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/nasrulhazim/claudenpx agentmods add skills/nasrulhazim/claude/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/nasrulhazim/claude/debugging)<a href="https://agentmods.dev/skills/nasrulhazim/claude/debugging"><img src="https://agentmods.dev/badge/skills/nasrulhazim/claude/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/nasrulhazim/claude/debugging"><img src="https://agentmods.dev/badge/skills/nasrulhazim/claude/debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00267 | $0.02969 |
| Opus 5.5 | $0.00107 | $0.01188 |
| Sonnet 5.5 | $0.00053 | $0.00594 |
| Haiku 4.5 | $0.00027 | $0.00297 |
Grade A, and why
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 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.
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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging and Error Recovery
A bug report names a symptom. Your job is the cause. The gap between them is where most wasted debugging time lives — patching the path the ticket names, while every sibling caller stays broken.
Command Reference
| Command | Description |
|---|---|
/debug triage |
Run the five-step triage on a reported failure |
/debug reproduce |
Build the smallest reliable reproducer |
/debug bisect |
Find the commit that introduced a regression |
/debug flaky |
Diagnose a test that passes and fails without code changes |
/debug guard |
Write the regression test that locks the fix in |
When to Use
- Something throws, returns the wrong value, or silently does nothing
- A test is flaky — passes alone, fails in the suite, or fails one run in ten
- Behaviour differs between local, staging and production
- A regression appeared and nobody knows which change caused it
- An exception's message and its actual cause do not match
- A queued job, scheduled command or event listener never runs
Do not use this skill to add features, refactor, or "clean up while I'm in here". A debug session ends when the bug is fixed and guarded, not when the file looks nicer.
The Five-Step Triage
Never skip a step. Steps 1 and 2 are where the answer actually is; steps 3–5 are mechanical.
Step 1: Reproduce
You have not started debugging until the failure happens on demand.
- Get the exact input: the request payload, the user, the tenant, the record ID, the time
- Reproduce it in the cheapest environment that still fails — a Pest test beats
tinker,tinkerbeats clicking through the UI - If it only fails in production, capture the difference:
php artisan about, the.envkeys that differ, the queue/cache drivers, the PHP version, the data volume
php artisan tinker --execute="dd(App\Models\Order::find(1234)->total());"
If you cannot reproduce it, say so plainly and stop. A fix for a bug you never saw fail is a guess wearing a diff.
What ships with it
2 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.
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 · 271 lines · 267 tokens per session scan A f8c36383c82b
debugging is a skill published in the GitHub repository nasrulhazim/claude (25 stars, last pushed yesterday), licensed MIT. It adds 267 tokens to every session and 2,969 once invoked, about $0.0011 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
reenable-test
Guide for investigating, fixing, verifying via TDD, and re-enabling disabled or flaky Chromium tests (C++, Android Java, or WebUI). Use this skill when asked to deflake, fix, or re-enable a disabled or flaky test case, or to verify post-submit stability of a re-enabled test. Don't use for disabling a failing test…
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
validate-fix
Prove a fix works before declaring done — re-run the failing test, run the full suite, typecheck, lint, and harden against recurrence. Use after implementing a bug fix, when user says "is this fixed?", or before closing an investigation.