Errors

This is a pattern recognition system for Claude Code errors that logs failures to JSONL, builds a rule database from repeated issues, and warns you before running commands that previously failed. It hooks into tool execution to capture connection errors, database failures, and hook timeouts, then generates fix suggestions based on historical patterns. The batch analyzer runs over your last 24 hours or 7 days of errors to surface what keeps breaking. Most useful when you're hitting the same issues repeatedly or want to understand why certain operations fail. The hook integration since CC 2.1.98 makes stderr visible directly in transcripts, which is honestly more helpful than the pattern matching for one-off debugging.

skills.sh installs: 223
GitHub stars: 301
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add yonatangross/orchestkit --skill errors --agent claude-code

Installs into .claude/skills of the current project.

Files

Error Pattern Analysis

Analyze errors captured from Claude Code sessions to identify patterns and get actionable insights.

Quick Start

/errors              # Batch analysis of historical error patterns
/debug               # CC 2.1.30 real-time debug for current session

When to Use Which

Command	Purpose	Scope
`/errors`	Batch analysis of error patterns (last 24h/7d)	Historical patterns
`/debug`	Real-time debug of current session state	Current session
`fix-issue`	Full RCA workflow for specific bug	Single issue

CC 2.1.169+: for errors that survive /clear and restarts, claude --safe-mode boots with every customization disabled (CLAUDE.md/plugins/skills/hooks/MCP) — the one-step test that separates "ork/hook/MCP bug" from "CC bug" before deeper analysis.

Quick Analysis

# Run batch analysis on last 24h of errors
python .claude/scripts/analyze_errors.py

# Analyze last 7 days
python .claude/scripts/analyze_errors.py --days 7

# Generate markdown report
python .claude/scripts/analyze_errors.py --report