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 airvalona/antigravity-like-claude-code --skill debuggit clone --depth 1 https://github.com/airvalona/antigravity-like-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/airvalona/antigravity-like-claude-code/debug)<a href="https://agentmods.dev/skills/airvalona/antigravity-like-claude-code/debug"><img src="https://agentmods.dev/badge/skills/airvalona/antigravity-like-claude-code/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/airvalona/antigravity-like-claude-code/debug"><img src="https://agentmods.dev/badge/skills/airvalona/antigravity-like-claude-code/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 | $0.00064 | $0.00444 |
| Opus 5.5 | $0.00026 | $0.00178 |
| Sonnet 5.5 | $0.00013 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00044 |
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 2mo 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 — Structured Debugging Workflow
Port of Claude Code's /debug.
Arguments
/debug <description or error>— start debugging that specific issue
Steps
-
Reproduce first. Before theorizing, try to actually trigger the bug (run the failing command/test, hit the failing code path). If it can't be reproduced with what's available, say so and ask for the missing piece (repro steps, input data, environment detail) rather than guessing.
-
Isolate. Narrow down from "something is wrong" to the specific function/line/condition:
- Read the stack trace bottom-up if one exists
- Add temporary logging/print statements at the narrowing points if needed, and remove them once the cause is found
- Check recent changes to the affected area first (
git log -p <file>/git blame) since regressions are more likely near recent edits
-
Form a hypothesis for the root cause before writing any fix. State it explicitly: "This happens because X does Y when Z."
-
Verify the hypothesis — confirm it actually explains the observed behavior (e.g. by triggering the exact condition and seeing the exact failure) before proposing a fix. Don't patch symptoms without confirming the cause.
-
Propose and apply the fix, then re-run the original repro to confirm it's actually resolved — not just that the code compiles/runs.
-
Clean up any temporary debug logging added during the process unless the user wants it kept.
Notes
Resist the urge to fix multiple unrelated things noticed along the way — note them for the user instead of scope-creeping the debug session.
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.
- 2mo ago First seen · 45 lines · 64 tokens per session scan A 9af8916ab0a8
debug is a skill published in the GitHub repository airvalona/antigravity-like-claude-code (2 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 444 once invoked, about $0.0003 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
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…
ci-fixer
CI failures - read error, minimal fix, verify.
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.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…