Debugging agents

joshsymonds/nix-config

Agent

Distributed systems debugging specialist for Nix, Home Assistant, Kubernetes, and AWS. Use for troubleshooting failures and root cause analysis.

getsentry/sentry-mcp

Agent

Sentry error tracking and performance monitoring agent. Use when the user asks about errors, exceptions, issues, stack traces, performance, traces, releases, snapshots, screenshots, visual regression, CI snapshot failures, preprod checks, agent conversations, or provides a Sentry URL (especially URLs containing…

oracle/skills

Agent

Collects Kubernetes and OCI evidence for the OKE troubleshooter.

oracle/skills

Agent

Scores troubleshooting hypotheses for OKE incidents using collected evidence.

oracle/skills

Agent

Resolves OCI load balancer identity and collects LB logging status and issue signals for OKE troubleshooting.

rokicool/gsd-opencode

Agent

Investigates bugs using scientific method, manages debug sessions, handles checkpoints. Spawned by /gsd-debug orchestrator.

cyberkaida/reverse-engineering-assistant

Agent Claude Code

Use this agent when you need expert guidance on Ghidra API usage, plugin/extension development, or troubleshooting integration issues. This includes questions about specific Ghidra classes and methods, best practices for plugin architecture, handling obscure API behaviors, resolving compatibility issues, or…

H-mmer/pentest-agents

Agent Claude Code

Stealth browser automation agent for targets behind Cloudflare, Akamai, Google, DataDome, or PerimeterX bot detection. Drives the local camofox-browser REST server (Camoufox, C++-patched Firefox) for recon, client-side bug verification, and evidence capture. Prefer this over the Burp-backed browser-agent when the…

H-mmer/pentest-agents

Agent Claude Code

Analyzes validation gaps in data flows. Takes traced flows and identifies where checks are missing, insufficient, or bypassable. The 'interaction reasoning' step — finds bugs that exist in the gaps between individually correct-looking code. MUST run on Opus. Use via /sast command.

H-mmer/pentest-agents

Agent Claude Code

Server-Side Template Injection specialist. Covers Jinja2 (H1 #74), Twig, Velocity, FreeMarker, ERB, Handlebars, Thymeleaf. Use for any rule-engine, comment/message rendering, PR automation, admin template, or user-customizable template surface. Systematic blocklist mapper + CVE bypass runner + runtime-vs-parse…

vllora/vllora

Agent

Agent "vllora-orchestrator" from vllora/vllora, covering role, task classification protocol, level 1: retrieval & statistics (fast/cheap), level 2: semantic analysis & debugging (deep/expensive) and delegation rules.

freshtechbro/claudedesignskills

Agent

Expert specialist in Animated Component Libraries implementation, patterns, and best practices.

DannyMac180/fable-advisor

Agent

High-complexity implementation lane running Claude's most capable model (Fable 5). Route a task here only when the outcome depends heavily on judgment the spec cannot fully capture — subtle concurrency, non-trivial algorithms, security-sensitive paths, gnarly debugging, wide-blast-radius refactors — or when the same…

melgarafael/DeskcommCRM

Agent Claude Code

Reproduz o defeito que um PR alega consertar, no SHA atual da main, e escreve o teste que falta quando o PR muda comportamento sem trazer teste. Chamado pela triagem nos passes 5/6. Sabota a própria correção para provar que o teste vigia. Trabalha SEMPRE num worktree exclusivo — nunca compartilha árvore com outro…

AVIDS2/memorix

Agent

Code review specialist for quality and security analysis.

AVIDS2/memorix

Agent

Fast codebase recon that returns compressed context for handoff to other agents.

artokun/comfyui-mcp

Agent

Diagnoses ComfyUI workflow failures by analyzing logs, history, and node definitions.

Nanako0129/pilotfish

Agent

Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…

sbhooley/ainativelang

Agent

If you are an AI agent that just needs AINL installed into your host stack, do not read these guides. Run the one-step install from the top of ../../AGENTS.md or ../../README.md.

sbhooley/ainativelang

Agent

This guide gets you from zero to generating OpenClaw automations in AINL within one session.

hex/claude-council

Agent

Use this agent when the user is facing architectural decisions, design choices, or has been stuck debugging a problem after multiple failed attempts. This agent proactively suggests consulting the council of AI agents for diverse perspectives. Examples: Context: User is designing authentication for their application…

mhattingpete/claude-skills-marketplace

Agent

Implement code based on a specific plan or task description. This agent is designed for focused, incremental implementation work where there is a clear specification or plan to execute. Use when there are well-defined implementation tasks from a feature plan.

nominal-io/instro

Agent Claude Code

Run an instro driver's standalone hardware-validation script against the connected instrument and return a structured triage (per-step pass/fail, trimmed error excerpts, and a driver-bug vs script-config vs hardware-wiring hypothesis for each failure). Use from the validate-driver-hardware skill so the noisy…

sbroenne/mcp-server-excel

Agent

Issues and specifications for this repository live in GitHub Issues. Use the gh command-line tool for all operations.