Initial commit

This commit is contained in:
Zhongwei Li
2025-11-29 18:14:36 +08:00
commit df3f963aea
6 changed files with 645 additions and 0 deletions

View File

@@ -0,0 +1,13 @@
{
"name": "catalyst-debugging",
"description": "Production error monitoring with Sentry MCP integration. Enable when debugging errors, analyzing stack traces, and investigating incidents. ~20k context tokens when enabled.",
"version": "1.0.2",
"author": {
"name": "Coalesce Labs",
"email": "hello@coalesce.dev",
"url": "https://github.com/coalesce-labs"
},
"commands": [
"./commands"
]
}

3
README.md Normal file
View File

@@ -0,0 +1,3 @@
# catalyst-debugging
Production error monitoring with Sentry MCP integration. Enable when debugging errors, analyzing stack traces, and investigating incidents. ~20k context tokens when enabled.

View File

@@ -0,0 +1,200 @@
---
description: Debug production errors using Sentry error tracking and analysis
category: debugging
tools: Task, TodoWrite
model: inherit
version: 1.0.0
---
# Debug Production Error
Investigate production errors using Sentry's error tracking, stack traces, and context.
## Prerequisites
- Sentry MCP must be enabled (this plugin should be enabled)
- Environment variables configured:
- `SENTRY_AUTH_TOKEN`
- `SENTRY_ORG`
- `SENTRY_PROJECT`
## Usage
```bash
/catalyst-dev:debug-production-error <error-description-or-id>
Examples:
/catalyst-dev:debug-production-error "TypeError in checkout flow"
/catalyst-dev:debug-production-error "ISSUE-123"
/catalyst-dev:debug-production-error "errors from last deployment"
/catalyst-dev:debug-production-error "unhandled exceptions this week"
```
## What This Command Does
Uses Sentry MCP tools to:
1. Search for relevant errors
2. Retrieve stack traces and context
3. Analyze error patterns and frequency
4. Identify affected users and environments
5. Suggest root causes and fixes
## Available Sentry Capabilities
When this plugin is enabled, you have access to ~19 Sentry tools:
**Error Search & Analysis**:
- Search issues by query
- Filter by status, assignment, date
- View error trends and patterns
- Identify new vs recurring errors
**Stack Trace Analysis**:
- Full stack traces with source context
- Source map resolution
- Frame-by-frame analysis
- Variable inspection
**Context & Metadata**:
- User context (who was affected)
- Environment details
- Release/deployment information
- Breadcrumb trail (user actions leading to error)
**Issue Management**:
- Update issue status
- Assign to team members
- Link to tickets/PRs
- Add comments and notes
**Root Cause Analysis** (Seer AI):
- AI-powered root cause identification
- Code-level explanations
- Specific fix recommendations
- Related error patterns
## Example Debugging Sessions
### Investigate Specific Error
```bash
/catalyst-dev:debug-production-error "Show me details for MYAPP-456 including stack trace and user context"
```
### Search by Error Type
```bash
/catalyst-dev:debug-production-error "Find all TypeError exceptions in the last 24 hours"
```
### Deployment Issues
```bash
/catalyst-dev:debug-production-error "What new errors appeared after release v2.3.0?"
```
### High-Impact Errors
```bash
/catalyst-dev:debug-production-error "Show unresolved errors affecting more than 100 users"
```
## Output Format
Analysis typically includes:
**Error Overview**:
- Error message and type
- Frequency and trend
- First seen / last seen
- Number of users affected
**Stack Trace**:
- Full call stack
- Source code context
- File paths and line numbers
- Variable values (if available)
**User Context**:
- User ID and properties
- Browser/device information
- URL and user actions (breadcrumbs)
**Root Cause** (when Seer analysis available):
- Likely cause explanation
- Relevant code snippets
- Specific fix recommendations
- Related issues
## Advanced Queries
### Filter by Environment
```bash
/catalyst-dev:debug-production-error "production errors in payment service"
```
### Time-Based Analysis
```bash
/catalyst-dev:debug-production-error "spike in errors between 2pm-3pm today"
```
### User-Specific
```bash
/catalyst-dev:debug-production-error "errors for user@example.com"
```
### Integration with Analytics
If you have both plugins enabled:
```bash
# Enable both
/plugin enable catalyst-debugging
/plugin enable catalyst-analytics
# Combined analysis
> "Show me errors in checkout AND how many users abandoned checkout today"
```
## Workflow Integration
### With Issue Tracking
After identifying root cause:
```bash
> "Create a GitHub issue for this error with the stack trace and fix recommendations"
```
### With Code Changes
After finding the bug:
```bash
/create-plan "Fix the TypeError in checkout.ts based on Sentry analysis"
```
## Context Cost
**This plugin adds ~20,670 tokens** to your context window. Disable when debugging is complete:
```bash
/plugin disable catalyst-debugging
```
---
**See also**: `/error-impact-analysis`, `/trace-analysis`

