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/madappgang/claude-code/debugging-strategiesnpx skills add MadAppGang/claude-code --skill debugging-strategiesgit clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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/madappgang/claude-code/debugging-strategies)<a href="https://agentmods.dev/skills/madappgang/claude-code/debugging-strategies"><img src="https://agentmods.dev/badge/skills/madappgang/claude-code/debugging-strategies.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 | $0.00035 | $0.02290 |
| Opus 5 | $0.00017 | $0.01145 |
| Sonnet 5 | $0.00007 | $0.00458 |
| Haiku 4.5 | $0.00003 | $0.00229 |
Grade A, and why
debugging-strategies 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 yesterday.
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 — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Universal Debugging Strategies
Overview
Language-agnostic debugging techniques and strategies applicable across all technology stacks.
Debugging Methodology
The Scientific Method for Debugging
- Observe: Gather information about the bug
- Hypothesize: Form theories about the cause
- Predict: What would confirm/refute each theory?
- Test: Run experiments to validate
- Conclude: Identify root cause and fix
Systematic Approach
1. Reproduce the bug reliably
2. Isolate the failing code path
3. Trace backwards from the error
4. Identify the root cause
5. Verify the fix
6. Add tests to prevent regression
Error Analysis
Stack Trace Reading
Read stack traces bottom to top:
Error: Cannot read property 'name' of undefined
at formatUser (src/utils/format.ts:42) ← Error thrown here
at processUsers (src/services/user.ts:28) ← Called from here
at UserList.render (src/components/UserList.tsx:15)
at App.render (src/App.tsx:8) ← Entry point
Focus on YOUR code - skip framework/library internals initially.
Error Categories
| Category | Examples | Common Causes |
|---|---|---|
| Null/Undefined | Cannot read property 'x' of undefined |
Missing data, async timing |
| Type Errors | x is not a function |
Wrong type, typo |
| Logic Errors | Wrong output, no error | Incorrect conditions |
| Runtime Errors | Out of bounds, division by zero | Invalid input |
| Async Errors | Unhandled promise rejection | Missing error handler |
| Network Errors | Timeout, connection refused | API down, wrong URL |
Debugging Techniques
Binary Search (Bisection)
When the bug is somewhere in a large codebase:
1. Find a known good state (commit, version)
2. Find current bad state
3. Test the midpoint
4. Narrow to half with bug
5. Repeat until found
Git bisect:
git bisect start
git bisect bad # Current commit is broken
git bisect good v1.0.0 # v1.0.0 was working
# Git checks out midpoint, test it
git bisect good/bad # Mark and continue
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.
- yesterday First seen · 393 lines · 35 tokens per session scan A b81ab42775a8
debugging-strategies is a skill published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 2,290 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Methodical bug investigation and root cause analysis.
cortivex-pipeline-debugger
Step-through debugging for Cortivex pipelines with breakpoints, inspection, replay, and execution tracing.
log-triage
CI/build/runtime error log analysis with root-cause detection, prioritized fix plans, and verification checklists.
review-logging-patterns
Review code for logging patterns and suggest evlog adoption. Optionally use @evlog/cli (evlog init to wire evlog, evlog agents to write the conventions into AGENTS.md, evlog map to score entry-point coverage, --baseline to gate regressions in CI) on Nuxt, Nitro, Next.js, TanStack Start, and Hono. Guides setup on those…
build-audit-logs
Build or review audit trails in TypeScript/JavaScript apps using evlog (pipelines, typed actions, denials, retention, compliance-style reviews). For application code, not for extending the evlog package.
create-evlog-framework-integration
Create a new evlog framework integration to add automatic wide-event logging to an HTTP framework. Use when adding middleware/plugin support for a framework (e.g., Koa, H3 standalone, Deno Fresh, etc.) to the evlog package. Covers source code, build config, package exports, tests, example app, and all documentation.