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 xonovex/platform --skill debugging-guidegit clone --depth 1 https://github.com/xonovex/platformWrote 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/xonovex/platform/debugging-guide)<a href="https://agentmods.dev/skills/xonovex/platform/debugging-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/debugging-guide/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/xonovex/platform/debugging-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/debugging-guide.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 | $0.00120 | $0.01121 |
| Opus 5.5 | $0.00048 | $0.00448 |
| Sonnet 5.5 | $0.00024 | $0.00224 |
| Haiku 4.5 | $0.00012 | $0.00112 |
Grade A, and why
debugging-guide 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging Guidelines
Systematic, hypothesis-driven debugging of native/low-level software, plus designing each class of bug out of existence. The cheapest bug is the one made impossible; the next cheapest is the one that trips a tripwire the instant it happens. Lifetime/ownership design lives in memory-management-guide, race correctness in lock-free-guide, and speed profiling in data-oriented-design-guide; this skill is about finding bugs and preventing classes of them.
Essentials
- Classify the bug - Each class (logic, uninitialized, leak, overwrite, race, design, intermittent) has a design choice that eliminates the whole class, see references/bug-taxonomy.md
- Hypothesis, not flailing - Form one falsifiable guess, change one thing, predict, observe; never edit randomly, see references/scientific-debugging.md
- Get a deterministic repro first - A reliable repro is what lets you step through the "before"; shrink it small, see references/reproduction-and-bisection.md
- Trip the wire early - Assertions, invariants, validation layers, and sanitizers turn silent corruption into a loud failure at the fault site, see references/instrumentation-and-checks.md
Find the cause
- Bisect to the change - With a 100% repro, search history for the commit that introduced the bug, see references/reproduction-and-bisection.md
- Read the callstack and the bytes - Access violations and watch-window values steer the next hypothesis, see references/scientific-debugging.md
- Confirm before fixing - Verify the hypothesis (breakpoint/log) before you commit to a fix direction, see references/scientific-debugging.md
Make bugs catchable
- Prefer prevention by design - Asserts on preconditions, end-of-page allocators, type-safe APIs, and "clean up everything" expose bugs that would otherwise hide, see references/bug-taxonomy.md
- Tame intermittency with determinism - Remove nondeterminism or record/replay so the rare bug reproduces, see references/determinism-and-replay.md
- Instrument allocations and invariants - Tag allocations with file/line, count references, validate at API entry, see references/instrumentation-and-checks.md
What ships with it
9 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 · 44 lines · 120 tokens per session scan A 5e2aac6c2e7e
debugging-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 4d ago), licensed MIT. It adds 120 tokens to every session and 1,121 once invoked, about $0.0005 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 2026-09-08.
Other skills, from other repositories
kastell-research
Read-only Kastell codebase exploration. Use when tracing a bug across files, mapping callsites before refactoring, or exploring unfamiliar subsystems. Runs in isolated context with Explore agent.
System Healthcheck
Run a lightweight, non-destructive system healthcheck — disk usage, memory, CPU load, process count, hostname — and store a structured snapshot in session memory. Use when the user says "run a healthcheck", "check system health", "how's the server doing", "is everything ok", or asks for a status/diagnostics snapshot…
docker-management
Docker container lifecycle management, Dockerfile authoring, and debugging.
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
feedback
Skill "feedback" from Hmbown/Codewhale, covering feedback, when to use, setup, workflow and non-goals.