自動化」。 Do NOT use when: 用戶明確知道要跑哪個 skill（用 /prism-routing）。 Do NOT use when: 用戶要規劃新 domain stack（用 /domain-plan）。 並存：/prism-routing 是快速路由（熟手用），/super-guide 是教學引導（需要理解的人用）。 上游：任何 skill 的產出、用戶的 domain stack。 下游：任何 Prismstack…
domain-build
根據 /domain-plan 產出的 skill map，自動搭建完整的 domain gstack repo。 Trigger: /domain-plan 完成後、用戶說「開始搭建」、「build」。 Do NOT use when: 還沒規劃 skill map（先用 /domain-plan）。 Do NOT use when: 要加單一 skill（用 /skill-gen）。 上游：/domain-plan（讀取 skill-map-.md）。 下游：/skill-check pack（Wave 2）。Wave 1 內建輕量 pack health 替代。 產出：完整的 domain gstack repo。.
domain-upgrade
Domain stack 的持續升級服務。傾聽用戶需求、收集測試回饋、編排改進。 Trigger: 用戶說「升級」、「改進」、「測試回饋」、「這裡不好用」、「我有新需求」。 Do NOT use when: 要做具體的 skill 修改（用 /skill-edit）。 Do NOT use when: 要新增 skill（用 /skill-gen）。 上游：用戶需求 / 測試回饋。 下游：/skill-edit, /source-convert, /tool-builder, /workflow-edit。 產出：升級後的 domain stack。.