Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/JansenAnalytics/claudexnpx agentmods add skills/jansenanalytics/claudex/error-monitorWrote 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/jansenanalytics/claudex/error-monitor)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/error-monitor"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/error-monitor/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/jansenanalytics/claudex/error-monitor"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/error-monitor.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 | $0.00035 | $0.00790 |
| Opus 5 | $0.00017 | $0.00395 |
| Sonnet 5 | $0.00007 | $0.00158 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
error-monitor 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 7d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
error-monitor
Monitor application logs and stderr in real-time for errors, crashes, and exceptions. Auto-capture stack traces, alert on new error patterns, track error rates.
When to Use
- Running dev servers and watching for errors
- Monitoring background services
- Catching runtime exceptions during testing
- Tracking error frequency over time
- Generating crash reports when processes die
Scripts
watch-errors.sh
Real-time log watcher that filters for error patterns and captures stack traces.
# Watch specific log files
bash scripts/watch-errors.sh --files "app.log,error.log"
# Pipe mode — capture stderr from a process
node server.js 2>&1 | bash scripts/watch-errors.sh
# With sound alert on each error
bash scripts/watch-errors.sh --files "app.log" --sound
# Execute a command on each error (e.g., notify)
bash scripts/watch-errors.sh --files "app.log" --exec "echo 'Error found!' >> alerts.txt"
# Custom output file
bash scripts/watch-errors.sh --files "app.log" --output /tmp/my-errors.jsonl
Error patterns detected: ERROR, FATAL, Exception, Traceback, panic, SIGTERM, SIGSEGV, SIGABRT, "unhandled", "uncaught", "segmentation fault", "core dumped", "out of memory", "killed"
Output format: JSONL file errors-YYYY-MM-DD.jsonl with fields:
timestamp— ISO 8601source— file or "stdin"level— ERROR, FATAL, EXCEPTION, CRASHmessage— the error linestack— captured stack trace (if multi-line)pattern— which pattern matched
error-rate.py
Analyze error frequency from JSONL files produced by watch-errors.
# Analyze today's errors
python3 scripts/error-rate.py errors-2026-03-07.jsonl
# Analyze multiple files
python3 scripts/error-rate.py errors-*.jsonl
# Output CSV for charting
python3 scripts/error-rate.py errors-*.jsonl --csv error-rates.csv
# Group by minute instead of hour
python3 scripts/error-rate.py errors-*.jsonl --interval minute
Reports: errors per interval, trend direction, busiest period, spike detection (>2σ from mean).
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.
- 7d ago First seen · 106 lines · 35 tokens per session scan A de7fb46e9aad
error-monitor is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 790 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
windbg-doctor
Check that this machine can actually debug - MCP connection reachable, debugger present, symbols configured - and explain how to fix whatever is missing. Use when mcp-windbg tools fail, when a session will not open, or before a first debugging session.
debug-remote
Attach to a running Windows process through a WinDbg debug server and inspect it live. Use when the user wants to debug a process on another machine, or one already under a .server session, rather than a crash dump.
analyze-dump
Triage a Windows crash dump - identify the exception, the faulting frame, and what to look at next. Use when the user points at a .dmp file or asks why a Windows process crashed.
kernel-debug
Attach to a live Windows kernel target over KDNET, a named pipe, or serial and drive it. Use when the user wants to debug a kernel, a driver, or a bugchecking VM.
self-ops
Runtime self-diagnosis knowledge: database layout, observability APIs, timeout hierarchy, restart procedure, failure replay. Use when the user asks to debug this runtime itself — inspect its database, traces, prompt snapshots, timeouts, service health, or configuration.
m4-setup
Diagnose and repair common M4 environment, dataset, skill installation, backend, and vitrine setup problems. Use when M4 tools, datasets, skills, or visualization are missing or broken.