Debugging agents

Oolab-labs/patchwork-os

Agent Claude Code

Autonomous debugging agent that uses IDE bridge debug and terminal tools. Sets breakpoints, evaluates expressions, inspects runtime state, and fixes bugs. Use when encountering test failures, runtime errors, or unexpected behavior.

Oolab-labs/patchwork-os

Agent

Part of claude-ide-bridge

Long-term codebase architectural health agent. Identifies God objects, circular dependencies, tightly coupled modules, and modularization opportunities using LSP import tree and call hierarchy analysis. Use for architecture audits, pre-refactor planning, or onboarding deep-dives.

codecast-sh/codecast

Agent

Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.

manykarim/robotframework-agentskills

Agent

Part of rf-agentskills

Diagnose and resolve Robot Framework test failures, flaky tests, environment issues, and execution errors. Invoke when the user needs to analyze output.xml results, interpret error messages, debug locator failures, fix timing issues, or understand why a test suite is failing.

TechNickAI/claude_telemetry

Agent Claude Code

Dixon - The Detective 🔎. Debugging specialist who hunts root causes, not symptoms. Invoke when encountering errors, test failures, or unexpected behavior. Systematically isolates problems, proposes minimal fixes, and recommends prevention strategies.

german-krasnikov/unity-biome-mcp

Agent

Use to investigate Unity connection, compilation, console, scene-health, runtime-state, rendering, memory, or performance problems through Unity Biome MCP. Do not use to implement fixes.

kornia/bubbaloop

Agent

Part of bubbaloop

Use when the user asks to inspect, control, or troubleshoot a running Bubbaloop deployment — node lifecycle (start/stop/restart/build), health checks, log reads, mission management, or scheduling tasks. Wraps the bubbaloop MCP server and enforces the discover-before-act discipline.

giantswarm/muster

Agent Cursor

Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development. Use proactively when needing to understand how a feature works before modifying or extending it.

gensecaihq/MCP-Developer-SubAgent

Agent Claude Code

MCP troubleshooting and debugging specialist for protocol issues, transport problems, and diagnostic analysis.

ReviewToolkits/cext-review-toolkit

Agent

Part of cext-review-toolkit

Use this agent to audit error handling correctness in C extension code that calls the Python/C API.\n\n \nUser: Check the error handling in my C extension.\nAgent: I will run the error path scanner, prioritize missing NULL checks and return-without-exception findings, and review extension-specific error patterns like…

iamrichardD/mcp-server-pinescript

Agent Claude Code

Advanced Pine Script parsing and AST generation expert that MUST BE USED PROACTIVELY for complex syntax analysis, parameter extraction, and validation rule creation. Specializes in parsing Pine Script code to extract parameters, identify syntax patterns, and generate structured representations for validation engines.

ScientiaCapital/skills

Agent Claude Code

Full observer with 7 drift detection patterns + devil's advocate stance. Writes to .claude/observers/QUALITY.md and .claude/observers/ARCH.md. Thorough analysis for STANDARD/FULL scope tasks.

ScientiaCapital/skills

Agent Claude Code

Lightweight code quality observer. Runs 4 quick checks: secrets scan, test gaps, silent failures, debt markers. Writes to .claude/observers/QUALITY.md. Fast (<60s), cheap (<$0.05).

ready-to-release/eac

Agent Claude Code

Debug Go code, investigate failures, trace issues, analyze performance.

umbraco/Umbraco-CMS-Backoffice-Skills

Agent Claude Code

Analyzes skill validation issues and suggests intelligent fixes. Spawned by /validate-skills command when issues are found.

DataCovey/nornweave

Agent Cursor

Debugging specialist for errors and test failures. Use when encountering issues.

tdwhere123/do-it

Agent

Part of do-it

Use when quick reconnaissance is complete and an unfamiliar or risky bounded scope needs a read-only trace or thorough map of ownership, contracts, consumers, and unknowns.

DennisLiuCk/claude-plugin-marketplace

Agent

Part of issue-review

A codebase investigation agent that searches a project’s source code to find where a problem could originate and lists likely causes.

DennisLiuCk/claude-plugin-marketplace

Agent

Part of issue-review

A problem-analysis agent that turns an incomplete report into key facts and suggested investigation paths. Reports may come from users, product managers, developers, testers, error logs, or monitoring alerts.

DennisLiuCk/claude-plugin-marketplace

Agent

Part of issue-review

A debugging agent that tests possible explanations for a software problem and works toward confirming the actual root cause.

wrxck/auto-audit

Agent

Part of auto-audit

Implement the minimal fix for a confirmed security finding with a working PoC. Creates a branch, edits source files, runs project tests if they exist, and commits. Does NOT open the PR. Invoke when a finding is in pocwritten state.

aiunlocked1412/boxbox

Agent

Part of boxbox

Reads the scanner's inventory and traces connections between features (imports, API calls, DB access, external services). Used by /boxbox in Step 2.

li0nel/claude-loop

Agent Claude Code

Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).

li0nel/claude-loop

Agent Claude Code

Locates files, directories, and components relevant to a feature or task. Call codebase-locator with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.