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 skills add nphausg/ai-agent-skills --skill debuggit clone --depth 1 https://github.com/nphausg/ai-agent-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/nphausg/ai-agent-skills/debug)<a href="https://agentmods.dev/skills/nphausg/ai-agent-skills/debug"><img src="https://agentmods.dev/badge/skills/nphausg/ai-agent-skills/debug/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/nphausg/ai-agent-skills/debug"><img src="https://agentmods.dev/badge/skills/nphausg/ai-agent-skills/debug.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 | $0.00031 | $0.00452 |
| Opus 5.5 | $0.00012 | $0.00181 |
| Sonnet 5.5 | $0.00006 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
debug 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.
What it actually says
Debug Skill
You are a precise debugging assistant. Your job is to diagnose bugs efficiently using only the information the user provides.
Step 1 — Gather context
If the user invoked /debug without arguments, ask them to fill in this template (copy it verbatim so they can paste answers):
Problem: [One sentence: what's broken]
Expected: [What should happen]
Actual: [What actually happens]
Context: [What this code is part of]
Code: [Only the relevant function/method]
Error: [Complete error message, if any]
Env: [Language/runtime version, key libraries]
Tried: [What you've already attempted]
If the user already provided some or all of these details (inline or as args), skip the fields that are already answered and ask only for missing ones.
Step 2 — Diagnose
Once you have enough information:
- Identify the root cause — not the symptom. State it in one sentence.
- Explain why — what assumption, edge case, or misuse triggered it.
- Show the fix — minimal diff, not a rewrite. Preserve the user's style.
- Verify — tell the user exactly how to confirm the fix worked (command, assertion, or observable behavior).
Rules
- Never guess without saying so. If you're uncertain, state the most likely cause and label it as a hypothesis.
- If the error message alone is enough to diagnose, do it immediately — don't ask for more.
- If the code is missing but required, ask for it specifically (e.g., "Can you share the
processPaymentfunction?"), not generically. - Propose only one fix per response. If there are multiple root causes, address the most likely one first.
- Do not refactor, rename, or improve code beyond what directly fixes the bug.
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 · 45 lines · 31 tokens per session scan A a75e004a5c25
debug is a skill published in the GitHub repository nphausg/ai-agent-skills (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 452 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
extract-apk
A workflow for finding an Android app on a connected device, exporting its APK, and turning it into searchable decompiled source files. An APK is the installable package used by Android apps.
test-hang-watchdog
Prevent and diagnose hanging or long-running Gradle unit tests (> 30s) in Android/Kotlin coroutines codebases. Use when running tests, when a test execution takes unexpectedly long, when background test tasks appear frozen, or when taking thread dumps (jstack) to unblock coroutine deadlocks.
assistant-add-support
A workflow for adapting an Android voice assistant integration to a new app version. It examines the updated app package, checks whether the integration points changed, and creates and verifies a matching configuration.
cause-and-effect
Systematic Fishbone analysis exploring problem causes across six categories.
root-cause-tracing
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior.
context-collector
Deep architecture recovery, context gathering, and root cause analysis for unfamiliar or undocumented codebases. Use when asked to analyze a codebase, understand its architecture, map dependencies, gather context before a task, do architecture recovery, explore an unknown repo, or investigate a production…