coalesce-labs/debug-production-error
plugins/debugging/skills/debug-production-error/SKILL.md
Debug production errors using Sentry MCP tools. Searches issues, analyzes stack traces, identifies root causes, and suggests fixes. Use when the user mentions a Sentry error, production exception, stack trace, error monitoring, crash report, or unhandled exception.
$ install --global
skillsauthnpx skillsauth add coalesce-labs/catalyst debug-production-errorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 21, 2026, 2:50 AM169.8s1 file scanned
SKILL.md
- name:
- debug-production-error
- description:
- Debug production errors using Sentry MCP tools. Searches issues, analyzes stack traces, identifies root causes, and suggests fixes. Use when the user mentions a Sentry error, production exception, stack trace, error monitoring, crash report, or unhandled exception.
- disable-model-invocation:
- false
- allowed-tools:
- Task, TodoWrite
- 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_TOKENSENTRY_ORGSENTRY_PROJECT
Usage
/debug-production-error <error-description-or-id>
Examples:
/debug-production-error "TypeError in checkout flow"
/debug-production-error "ISSUE-123"
/debug-production-error "errors from last deployment"
/debug-production-error "unhandled exceptions this week"
What This Command Does
Uses Sentry MCP tools to:
- Search for relevant errors
- Retrieve stack traces and context
- Analyze error patterns and frequency
- Identify affected users and environments
- 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
/debug-production-error "Show me details for MYAPP-456 including stack trace and user context"
Search by Error Type
/debug-production-error "Find all TypeError exceptions in the last 24 hours"
Deployment Issues
/debug-production-error "What new errors appeared after release v2.3.0?"
High-Impact Errors
/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
/debug-production-error "production errors in payment service"
Time-Based Analysis
/debug-production-error "spike in errors between 2pm-3pm today"
User-Specific
/debug-production-error "errors for [email protected]"
Integration with Analytics
If you have both plugins enabled:
# 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:
> "Create a GitHub issue for this error with the stack trace and fix recommendations"
With Code Changes
After finding the bug:
/catalyst-dev: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:
/plugin disable catalyst-debugging
See also: /catalyst-debugging:error-impact-analysis, /catalyst-debugging:trace-analysis
Related Skills
coalesce-labs/migrate-dual-harness
development
VerifiedTrustedCommunity
Migrate a single-harness repo to the dual-harness layout so both Claude Code and Codex load the same instructions and skills — AGENTS.md as the portable canonical doc, a thin CLAUDE.md `@AGENTS.md` bridge, and a `.agents/skills` dir with a `.claude/skills` symlink onto it. Use when asked to migrate to dual-harness, make this repo work in both Claude and Codex, or for agent metadata cleanup.
17SKILL.mdUpdated Jul 27, 2026
coalesce-labs/recovery-pass
tools
VerifiedTrustedCommunity
Goal-driven senior-engineer pipeline-unstick sweep (CTL-1176 rung 3). Given the stuck/failed/needs-human set (or ONE ticket handed by the recovery router), its GOAL is to get the pipeline MOVING again — not to fix one ticket's review findings (that is phase-remediate). It runs AFTER the eyes (diagnostician evidence) and the hands (deterministic unstuck-sweep seams) have already tried, and it CONSUMES their output from a recovery-pass.json brief rather than re-diagnosing or redoing their narrow work. It acts like a senior engineer with full tool access — it resolves merge conflicts, rebases, force-pushes, merges green PRs, and re-dispatches stalled phases AUTONOMOUSLY — and escalates to the operator ONLY for a genuine value judgment / something that degrades other functionality / a real cost-benefit trade-off / a serious architecture change / an ADR conflict. On escalation it AUTHORS the operator inbox row + the push notification (executive-voiced). Dispatched as a `claude --bg` job by phase-agent-dispatch via slash command, AND invocable bare by the operator as a sweep — hence `user-invocable: true`. Ships behind CATALYST_RECOVERY_PASS (off by default — no live behavior change until shadow/enforce).
17SKILL.mdUpdated Jun 18, 2026
coalesce-labs/setup-catalyst
tools
VerifiedTrustedCommunity
Diagnose and fix Catalyst setup issues. Validates tools, database, config, OTel, direnv, and thoughts. Automatically fixes what it can — creates directories, initializes the database, sets WAL mode, runs migrations. Use for new installs, upgrades, or when something isn't working.
17SKILL.mdUpdated Jun 7, 2026
coalesce-labs/plugins/dev/skills/phase-triage
tools
VerifiedTrustedCommunity
--- name: phase-triage description: Phase agent that triages a Linear ticket — expands acronyms, classifies (feature/bug/docs/refactor/chore), identifies genuine blockers (a semantic second-pass over the backlog — NOT a prose scrape; CTL-838), estimates scope, writes triage.json, and posts a triage analysis comment to Linear. Triage completion is signaled by that comment plus the local triage.json — there is no `triaged` label. Emits phase.triage.complete.<TICKET> on success and phase.triage.fai
17SKILL.mdUpdated May 18, 2026