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 viknesh20-20/claude-code-tool-kit --skill error-monitorgit clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kitWrote 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/viknesh20-20/claude-code-tool-kit/error-monitor)<a href="https://agentmods.dev/skills/viknesh20-20/claude-code-tool-kit/error-monitor"><img src="https://agentmods.dev/badge/skills/viknesh20-20/claude-code-tool-kit/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/viknesh20-20/claude-code-tool-kit/error-monitor"><img src="https://agentmods.dev/badge/skills/viknesh20-20/claude-code-tool-kit/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 | $0.00039 | $0.00709 |
| Opus 5 | $0.00019 | $0.00354 |
| Sonnet 5 | $0.00008 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
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 10d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Error Monitoring Setup
Detect Framework
!ls package.json requirements.txt go.mod Cargo.toml *.csproj 2>/dev/null
!cat package.json 2>/dev/null | grep -E "react|next|express|fastify|koa|nest|vue|angular|svelte" | head -5
!cat requirements.txt pyproject.toml 2>/dev/null | grep -iE "django|flask|fastapi|starlette" 2>/dev/null | head -5
Existing Error Tracking
!grep -r "sentry\|bugsnag\|rollbar\|airbrake\|errortracking\|newrelic" --include="*.json" --include="*.ts" --include="*.js" --include="*.py" -l 2>/dev/null | head -5
Setup Process
Step 1: Choose Provider
Based on the project stack:
- Sentry: Best overall, supports all major languages
- Bugsnag: Good for mobile and frontend
- Custom: For projects that can't use third-party services
Step 2: Framework-Specific Integration
React/Next.js:
- Error Boundary component wrapping the app
Sentry.init()in entry point- Source map upload in build step
- Client-side error capturing
Express/Fastify/Koa:
- Error handling middleware (must be last middleware)
- Request context enrichment (user, request ID)
- Unhandled rejection handler
FastAPI/Django/Flask:
- Middleware for request error capture
- Custom exception handlers
- Background task error tracking
Go:
- Panic recovery middleware
- Error wrapping with context
- Goroutine error capture
Step 3: Configuration
Generate configuration file with:
- DSN/API key reference (from environment variable, never hardcoded)
- Environment detection (development, staging, production)
- Release version tracking
- Sample rate configuration
- Sensitive data scrubbing rules (strip passwords, tokens, PII)
Step 4: Custom Error Classes
Generate project-specific error types:
AppErrorbase class with code, message, contextValidationErrorfor input validation failuresNotFoundErrorfor missing resourcesAuthErrorfor authentication/authorization failuresExternalServiceErrorfor third-party failures
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.
- 10d ago First seen · 79 lines · 39 tokens per session scan A b5ab8f978329
error-monitor is a skill published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 709 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 2026-08-31.
Other skills, from other repositories
rust-check
Run cargo check on the current Rust project to find compile errors.
debug
Reproduce, minimize, localize, identify root cause, and distinguish diagnosis from an authorized fix. Prefer root-cause over symptom patches.
langsmith-tracing
LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.
postmortem
Auto-generates a structured postmortem from a completed campaign. Reads the campaign file, telemetry logs, and feature ledger. Produces a documented analysis of what broke, what the safety systems caught, and what patterns emerged. Can also be invoked manually for any incident.
systematic-debugging
4-phase root cause analysis: observe, hypothesize, verify, fix. Enforces investigation before any code changes. Emergency stop after 2 failed fixes. Prevents shotgun debugging and fix cascades.
debugging-patterns
Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.