Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/xl188/XLSkillsnpx agentmods add skills/xl188/xlskills/systematic-debuggingWrote 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/xl188/xlskills/systematic-debugging)<a href="https://agentmods.dev/skills/xl188/xlskills/systematic-debugging"><img src="https://agentmods.dev/badge/skills/xl188/xlskills/systematic-debugging/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/xl188/xlskills/systematic-debugging"><img src="https://agentmods.dev/badge/skills/xl188/xlskills/systematic-debugging.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00053 | $0.03556 |
| Opus 5.5 | $0.00021 | $0.01422 |
| Sonnet 5.5 | $0.00011 | $0.00711 |
| Haiku 4.5 | $0.00005 | $0.00356 |
Grade A, and why
dsh-systematic-debugging scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. HTTP 脚本 / curl 打 dev server How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging（DSH 版）
Random fixes waste time and create new bugs. Quick patches mask underlying issues.
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.
与 Hermes 版的关系：四阶段、铁律、red flags 同源。工具换为 DSH（read / grep / glob / pwsh / subagent / job_*），并新增并行化：证据收集、假设验证可多路并行（DSH 同一条消息多 subagent 并行 + 后台任务不占并发槽）。
The Iron Law
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
If you haven't completed Phase 1, you cannot propose fixes.
The Feedback Loop Rule
The feedback loop is the debugging work. Before reading code to build a theory, create or identify a tight command that can go red on the user's exact symptom and green when the bug is fixed. A tight loop is fast, deterministic, agent-runnable, and specific enough to catch this bug — not merely "doesn't crash".
When a clean repro is hard, spend disproportionate effort building the loop. Guessing without a red-capable loop is the failure mode this skill exists to prevent.
When to Use
Use for ANY technical issue:
- Test failures / Bugs in production / Unexpected behavior
- Performance problems / Build failures / Integration issues
Use this ESPECIALLY when:
- Under time pressure (emergencies make guessing tempting)
- "Just one quick fix" seems obvious
- You've already tried multiple fixes
- Previous fix didn't work
- You don't fully understand the issue
Don't skip when:
- Issue seems simple (simple bugs have root causes too)
- You're in a hurry (rushing guarantees rework)
- Someone wants it fixed NOW (systematic is faster than thrashing)
The Four Phases
You MUST complete each phase before proceeding to the next.
Phase 1: Root Cause Investigation
BEFORE attempting ANY fix:
1. Read Error Messages Carefully
- Don't skip past errors or warnings；完整读栈、行号、文件路径、错误码
- Action: 用
read读相关源文件；用grep在代码库搜错误串
2. Build a Tight Feedback Loop
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 · 285 lines · 53 tokens per session scan A a5ae980c98bf
dsh-systematic-debugging is a skill published in the GitHub repository xl188/XLSkills (2 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 3,556 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
Diagnose and repair Hermes Agent
Use for diagnosing, repairing or optimizing a Hermes installation, especially after an update, skill-library changes, instruction conflicts, software failures or repeated checkpoint errors; also audit agent claims against retained tool and log evidence. Do not apply as a mandatory preflight for unrelated tasks…
adhoc-verification
Produce fresh, focused, local verification evidence for a code change without relying on the full test suite. Use when a system reminder (or the user) demands ad-hoc verification after an edit, or when you want to prove one behavior in isolation. Covers the correct way to write a throwaway supertest/harness script…
grill-with-docs
Cross-examine codebase architecture against official library documentation and API specs. Identifies deprecations, anti-patterns, and suboptimal library usage.
frontend-visual-verification
Confirm a CSS/HTML/template change actually rendered in a running browser — without being fooled by stale browser cache. Use whenever you edited frontend code (CSS, EJS/HTML, components) and must verify the visual result, especially when a vision screenshot seems to contradict the DOM or the served asset.
skill-auditor
Use when auditing Hermes skills for broken references.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.