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 patrick-fu/awesome-skills --skill debugginggit clone --depth 1 https://github.com/patrick-fu/awesome-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/patrick-fu/awesome-skills/debugging)<a href="https://agentmods.dev/skills/patrick-fu/awesome-skills/debugging"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/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/patrick-fu/awesome-skills/debugging"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/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 | $0.00025 | $0.00799 |
| Opus 5.5 | $0.00010 | $0.00320 |
| Sonnet 5.5 | $0.00005 | $0.00160 |
| Haiku 4.5 | $0.00003 | $0.00080 |
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 17d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging
Build causal evidence for the reported failure. Match the request: diagnosis ends with findings and remaining uncertainty; a fix request includes the related repair and verification. Use project conventions and relevant domain or architecture documentation. Redact secrets from shared commands, outputs, and captures; pass credentials through the environment.
Anchor
Identify the expected behavior, actual symptom, affected scenario, and relevant artifact/version, configuration, and state. Distinguish observations from hypotheses. Reuse prior evidence when its identity and conditions still match.
Keep the original scenario as the acceptance target. A nearby error, mock-only failure, or different instance is not a substitute for the reported symptom.
Observe
Choose the smallest available evidence that can distinguish likely causes. Start with the relevant route; load further references only when the evidence gap requires them.
- Reproduce: run a symptom-specific test, request, CLI, replay, or harness. Verify that it actually fails on this bug. Tighten or minimize the loop where useful, retaining the original inputs and conditions.
- Instrument: when a running path needs observation, read instrumentation.
- Forensics: for existing captures or profiling a live process, read forensics.
- Flaky: for intermittent, concurrent, or order-dependent failures, read flaky failures.
Use credible logs, captures, and source evidence even when a full reproducer is unavailable. State which claims they support and which remain untested. Run reachable checks yourself. When a device, permission, or physical action requires the user, request the smallest concrete action and evidence return.
Probe
Rank plausible alternatives. For each useful probe, state its prediction: "If X causes the failure, observing or changing Y should produce Z." Change one discriminating factor where practical and compare the result with the prediction. Trace the first divergence back through boundaries and callers to the originating state or input. Negative results narrow the search too.
What ships with it
4 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.
- 17d ago First seen · 90 lines · 25 tokens per session scan A 08ff021a9d63
debugging is a skill published in the GitHub repository patrick-fu/awesome-skills (69 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 799 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 2026-10-09.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.