4,369 tagged Debugging, measured the same way as everything else here.
Browse within: code-quality 49bug-bounty 47bugcrowd 44hackerone 44Multi-Agent 40agentic-coding 36agent-orchestration 33claude-code-skills 33Autonomous Agents 31agentic 30github-copilot 30plugin 30claude-ai 27gemini-cli 27
Agent
Strategic Architecture & Debugging Advisor (READ-ONLY). Use when: architecture analysis, code diagnosis, debugging root causes, implementation verification, structural recommendations, system design review.
Agent Claude Code
Predicts consequences and dependency impact of changes (MAP).
Agent Claude Code
Purpose: Specialized Claude Code agent with deep knowledge of the AgentReady codebase to assist with development, testing, and maintenance tasks.
Agent
Use this agent when you need to analyze code changes for potential bugs, trace logic flow across multiple files, or investigate suspicious behavior in the codebase. This agent specializes in deep-dive analysis while maintaining a concise summary format to preserve context. Perfect for reviewing recent modifications…
Agent Claude Code
Use this agent ONLY as a LAST RESORT for MULTI-HOP structural analysis across the DGame codebase that plain Grep/Read cannot answer efficiently — e.g. tracing a full dependency/call chain, assessing the blast-radius of changing a widely-used symbol (who transitively depends on it), or mapping how many modules connect…
Agent Claude Code
Duplicate code detection and refactoring specialist. Uses similarity-rs for semantic similarity detection and performs refactoring based on DRY principle. USE PROACTIVELY after fixing build/clippy errors or when code duplication is suspected.
Agent Claude Code
Use this agent to compile/build IDA Pro extensions including plugins, idalib applications, processor modules, or file loaders (all known as IDA addons) using the IDA C++ SDK. Use this agent to create a new addon template, troubleshoot build issues, configure the IDASDK environment, integrate ida-cmake into existing…
Agent Claude Code
Electron Linux desktop specialist. Use for BrowserWindow patches, Wayland/X11 compatibility, DBus tray integration, native theme handling, and desktop environment debugging.
cloudnative-co/claude-code-starter-kit
Agent
Build and type error resolver for pre-existing or unfamiliar build/test failures that need isolated investigation. Do not auto-delegate errors introduced by changes in the current session — fix those directly in the main context.
Agent
Creates prioritized fix plans from audit findings. Generates FIXES.md with deduplication.
Agent
PowerShell 7 specialist for secure automation, troubleshooting, and production-ready scripts.
Agent
Any file using evalSPMF, probOutput, probEvent, or Pr[...] on OracleComp spec needs [IsProbabilitySpec spec]. evalDist / 𝒟[…] also needs a MeasurableSpace on the result type. Lemmas that use uniform cardinalities, PMF.uniformOfFintype, or connect support to nonzero probability need [IsUniformSpec spec]. Plain support…
Agent
Implements multi-file features and bug fixes with focused unit tests and a validation handoff.
Agent ✓ vendor
Analyze solver trajectories after a probe run to diagnose tool-level errors (rate limits, wrong tool names, script crashes) that proberesult.json doesn't capture. Dispatch after eval.py completes. Returns a redacted diagnosis JSON — safe to pass to the improver.
vasu31dev/playwright-ts-template
Agent Claude Code
Use this agent when you need to debug and fix failing Playwright tests.
Agent
You are a fast exploration agent focused on understanding codebases.
Agent
A read-only exploration worker for locating code, symbols, strings, services, protections, and possible attack surfaces. It reports findings without changing files.
dynamics365ninja/d365fo-mcp-server
Agent Claude Code
Improver role of the D365FO agent eval loop. Reads the corpus of run records, ranks failure clusters, reproduces a TOOLDEFECT/KNOWLEDGEGAP/VALIDATORGAP as a minimal VM-free repo test, fixes it, validates against the held-out split, and opens a PR citing corpus evidence. Runs in the repo (never touches the VM). Use…
Agent Claude Code
A code review agent that checks analysis scripts for logical errors, incorrect function usage, wrong variable references, off-by-one errors, silent coercion bugs, and data manipulation mistakes that could produce wrong results. Focuses on R and Python scripts produced by AI for social science analysis.
Agent
Verifies implementation work by running code, executing tests, and generating adversarial test cases. Checks against the problem definition and principles, not against the proposal document. Approval is gated on execution results, not code reading.
Agent
Code exploration specialist that leverages the th0th semantic index instead of brute-force file reads. Use when the user asks "where is X?", "how does Y work?", "who calls Z?", or for any question about an indexed codebase. Starts every investigation by consulting the th0th index (project map, definitions, references)…
Koomook/fastcampus-ai-agent-vibecoding
Agent Claude Code
Use this agent when you need to review recently written code for quality, best practices, potential bugs, or improvements. This agent should be called proactively after completing a logical chunk of code implementation, such as:\n\n- After writing a new function or class\n- After implementing a feature or fixing a…
Agent
Use this agent for complex, multi-step codebase explorations that require strong reasoning — call graph building, multi-file architectural analysis, and deep investigations across many files. This agent uses a more capable model than the standard explorer. Use the standard grepika:explorer agent for quick lookups…
Agent
Use this agent when you need to explore a codebase efficiently using the grepika MCP server. This agent specializes in token-efficient code search, file discovery, structural analysis, and code-graph navigation. It should be used instead of the generic Explore agent when grepika tools are available. Context: User asks…