Borrowing it
Nothing to install: this file belongs to charliehzm/medharness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/charliehzm/medharness/main/.claude/skills/systematic-debugging/SKILL.mdgit clone --depth 1 https://github.com/charliehzm/medharnessWrote 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/charliehzm/medharness/systematic-debugging)<a href="https://agentmods.dev/skills/charliehzm/medharness/systematic-debugging"><img src="https://agentmods.dev/badge/skills/charliehzm/medharness/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 | $0.00151 | $0.00726 |
| Opus 5 | $0.00076 | $0.00363 |
| Sonnet 5 | $0.00030 | $0.00145 |
| Haiku 4.5 | $0.00015 | $0.00073 |
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 7d 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
Stops the "patch the symptom, ship, repeat" anti-pattern.
The cycle
Symptom
↓ narrow (which input class / which code path)
Reproducer (smallest input that triggers it)
↓ instrument (log / trace / debugger)
Hypothesis (1 falsifiable claim)
↓ test the hypothesis directly
Root cause (the WHY behind the WHAT)
↓ fix at root (not symptom)
Regression test (locks behavior)
Anti-patterns
| Anti | What it looks like | Cost |
|---|---|---|
| Try-this-try-that | "let me change X and rerun" | hours wasted, no learning |
| Symptom patch | catch + log + return | bug returns elsewhere |
| Print debugging at scale | scattered prints, none removed | noise, audit hits |
| Fix without test | regression returns | infinite loop |
Workflow
- Capture the failure clearly (test name + error + line).
- Narrow input class — what's special about the failing case?
- Build a minimal reproducer (independent of the test suite).
- Form ONE hypothesis. Test it. If wrong, revise.
- Identify root cause; trace back to design / spec / data invariant.
- Apply fix at root.
- Add regression test that exercises the minimal reproducer.
- Write DEBUG_LOG entry: symptom + reproducer + root cause + fix + test ref.
Integration
- Triggered by: test failure (Step 9), review feedback (Step 8), bug report, compliance gap (Step 10 → Step 11)
- Output: DEBUG_LOG entries inform
memory-curate(Phase 3 inference rederive) andaudit-snapshot(prompts/debug_log/)
Common failure modes
- Hypothesis = "it should work" — not falsifiable. Mitigation: every hypothesis must predict an observable.
- Fix without regression test — the bug will return. Mitigation: discipline; reject the diff otherwise.
- Fix at the wrong layer — patches caller when bug is in callee's invariant. Mitigation: ask "why did the invariant break".
What ships with it
1 file 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.
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.
- 7d ago First seen · 72 lines · 151 tokens per session scan A 5947435b09fc
systematic-debugging is a skill published in the GitHub repository charliehzm/medharness (86 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 151 tokens to every session and 726 once invoked, about $0.0008 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
HIPAA Compliance Testing
Testing HIPAA compliance for healthcare applications including PHI handling, audit logging, access controls, and data encryption verification.
agent-debug-fixer
中文调试修复技能。用于报错、测试失败、页面异常、功能不符合预期、需要定位根因并做最小修复时。触发语包括"进入调试模式""帮我修问题""报错了""测试失败""页面坏了""找根因"。.
om-troubleshooter
Diagnose and fix standalone Open Mercato bugs across scope, commands, locking, fields, generated registries, UI hydration, cache/search, bootstraps, queues, and providers. Use for "fix bug", "why does this fail", "regression", "debug", "napraw błąd", or a failing test.
moai-workflow-loop
Ralph Engine - Automated feedback loop with LSP diagnostics and AST-grep integration for continuous code quality improvement. Use when implementing error-driven development, automated fixing, or continuous quality validation workflows.
moai-workflow-testing
Use when writing tests, measuring coverage, or running characterization, performance, or PR-review QA. Comprehensive specialist combining DDD testing, characterization tests, performance profiling, and TRUST 5 quality-assurance validation.
confirm-failures-are-causally-linked-to-the-task-before-reportin
When delegating a task affected by this skill, include.