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/azzygoatcoder/agent-useful-skills/systematic-debuggingnpx skills add Azzygoatcoder/agent-useful-skills --skill systematic-debugginggit clone --depth 1 https://github.com/Azzygoatcoder/agent-useful-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/skills/azzygoatcoder/agent-useful-skills/systematic-debugging)<a href="https://agentmods.dev/skills/azzygoatcoder/agent-useful-skills/systematic-debugging"><img src="https://agentmods.dev/badge/skills/azzygoatcoder/agent-useful-skills/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 | $0.00021 | $0.00703 |
| Opus 5 | $0.00010 | $0.00351 |
| Sonnet 5 | $0.00004 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00070 |
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 4d 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
Overview
Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure.
Violating the letter of this process is violating the spirit of debugging.
The Iron Law
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
If you haven't completed Phase 1, you cannot propose fixes.
场景判定（先定轻重，再定流程）
| 场景 | 力度 |
|---|---|
| 生产环境、正式项目、共享代码、反复出现的 bug | 完整四阶段：根因 → 模式 → 假设验证 → 实施 |
| 个人业余项目、低风险探索、一次性脚本 | 轻量调试：至少做到「稳定复现 → 定位根因 → 验证修复」；不需要形式上把四阶段全走一遍 |
| 纯 throwaway / 临时现象 | 可不深挖，但不要把这个修复当作“已验证”提交 |
判断标准：这个 bug 会浪费别人/后续/生产多少时间？ 低风险就快走，高成本就按完整流程。完整流程不是仪式，是“这个错误值得花时间”时的护城河。
Quick Reference
| Phase | Key Activities | Success Criteria |
|---|---|---|
| 1. Root Cause | Read errors, reproduce, check changes, gather evidence | Understand WHAT and WHY |
| 2. Pattern | Find working examples, compare | Identify differences |
| 3. Hypothesis | Form theory, test minimally | Confirmed or new hypothesis |
| 4. Implementation | Create test, fix, verify | Bug resolved, tests pass |
完整四阶段、Red Flags、Common Rationalizations 和 Supporting Techniques 见 references/debugging-guide.md。
轻量路径（个人/低风险项目）
- 先复现：能不能稳定触发？不能，先补数据/日志，别猜。
- 定位根因：读错误信息、看最近改动、追到数据源头。至少确定“是哪里错了”，而不是“哪里看起来像错”。
- 最小修复：一次只改一个变量，验证修复是否生效。
- 验收：确认问题消失；如果影响真实使用，补一个最小回归测试。
Red Flags（速记）
- 还没定位根因就开始改
- “先快速修一下，之后再查”
- 一次改多个地方
- 3 次以上修复失败还在继续
遇到这些，STOP 回到根因调查。
Supporting Techniques
root-cause-tracing.md— Trace bugs backward through call stack to find original triggerdefense-in-depth.md— Add validation at multiple layers after finding root causecondition-based-waiting.md— Replace arbitrary timeouts with condition polling
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- condition-based-waiting-example.ts 4.9 KB runs code
- condition-based-waiting.md 3.4 KB
- CREATION-LOG.md 4.2 KB
- defense-in-depth.md 3.6 KB
- find-polluter.sh 1.9 KB runs code
- references/debugging-guide.md 8.2 KB
- root-cause-tracing.md 5.2 KB
- test-academic.md 653 B
- test-pressure-1.md 1.9 KB
- test-pressure-2.md 2.2 KB
- test-pressure-3.md 2.6 KB
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.
- 4d ago First seen · 66 lines · 21 tokens per session scan A 03f2a83202b2
systematic-debugging is a skill published in the GitHub repository Azzygoatcoder/agent-useful-skills (4 stars, last pushed 6d ago), licensed MIT. It adds 21 tokens to every session and 703 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 2026-08-31.
Other skills, from other repositories
dsh-plugin-dev
开发 DeepSeek Harness (DSH) 插件的标准与权威参考：编写/修改/审查/调试 DSH/Cordis 插件、服务、事件、插件配置、模型工具、LLM 适配器、三种角色拆分、打包安装、workspace 包、cordis.yml 组合时使用；提到 DSH 插件、Cordis、plugin、服务、事件、工具、适配器即触发。 The authoritative standard for developing DeepSeek Harness (DSH) plugins — create, modify, review or debug DSH/Cordis plugins, services, events…
dsh-plugin-client
开发 DSH 插件的 client 半端（浏览器 UI）时使用：按已验证的 slot 与标准-kit 契约注册界面、双目标构建并包装客户端 bundle。.
dsh-plugin-dev
开发或调试 DeepSeek Harness 插件时使用：按已验证的结构编写 bundle、本地调试、发布与收录。.
dsh-plugin-i18n
给 DSH 插件的客户端 UI 做中英文国际化时使用：locale 命名空间、slot 声明、t() 取词与切语言即时生效。.
dsh-git-commit
提交代码时使用：按约定式提交写 commit message，并在提交前做最小自检。.
dsh-dependency-audit
升级或审查项目依赖时使用：审计安全告警、控制安装脚本风险、制定升级回滚预案。.