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 rexleimo/aios --skill debug-hubgit clone --depth 1 https://github.com/rexleimo/aiosWrote 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/rexleimo/aios/debug-hub)<a href="https://agentmods.dev/skills/rexleimo/aios/debug-hub"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/debug-hub/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/rexleimo/aios/debug-hub"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/debug-hub.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 26 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Server-Side Request Forgery · line 26 Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
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 | $0.00066 | $0.01252 |
| Opus 5.5 | $0.00026 | $0.00501 |
| Sonnet 5.5 | $0.00013 | $0.00250 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade B, and why
debug-hub scanned grade B with 1 finding 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const __dh=async(m,d)=>{try{await fetch('http://127.0.0.1:39200/api/logs/single',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({id:crypto.randomUUID(),timestamp:Date.now(),level:'debug',m How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug-Hub
Working directory: any (scripts run from project root by convention)
Evidence-first debugging: inject zero-dependency log calls, collect via debug-hub HTTP API, analyze through MCP tools, strip all injected code when done.
Inline Reporter
Inject once at the top of the first file you modify. Node 18+ / modern browsers, zero npm deps:
const __dh=async(m,d)=>{try{await fetch('http://127.0.0.1:39200/api/logs/single',{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify({id:crypto.randomUUID(),timestamp:Date.now(),level:'debug',message:m,data:d,sdk:{name:'dh',version:'1',runtime:'node'}})})}catch{}}
Python target? Use the debug skill instead — it bundles a Python collector that sends to the same debug-hub API. This applies regardless of whether debug_hub MCP is available; the __dh helper is JavaScript-only.
Marker Convention
Every injected debug line carries DH:<sessionId>. Cleanup strips any line containing this string.
__dh('DH:sess-abc user state', {user});
__dh('DH:sess-abc payment duration', {ms: Date.now()-t0});
MCP Tools
| Tool | What it does |
|---|---|
debug_hub.start_session { objective } |
Start session, returns sessionId |
debug_hub.instrument { sessionId, files: [{path, lineCount}] } |
Track files with injected debug code |
debug_hub.search_logs { keyword, level, since, traceId } |
Query collected runtime logs |
debug_hub.get_stats |
Error counts, level breakdown |
debug_hub.cleanup_instruments { sessionId, dryRun?, workspace? } |
Remove all injected debug lines |
Other tools: list_traces, get_trace, compact_context, health — see MCP tool list.
When NOT to Use This Skill
Debug-hub is for runtime bugs where you can reproduce the issue and need to observe variable state, timing, or control flow at runtime. Do NOT use debug-hub for:
- Compile-time / type errors: TypeScript type errors, syntax errors, lint failures — read the error message and fix the code directly. No runtime injection needed.
- CI/CD platform differences: Path separators, case sensitivity, missing dependencies in CI — inspect CI logs and config files, not runtime state.
- Configuration / matching rule problems: Skill trigger conflicts, wrong config values, permission misconfig — read and fix the config files directly.
- Non-JavaScript environments: The
__dhhelper requires Node 18+ or browserfetch. For Python, use thedebugskill (bundled Python collector) instead. For other languages, use platform-native debug tools.
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 Changed a9b0449e9aed
- 1mo ago Changed f4777af3e459
- 1mo ago Changed 383263038325
- 1mo ago First seen · 88 lines · 66 tokens per session scan B 794d003e83ec
debug-hub is a skill published in the GitHub repository rexleimo/aios (61 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 1,252 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
surf
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
debug
Use when something is broken — a failing or flaky test, crash, wrong result or regression — and the root cause must be reproduced and proven before any fix. On-demand; callable mid-implement. NOT a feature to spec or build (that is specify/implement), NOT the lint/test gate (that is verify), NOT adversarial diff…
kirby-debugging-and-tracing
Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.
lastlight-debug
Debug a running Last Light instance over its admin API with the lastlight CLI — no SSH. Use when the user wants to "look at / debug a failed or stuck workflow", "why didn't the bot do X", "check a bad agent run / phase error on ", "tail a session", "search the logs", "read the server/docker logs", "list/trigger a…
acrawl-mcp
Drive the acrawl MCP server for browser automation, web scraping, and live DevTools inspection — navigating pages, clicking, filling forms, extracting structured data, and auditing network traffic, console errors, cookies, storage, performance, accessibility, and code coverage. Use this whenever a task touches acrawl…