Debugging agents

luke-kerwin/claude-code-setup

Agent Claude Code

You are a specialist at finding code patterns and examples in the codebase. Your job is to locate similar implementations that can serve as templates or inspiration for new work.

romiluz13/claude-code-excellence-audit

Agent Claude Code

Investigates and fixes bugs, errors, and test failures. Use PROACTIVELY when encountering any errors or unexpected behavior.

khanh-vu/claude-force

Agent Claude Code

Bug Investigator - specialized in diagnosing, root cause analysis, and providing solutions for complex bugs and issues.

kimmy-sil/empirical-paper-cc

Agent Claude Code

A debugging specialist that follows the path from an error or unexpected result to its cause, smallest fix, and verification.

lucafusarbassini/research-automation

Agent

Diagnoses training failures, checks for bugs and information leakage.

noahlz/claude-plugins

Agent

Analyzes build/compilation failures and determines root cause and potential fixes for a Plan.

noahlz/claude-plugins

Agent

Analyzes test suite failures and determines root cause and potential fixes for a Plan.

ParkerRex/tec-claude-code-agents

Agent Claude Code

Automated end-to-end debugging system that takes you from incident report to merged PR with comprehensive documentation.

ParkerRex/tec-claude-code-agents

Agent Claude Code

Orchestrates the complete debug workflow from RCA through implementation to PR creation.

catch-the-wave/fullstack-ios-claude-skills

Agent

Analyzes codebases and maintains persistent knowledge in .claude/CODEBASE.md. Creates institutional memory through full scans or delta updates. Identifies architecture, patterns, smells, and decisions. Use for initial codebase understanding or updating analysis after changes.

FelixSoderstrom/GIVERNY

Agent Claude Code

Understands code. Use when you want to know how code works.

heygen-com/auto-model-optim

Agent Claude Code

Autonomous inference-optimization agent. Runs the keep-or-revert auto-optim loop in this repo to minimize a model's inference latency on a fixed device without failing the quality gate. Model-agnostic; the target, thresholds, and stop conditions all come from goals.json. The shipped example is the Wan 2.2 VAE decoder…

irahardianto/rugged-gemini

Agent Gemini CLI

Structured incident response and pre-mortem analysis specialist. Handles triage, root cause analysis, mitigation coordination, postmortem documentation, and proactive failure analysis (pre-mortem). Read-only — produces incident reports, postmortems, pre-mortem findings, and remediation recommendations. Never writes…

irahardianto/rugged-gemini

Agent Gemini CLI

Read-only quality gate authority. Invoke for code review, audit, debugging sessions, root cause analysis, performance data review, test coverage verification, and compliance checks. Produces findings and recommendations — never writes or edits code.

band-app/band

Agent Claude Code

Reviews production source-code changes (apps/web/src/, apps/desktop/src/, apps/cli/src/, packages//src/) against .claude/coding-criteria.md (rules CODE-1...CODE-19), plus flags obvious correctness bugs and pattern drift in source files within scope. Read-only. Dispatched by the review-changes skill in normal flow; can…

band-app/band

Agent Claude Code

Reviews production source code in the diff for performance concerns (query patterns, hot-path loops, sync I/O in handlers, render-time work, pagination, large responses) against .claude/performance-criteria.md (rules PERF-1...PERF-10), plus flags obvious perf-adjacent bugs in code that runs in a hot path. Read-only.…

band-app/band

Agent Claude Code

Reviews the diff for security concerns (secrets handling, injection, auth scope, GitHub Actions security, dependency risk, crypto) against .claude/security-criteria.md (rules SEC-1...SEC-15), plus flags obvious security-adjacent bugs. Read-only. Dispatched by the review-changes skill in normal flow; can also be…

Horosheff/Excalibur-2-Cloud

Agent Cursor

⑦ Fixer: converts pipeline incident memory into durable repo fixes before the next run. Director-chain only; inherit automation model; no nested Task/cloud.

phucle297/my-claude-config

Agent

Systematic debugging subagent — reproduce, isolate, root-cause before fixing.

atra-consulting/coding-with-ai-lab

Agent Claude Code

Use this agent when you need to write, review, modify, or debug shell scripts that must work reliably across Linux, macOS, and Windows Subsystem for Linux (WSL). Examples include:\n\n \nContext: User needs to create a deployment script that works on developer machines (macOS) and CI/CD pipelines (Linux).\nuser: "I…

noeltock/prompt-relay

Agent

Implements semi-defined coding work where the approach is visible but not fully specified — debugging with a clear surface, style-sensitive refactors, consolidations needing judgment among existing patterns, and large/messy diffs even when specified. Sits between coder-low (needs decisions pre-named) and the lead…

s1366560/agi-demos

Agent

PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance. Incorporates Supabase best practices.

MatthewYe/opencode-toolbox

Agent

An autonomous implementation agent that follows an AGENT-BRIEF, a written task contract, and uses TDD, or test-driven development, while coding. It also diagnoses unexpected errors and adjusts its approach.

AssemblyAI/blurt

Agent Claude Code

Reviews code for reuse, simplification, dead code, efficiency, and altitude — quality only, not correctness bugs. Pre-briefed on Blurt's deliberately-dormant code so a dead-code pass doesn't propose deleting it. Use for /simplify-style cleanup passes, one agent per angle.