View File

@@ -0,0 +1,175 @@
---
description: Analyze the impact and scope of production errors
category: debugging
tools: Task, TodoWrite
model: inherit
version: 1.0.0
---
# Error Impact Analysis
Assess the severity, reach, and business impact of production errors.
## Usage
```bash
/error-impact-analysis <error-or-timeframe>
Examples:
/error-impact-analysis "ISSUE-789"
/error-impact-analysis "checkout errors last 7 days"
/error-impact-analysis "critical errors this week"
/error-impact-analysis "impact of recent deployment"
```
## What This Analyzes
### Quantitative Impact
- Number of occurrences
- Number of users affected
- Error rate over time
- Affected environments/releases
### Qualitative Impact
- Error severity (critical, high, medium, low)
- Affected user workflows
- Business function impact (checkout, signup, etc.)
- User experience degradation
### Trend Analysis
- Is it increasing or decreasing?
- When did it start?
- Related to specific release?
- Correlation with traffic/usage
## Example Analyses
### Single Issue Impact
```bash
/error-impact-analysis "What's the impact of MYAPP-123? How many users, revenue impact?"
```
### Category Impact
```bash
/error-impact-analysis "Overall impact of all payment-related errors this month"
```
### Release Health
```bash
/error-impact-analysis "Error impact comparison: current release vs previous release"
```
### Critical Errors
```bash
/error-impact-analysis "Show all critical errors and their combined user impact"
```
## Output Format
Analysis includes:
**Scope**:
- Total occurrences
- Unique users affected
- Affected countries/regions
- Browser/device breakdown
**Severity Assessment**:
- Error frequency
- User impact score
- Business criticality
- Blocking vs non-blocking
**Trends**:
- Occurrence over time (chart/data)
- Peak times
- Growth rate
- Comparison to baseline
**Business Impact**:
- Affected revenue-generating flows
- Customer support tickets related
- SLA implications
- Reputation risk
**Prioritization**:
- Recommendation on urgency
- Comparison with other errors
- ROI of fixing
## Integration with Analytics
Enable both plugins for deeper impact analysis:
```bash
/plugin enable catalyst-debugging
/plugin enable catalyst-analytics
/error-impact-analysis "How many users who hit error X churned vs users who didn't?"
```
This combines:
- Sentry error data (who hit the error)
- PostHog behavior data (did they churn)
## Incident Response Workflow
### 1. Assess Impact
```bash
/error-impact-analysis "new spike in errors at 3pm"
```
### 2. Determine Severity
Based on output:
- **Critical**: >1000 users, blocking checkout/signup
- **High**: >100 users, degraded experience
- **Medium**: <100 users, minor inconvenience
- **Low**: <10 users, edge case
### 3. Prioritize Response
```bash
> "Based on this impact, should we rollback or hotfix?"
```
### 4. Track Resolution
```bash
> "After fix, compare error rates before and after"
```
## Tips for Impact Analysis
1. **Consider timeframe** - "last hour" for incidents, "last week" for trends
2. **Segment users** - Impact on paid vs free users may differ
3. **Check related errors** - One root cause may affect multiple error types
4. **Compare releases** - Pinpoint when impact started
5. **Business context** - Impact during peak hours is more severe
## Context Cost
Plugin uses ~20k tokens. Disable after analysis:
```bash
/plugin disable catalyst-debugging
```
---
**See also**: `/debug-production-error`, `/trace-analysis`

