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 Proxy2021/Enso --skill error_monitorgit clone --depth 1 https://github.com/Proxy2021/EnsoWrote 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/proxy2021/enso/error_monitor)<a href="https://agentmods.dev/skills/proxy2021/enso/error_monitor"><img src="https://agentmods.dev/badge/skills/proxy2021/enso/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/proxy2021/enso/error_monitor"><img src="https://agentmods.dev/badge/skills/proxy2021/enso/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 | $0.00070 | $0.01189 |
| Opus 5.5 | $0.00028 | $0.00476 |
| Sonnet 5.5 | $0.00014 | $0.00238 |
| Haiku 4.5 | $0.00007 | $0.00119 |
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 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Real-time error monitoring dashboard: error summary with severity breakdown, error trends over time, category analysis, recent error feed, fix tracking, system health score, circuit breaker states, error code analysis, recurring error pattern detection, and actionable recommendations. Reads from Enso's action log, error log, circuit breakers, and error rate monitor.
Tool Reference
enso_error_monitor_overview (primary)
Get error monitoring overview: total errors, severity breakdown (critical/error/warning/info), top error categories, and recent errors for a given time window. Use when the user says: 'show error dashboard', 'error overview', 'system errors', 'error monitor', 'how many errors', 'error health'.
Parameters:
hours(number): Time window in hours (1-168, default: 24)
enso_error_monitor_errors
Get recent error entries with optional severity filter. Returns chronological error list with full details including category, message, severity, requestId, and timestamps. Use when the user says: 'show recent errors', 'error list', 'what errors happened', 'show critical errors', 'error log'.
Parameters:
count(number): Number of errors to return (1-200, default: 50)severity(string): Filter by severity: 'all', 'critical', 'error', 'warning', 'info' (default: 'all')
enso_error_monitor_trends
Get error trends over time — hourly error counts bucketed by severity for a given time window. Shows how error rates change over hours. Use when the user says: 'error trends', 'error rate', 'error frequency', 'error timeline', 'when do errors happen'.
Parameters:
hours(number): Time window in hours (1-168, default: 24)
enso_error_monitor_categories
Get error breakdown by category with counts, severity distribution, and last occurrence. Identifies which subsystems produce the most errors. Use when the user says: 'error categories', 'where are errors coming from', 'error sources', 'error breakdown', 'which module has errors'.
Parameters:
hours(number): Time window in hours (1-168, default: 24)
What ships with it
14 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.
- app.json 20 KB
- executors/activity.js 574 B runs code
- executors/alert_status.js 5.9 KB runs code
- executors/categories.js 1.2 KB runs code
- executors/circuit_breakers.js 1.2 KB runs code
- executors/error_codes.js 1.9 KB runs code
- executors/errors.js 575 B runs code
- executors/fixes.js 1.1 KB runs code
- executors/health_check.js 4.0 KB runs code
- executors/overview.js 878 B runs code
- executors/recurring.js 2.0 KB runs code
- executors/tl_report.js 6.1 KB runs code
- executors/trends.js 1.5 KB runs code
- template.jsx 51 KB
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 · 81 lines · 70 tokens per session scan A c1431e6290a2
error_monitor is a skill published in the GitHub repository Proxy2021/Enso (6 stars, last pushed 5mo ago), licensed MIT. It adds 70 tokens to every session and 1,189 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
argent-metro-debugger
Debug a JS runtime via CDP using argent debugger tools. Primary path is React Native via Metro (iOS / Android / Vega); a subset of the tools (debugger-connect, debugger-status, debugger-evaluate, debugger-log-registry) also drive a Chromium (CDP) app's renderer (an Electron app, or any Chromium browser exposing CDP)…
argent-react-native-optimization
Optimizes a React Native app by profiling first to find real bottlenecks, then sweeping for mechanical issues. Entry-point for all performance work. Use when the app feels slow, user asks to optimize, fix re-renders, reduce jank, or improve startup. Delegates to argent-react-native-profiler for measurement.
argent-native-profiler
Native profiling for CPU hotspots, UI hangs, memory issues. iOS via xctrace; Android via Perfetto. Use when diagnosing native-level performance issues.
compose-performance
Use when investigating Jetpack Compose recomposition cost, compiler stability reports, skippability, unstable parameters, frame-rate State reads, cross-phase snapshot back-writing, or @ReadOnlyComposable contracts.
maui-ai-debugging
Legacy DevFlow debug skill. USE FOR: maui-ai-debugging, maui devflow, screenshots, visual tree, Blazor CDP, simulator/emulator debugging. DO NOT USE FOR: setup, desktop automation, AppleScript, host xdotool.
extract-apk
A workflow for finding an Android app on a connected device, exporting its APK, and turning it into searchable decompiled source files. An APK is the installable package used by Android apps.