By tyroneross
Coding Debugger for coding agents with debugging memory, verdict-based retrieval, pattern extraction, root-cause workflows, and parallel domain assessment.
Run parallel domain assessment for complex debugging symptoms
Main Coding Debugger entry. Dispatches to a subcommand based on your request, or lists options if unclear. Use `coding-debugger:<subcommand>` to target a specific action directly.
Deep iterative debugging: investigate root cause with causal tree analysis, fix, verify, score, critique — up to 5 iterations
Load full details for a specific Coding Debugger incident or pattern ID.
Scan recent sessions for debugging incidents
Use this agent when the debugging symptom involves API endpoints, REST/GraphQL errors, request/response issues, authentication, rate limiting, or server-side route handlers. Examples - "500 error", "endpoint not found", "auth failed", "CORS error".
Use this agent when debugging requires multi-domain analysis, when the symptom is unclear about which domain is affected, or when you need to coordinate parallel assessments across database, frontend, API, and performance domains.
Use this agent when the debugging symptom involves database issues, queries, migrations, schema problems, Prisma errors, PostgreSQL, connection pooling, or data integrity. Examples - "slow query", "migration failed", "constraint error", "Prisma error", "connection timeout".
Use this agent to pressure-test a proposed fix before declaring a bug resolved. Challenges whether the fix addresses the root cause or just a symptom, checks for potential regressions, and verifies evidence exists for the claimed fix. Run after a fix is implemented but before declaring it done.
Use this agent when the debugging symptom involves React, hooks, rendering, UI components, state management, hydration errors, or client-side performance. Examples - "useEffect infinite loop", "component not rendering", "hydration mismatch", "state not updating".
Use for deep iterative debugging when memory lookup returns LIKELY_MATCH/WEAK_SIGNAL/NO_MATCH, a fix didn't hold, or the user asks for root cause analysis. Not for known fixes or trivial issues.
Use when the user asks to "debug this", "fix this bug", "investigate error", "diagnose", "root cause", or reports a crash/exception/failure. Memory-first workflow checks past incidents before investigating.
Use when the user asks to "add logging", "add tracing", "improve observability", "OpenTelemetry", "structured logging", or reports silent failures or no runtime visibility. Generates stack-appropriate logging with optional OTel.
Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Never solve the same bug twice
AI-assisted debugging memory for coding agents. It learns from past incidents, classifies similar failures, and supports deep root-cause workflows for hard fixes.
.claude/audit files.claude/memory/ per project) or Shared (~/.claude-code-debugger/ global)# Add the marketplace
/plugin marketplace add tyroneross/claude-code-debugger
# Install the plugin
/plugin install coding-debugger@claude-code-debugger
# npm
npm install @tyroneross/claude-code-debugger
# pnpm
pnpm add @tyroneross/claude-code-debugger
# yarn
yarn add @tyroneross/claude-code-debugger
# npm
npm install -g @tyroneross/claude-code-debugger
# pnpm
pnpm add -g @tyroneross/claude-code-debugger
# yarn
yarn global add @tyroneross/claude-code-debugger
The package name stays @tyroneross/claude-code-debugger for compatibility. The preferred CLI binary is coding-debugger; claude-code-debugger remains as an alias.
pnpm store mismatch error:
If you see ERR_PNPM_UNEXPECTED_STORE, your project has a local .pnpm-store directory. Fix with:
rm -rf .pnpm-store node_modules
pnpm install
npm/pnpm conflict:
If your project uses pnpm (has pnpm-lock.yaml), always use pnpm add instead of npm install.
After installation, these slash commands are automatically available in Claude Code:
| Command | Description |
|---|---|
/debugger "symptom" | Search past bugs for similar issues before debugging |
/debugger | Show recent bugs and pick one to debug |
/debugger-detail <ID> | Drill into a specific incident or pattern |
/debugger-status | Show memory statistics |
/debugger-scan | Scan recent sessions for debugging incidents |
/assess "symptom" | Run parallel domain assessment (database, frontend, API, performance) |
Examples:
/debugger "API returns 500 on login"
→ One-liner matches with verdicts (KNOWN_FIX, LIKELY_MATCH, etc.)
→ Use /debugger-detail <ID> to drill into any match
/debugger-detail INC_API_20260215_143022_a1b2
→ Full incident details: root cause, fix, verification, files changed
/debugger-status
→ "5 incidents stored, 2 patterns, 12 KB used"
/debugger-scan
→ Scans recent sessions for debugging incidents
# Check current configuration
claude-code-debugger config
# Show memory statistics
claude-code-debugger status
# Search memory before debugging
claude-code-debugger debug "Search filters not working"
# Search for specific incidents
claude-code-debugger search "react hooks"
# Drill into a specific incident or pattern
claude-code-debugger detail INC_REACT_20260215_001
# Record whether a suggested fix worked
claude-code-debugger outcome INC_REACT_20260215_001 worked
# Suggest patterns to extract
claude-code-debugger patterns
# Extract and store patterns
claude-code-debugger patterns --extract
# Mine audit trail for missed incidents
claude-code-debugger mine --days 30
# Store mined incidents
claude-code-debugger mine --days 30 --store
# Rebuild keyword index (after manual edits)
claude-code-debugger rebuild-index
npx claudepluginhub tyroneross/claude-code-debugger --plugin claude-code-debuggerBarbara Minto's Pyramid Principle for short-form, long-form, presentations, and audits
Multi-phase build orchestration with native debugging: assess, plan, execute, review, iterate. Plan-verify gate on Phase 2. Optional UI design gates. Native debug-loop, debugging-memory, and logging-tracer skills provide root-cause investigation without a bundled MCP server. Orchestrator owns when-to-fire; bundled skills own procedural detail; logging-tracer-bridge is an optional escalation hop to the standalone Coding Debugger supporting plugin for extended capability.
Map dependencies and analyze blast radius before changing code
End-to-end design tool for AI coding agents — guided UI builds, web/iOS/macOS guidance, visual checks, mockup matching, interaction testing, native scanning, native layout-fill / gap analysis
Agent Rally Point — repo-local coordination surface for parallel coding agents (Claude Code, Codex, Gemini). Records claims, checks write boundaries, routes handoffs, and exposes room state via the rally CLI. Skills: agent-rally-point (per-session loop), rally-workflows (fan-out + dynamic-workflows protocol), mini-loop (per-task quality gate). Advisory-only hooks auto-fire on SessionStart + PreToolUse to surface room awareness and deconflict before edits — never blocks. Backend: rally CLI (cargo install --path crates/rally-cli).
Debug issues systematically with root cause analysis and execution tracing
Intelligent error tracking and solution recall system. Learns from every error you solve, providing instant access to past solutions with multi-level matching and confidence scores.
Ask Claude Code to help you debug an issue
Systematic debugging and root cause analysis framework - four-phase investigation process ensuring understanding before fixes
Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions. Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.