Generated banner for Convex Monitor
Generated logo for Convex Monitor

Convex Monitor

ConvexOfficialPublished by Convex

  • Skill
  • Workflow
  • Software development
  • Apache-2.0
  • No issues found

From the author

Watch for the next dev/prod error or request in a Convex app and react to it.
— the description by Convex

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The convex-monitor skill provides a structured approach to observing and responding to events within a Convex application. It is designed to detect errors or feature requests by monitoring local logs, deployment subscriptions, and production error data. The skill utilizes a blocking mechanism to wait for events, falling back to a polling loop when necessary, ensuring consistent event handling across different environments.

What it does

  • Monitors for development and production errors or feature requests.
  • Uses a blocking wait mechanism to detect events without constant polling.
  • Supports a fallback polling loop for environments where blocking is not supported.
  • Standardizes event handling through a fixed and versioned event schema.
  • Facilitates triage and remediation workflows for identified errors.

When to use it

  • When you need to automate responses to errors in your Convex development or production environment.
  • When you want to integrate feature request tracking directly into your development workflow.
  • When working with Sentinel to triage production errors.
  • When you require a consistent event contract across different deployment environments.

Advantages

  • Reduces manual monitoring by automating event detection.
  • Provides a unified interface for handling both local and production-level issues.
  • Ensures consistent behavior regardless of the underlying monitoring mechanism.
  • Simplifies the triage and fix process for application errors.

Usage examples

“Monitor my project for the next error.”
The agent initiates a wait_for_event call to listen for the next convex_error or prod_error event, allowing it to trigger a fix or triage process once an event occurs.
“Check for new feature requests in the app.”
The agent uses the monitor to watch for feature_request events, enabling it to notify the team or begin planning the implementation.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/convex/convex-monitor/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip convex-monitor.zip -d .agents/skills

Documentation by Convex

<!-- GENERATED from convex-agents content/capabilities/monitor.json — do not edit by hand. -->

Watch for the next thing to react to

Block on the next typed event instead of polling. Races local error logs, deployment subscriptions, and Sentinel prod-error rows; returns the first to fire (or a quiet heartbeat).

Workflow

  1. Call wait_for_event with {project_dir, event_kinds, timeout_ms}.

  2. On kind=convex_error/next_error: decode and fix it. On kind=prod_error: triage (see sentinel) and fix. On kind=feature_request: build it. On kind=quiet: loop.

  3. Where a harness has no blocking MCP (e.g. Copilot cloud), the pack runs a poll loop with the SAME event contract — same behavior, different mechanism.

Rules

  • Prefer the blocking tool; fall back to a poll loop only where blocking MCP is weak.

  • The event schema is fixed and versioned — the same trigger yields the same typed event.

  • Prod events (kind=prod_error) require a deployed cloud app plus Sentinel.

Files

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Convex
Publisher
Convex (Official)
Source
convex/agent-skills · skills/convex-monitor · commit f60629d
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Convex or Convex.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download convex-monitor.zip