201
commands/trace_analysis.md Normal file
View File

@@ -0,0 +1,201 @@
---
description: Analyze distributed traces and performance issues with Sentry
category: debugging
tools: Task, TodoWrite
model: inherit
version: 1.0.0
---
# Trace Analysis
Investigate distributed traces, transaction performance, and slow requests using Sentry.
## Usage
```bash
/trace-analysis <trace-id-or-query>
Examples:
/trace-analysis "a4d1aae7216b47ff8117cf4e09ce9d0a"
/trace-analysis "slow API requests to /checkout"
/trace-analysis "traces with >5 second response time"
/trace-analysis "performance issues in payment service"
```
## What This Analyzes
### Trace Components
- Transaction spans (API calls, DB queries, external services)
- Timing breakdown per span
- Parent-child span relationships
- Span operations and descriptions
### Performance Metrics
- Total transaction duration
- Time spent in each service
- Database query performance
- External API latency
- Network overhead
### Bottleneck Identification
- Slowest spans in trace
- Sequential vs parallel operations
- N+1 query detection
- Inefficient operations
## Example Analyses
### Specific Trace Investigation
```bash
/trace-analysis "Analyze trace abc123def456: where's the bottleneck?"
```
### Performance Pattern
```bash
/trace-analysis "Why are checkout API requests slow today?"
```
### Service Comparison
```bash
/trace-analysis "Compare performance of payment service vs order service"
```
### Database Performance
```bash
/trace-analysis "Find traces with slow database queries in user service"
```
## Output Format
Analysis includes:
**Trace Overview**:
- Transaction name and operation
- Total duration
- Timestamp
- Environment and release
**Span Breakdown**:
```
Transaction: POST /api/checkout (2.4s)
├─ Authentication (45ms)
├─ Database Query: SELECT users (120ms)
├─ External API: Payment Gateway (1.8s) ⚠️ SLOW
├─ Database Query: INSERT orders (230ms)
└─ Email Service (180ms)
```
**Performance Insights**:
- Slowest operations
- Time distribution (pie chart/percentages)
- Parallel vs sequential execution
- Optimization opportunities
**Recommendations**:
- Cache frequently accessed data
- Optimize specific queries
- Implement async processing
- Add timeouts for external calls
## Advanced Analysis
### Multi-Trace Patterns
```bash
/trace-analysis "Find common bottlenecks across all slow checkout traces today"
```
### Service Dependencies
```bash
/trace-analysis "Map service call chain for failed transactions"
```
### Error Correlation
```bash
/trace-analysis "Traces that resulted in errors: what went wrong before?"
```
## Integration Opportunities
### With Error Debugging
```bash
# Enable debugging plugin (if not already)
/plugin enable catalyst-debugging
# Combine trace and error analysis
> "Show me the trace for the transaction that caused error ISSUE-456"
```
### With Code Changes
After identifying bottleneck:
```bash
/create-plan "Optimize the slow payment gateway call identified in trace analysis"
```
## Performance Optimization Workflow
### 1. Identify Slow Transactions
```bash
/trace-analysis "transactions with >2s response time in last hour"
```
### 2. Analyze Bottlenecks
```bash
> "Drill into the slowest trace: which span is the problem?"
```
### 3. Root Cause
```bash
> "Why is the database query taking 800ms?"
```
### 4. Implement Fix
```bash
/create-plan "Add database index for user lookups based on trace analysis"
```
### 5. Verify Improvement
```bash
> "After deploy, compare trace durations before and after"
```
## Tips
1. **Start with aggregates** - "slow checkouts" before diving into specific traces
2. **Look for patterns** - One slow trace might be an outlier, many indicate systemic issue
3. **Check external dependencies** - Third-party APIs often cause slowdowns
4. **Consider concurrency** - Sequential operations that could be parallel
5. **Database queries** - N+1 queries, missing indexes, inefficient queries
## Context Cost
Plugin uses ~20k tokens. Disable after analysis:
```bash
/plugin disable catalyst-debugging
```
---
**See also**: `/debug-production-error`, `/error-impact-analysis`

53
plugin.lock.json Normal file
View File

@@ -0,0 +1,53 @@
{
"$schema": "internal://schemas/plugin.lock.v1.json",
"pluginId": "gh:coalesce-labs/catalyst:plugins/debugging",
"normalized": {
"repo": null,
"ref": "refs/tags/v20251128.0",
"commit": "efa5bfd91ef05a51060939423de8d6b0bd4bb609",
"treeHash": "e9399760b602fe5ccfb545df9be0316d855224dd02128200a89aa1247a82141e",
"generatedAt": "2025-11-28T10:15:41.903039Z",
"toolVersion": "publish_plugins.py@0.2.0"
},
"origin": {
"remote": "git@github.com:zhongweili/42plugin-data.git",
"branch": "master",
"commit": "aa1497ed0949fd50e99e70d6324a29c5b34f9390",
"repoRoot": "/Users/zhongweili/projects/openmind/42plugin-data"
},
"manifest": {
"name": "catalyst-debugging",
"description": "Production error monitoring with Sentry MCP integration. Enable when debugging errors, analyzing stack traces, and investigating incidents. ~20k context tokens when enabled.",
"version": "1.0.2"
},
"content": {
"files": [
{
"path": "README.md",
"sha256": "31a4db05cc0683529f8eb06740186fa5126bae6050fa620afcd5d69adb5345ea"
},
{
"path": ".claude-plugin/plugin.json",
"sha256": "54ab5b3865b263b732466dabf95aa144ccb89a62189312b7cb9bb83643b57f0b"
},
{
"path": "commands/error_impact_analysis.md",
"sha256": "5a9d7468f7e9b7c8e0eceb375330db6867f40f51874af1859f1352efb15881c2"
},
{
"path": "commands/trace_analysis.md",
"sha256": "6785162df87b9271a7d709b42b6265b218da4a07a8fec8d6cf17ab997ec6430a"
},
{
"path": "commands/debug_production_error.md",
"sha256": "6bb6d26b9d0490e692ebec2209ddfcc6de9ef7e6b49b1882e9d762e599ad9b06"
}
],
"dirSha256": "e9399760b602fe5ccfb545df9be0316d855224dd02128200a89aa1247a82141e"
},
"security": {
"scannedAt": null,
"scannerVersion": null,
"flags": []
}
}