Debugging commands

controlplane-com/ai-plugin

Command

Part of cpln

Diagnose and fix a Control Plane workload that is unhealthy or not working correctly.

Caspian-Sun/claude-code-workflow

Command Claude Code

You are now acting as a Frontend Debugging Engineer. Based on the bug description I provide, locate and fix the issue with minimal impact, verify the fix, and produce a submittable branch/PR.

zircote-plugins/sdlc-quality

Command

Part of sdlc

Run SDLC compliance check against the current project. Validates build system, code quality, testing, CI/CD, security, documentation, VCS, and release configurations.

Chappygo-OS/Atomic-Spec

Command

Detect and remove orphaned code, unused components, dead routes, and stale database artifacts.

valpere/chorus

Command

Part of chorus

Parallel debugging — five agents propose root-cause hypotheses for a symptom.

rube-de/cc-skills

Command

TDD-driven bugfix workflow: tester writes failing test (RED) → developer fixes (GREEN) → developer refactors (REFACTOR) → reviewer validates. Accepts issue number, description, or both. Auto-creates PR unless --no-pr flag is passed.

Calhooon/bsv-wallet-cli

Command

Command "LEARNING" from Calhooon/bsv-wallet-cli, covering learning — commands, lessons learned, debugging insights and pattern notes.

MosaicXR-AI/mosaic-bridge

Command

Part of mosaic-bridge

Launch Ray — Mosaic Bridge shader expert (ShaderGraph, HLSL, node wiring, shader debugging).

Goldziher/poly

Command

Part of poly

Lint and check formatting with poly — apply no fixes; summarize findings and drift.

nobrainer-tech/langflow-mcp

Command Claude Code

Comprehensive memory usage optimization with leak detection, garbage collection tuning, and memory profiling.

Horosheff/cursor-jr

Command

A command for running a complete health check on CursorJr, including its agents, knowledge base, behavior tests, and manifest file.

mverab/claude-beyond-code

Command Claude Code

Start a new incident log file.

sso-ss/vibe-ship-it

Command Claude Code

The user is stuck or frustrated. Follow the unstuck skill protocol.

yao-beyond/debug-hunter

Command

Part of debug-hunter

Run the debug-hunter 7-stage financial bug & fraud closed loop on a target scope.

fermonterom/claude-testing-kit

Command Claude Code

Escanea el proyecto, valida build, env vars, seguridad, tests, y da un score 0-100 con semaforo.

evmts/guillotine-mini

Command Claude Code

Systematically isolate the exact line causing a crash through methodical code bisection.

metabase/repro-bot

Command Claude Code

Analyze past reproduction runs and implement concrete improvements to the repro workflow.

metabase/repro-bot

Command Claude Code

Investigate and reproduce a Metabase bug report against a fresh, isolated Metabase instance. Post findings as a structured Linear comment.

skyfox675/agents-skills

Command Claude Code

The full-stack deep dive — /gh-issue plus BOTH the live-browser and read-only AWS diagnosis phases, correlated: reproduce the symptom as the signed-in user, capture the failing request, then chase that exact request through the cloud (edge, logs, service, data) until the fault layer is found. Use for symptoms nobody…

GGPrompts/my-gg-plugins

Command

Query OpenAI Codex for root cause analysis (read-only, no edits).

GGPrompts/my-gg-plugins

Command

Query Google Gemini for root cause analysis (read-only, no edits).

vamshisuram/cc-manager

Command

Part of cc-manager

Print a terminal-only health summary of the Claude Code setup.

ReviewToolkits/cpython-review-toolkit

Command

Part of cpython-review-toolkit

Like explore, but INFORMED: every agent first reads a briefing of recurring CPython C bug SHAPES (sibling-hunt templates with their guarded twins), the cross-cutting triage rules, and the false-positive taxonomy — so it confirms-without-relitigating, suppresses known FPs, and hunts un-found siblings of known shapes…

ReviewToolkits/cpython-review-toolkit

Command

Part of cpython-review-toolkit

Cross-reference the seed catalog of previously-found CPython crashes against a fresh scan, so a fix (or a regression-after-revert) is detected. Static, drift-tolerant regression — no repros run.