
Two debugging subagents and three commands that find the root cause of errors, set up error tracking and run multi-agent code reviews.
by wshobson· AI & agentsUnclaimed · Yours? Claim it
4 images
About
A community plugin by Seth Hobson, from his wshobson/agents collection for coding agents. It adds two debugging subagents and three commands that help your agent trace an error back to its root cause, set up error tracking and review code with several specialist reviewers at once. What it adds - debugger: a subagent for errors, test failures and unexpected behaviour. It captures the error and stack trace, isolates where it fails, makes a minimal fix, checks it works and suggests how to prevent it. - error-detective: a subagent that searches logs and code for error patterns and stack traces, correlates errors across services and with deployments, and writes regex patterns and monitoring queries. - /error-debugging:error-analysis: a structured root-cause analysis of an error message, stack trace or log, from classifying it and the five whys through to a fix and prevention steps. - /error-debugging:error-trace: sets up error tracking and monitoring, with a tracking service such as Sentry, structured logging, alerts, error grouping and a dashboard. - /error-debugging:multi-agent-review: coordinates code quality, security, architecture and performance reviewers and merges their findings into one prioritised review. How to install it In Claude Code, run /plugin marketplace add wshobson/agents, then /plugin install error-debugging@claude-code-workflows. The collection also documents setup for Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot and Pi. Good to know - It's instructions for your agent, with no server, account or API key. The agent reads your code and logs, and changes files only as your agent's permissions allow. - It's a community project by Seth Hobson, not an official product of any error-tracking service.
Plugins people install alongside Error Debugging.
Once it’s added
“Find the root cause of this TypeError in checkout.js and fix it.”
“Why is this test failing? Fix it and tell me how to stop it happening again.”
“Search these logs for errors that started after yesterday's deploy.”
“Write a regex that pulls every stack trace out of app.log.”
“Set up Sentry error tracking with alerts for our Node API.”
“Review this pull request with security, performance and architecture reviewers.”
Before you add it
Reads only
Your code, stack traces and log files · Recent code changes, to correlate them with errors
Makes changes · your agent can ask first
Minimal code fixes and debug logging, when you allow edits · Error tracking, structured logging and alert setup in your project
From people who use it
Step by step
Nothing new reaches your agent until a person has looked at it.
Scanned on every change, and again when our rules improve.
Runs on your machine.
Runs on your machine.
/plugin marketplace add wshobson/agents /plugin install error-debugging@claude-code-workflows
Scanned and passed · checked 6 h ago
No reviews yet. Used Error Debugging? Say how it went.
Write a reviewPlugins people install alongside Error Debugging.
ByteDance's local MCP server that lets your agent run any shell command or script on your machine, with your own permissions.
Keeps your agent's plan, findings and progress in markdown files on disk, so long tasks survive /clear, crashes and compaction.
A self-learning skill layer for Claude Code: distills skills from your real sessions, updates them as you work and prunes unused ones.
Nobody has shared how they use Error Debugging yet.
Security scan
Passed
Safe to install in every agent it supports. Claude plugins.