Debugging agents

drvoss/everything-copilot-cli

Agent

Dead code removal, code cleanup, and safe modernization without behavioral changes.

ed-donner/personal-space

Agent

Adversarial reviewer for Personal Space. Uses the running app in unscripted, hostile ways to break it, working from the browser's text snapshot, and records every finding in ADVERSARIALREVIEW.md. Never fixes, never triages its own findings.

IndianOldTurtledove/codex-oss-maintainer-toolkit

Agent Codex

Diagnose and fix build, test, or runtime errors with minimal changes.

wagnersza/copilot-plugin-cc

Agent

Part of copilot

Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Copilot through the shared runtime.

Gixsy95/abap_wiki

Agent Codex

Self-sufficient analyzer of ABAP sources for the L1 step of the abapwiki knowledge base. Operates raw-only: reads the files in raw/system-library/ without MCP. Receives sapname, saptype, devclass, rawsourcepath and an artifactpath; WRITES to file a structured YAML report with narrativesections, classified dependencies…

JubaKitiashvili/everything-react-native-expo

Agent Claude Code

Part of erne-universal

Screenshot-based UI analysis, visual bug detection, layout/spacing/alignment fixes, before/after verification, Figma comparison. Triggered by /debug-visual or when user shares a screenshot with UI issues.

loonghao/auroraview

Agent

You are an expert architect and debugging specialist with deep expertise in system design, low-level programming, and framework architecture. Your role is to analyze complex technical requirements, conduct thorough research, and design robust, well-reasoned solutions following industry best practices.

sagarmk/beacon-plugin

Agent

Part of beacon

Delegate to this agent for deep codebase exploration — semantic search, exact symbol lookup and reference tracing over a Beacon index. Use when the question requires understanding how multiple files connect.

Heratiki/locallama-mcp

Agent

Debug your application to find and fix a bug.

Heratiki/locallama-mcp

Agent

Perform janitorial tasks on any codebase including cleanup, simplification, and tech debt remediation.

ErkanBarin/playwright-agent-mcp-starter

Agent

Diagnoses flaky tests by analyzing traces, screenshots, and common flake patterns.

ysyecust/everything-claude-code

Agent

Part of ecc

Kotlin/Gradle build, compilation, and dependency error resolution specialist. Fixes build errors, Kotlin compiler errors, and Gradle issues with minimal changes. Use when Kotlin builds fail.

signalridge/dotfiles

Agent

Adversarial read-only checker for ONE stated claim. You give it a single specific assertion — "this function is never called with null", "removing X breaks nothing", "the fix in commit abc handles the empty case", "these two configs cannot both be active" — and it tries to REFUTE it, returning CONFIRMED / REFUTED /…

ncoevoet/claude-markdown-health-check

Agent Claude Code

Analyzes logs for anomalies. Use when investigating errors or unexpected behavior in application logs.

wende/cicada

Agent

Fast code exploration and discovery. Use when you need to quickly find modules, functions, or understand code structure.

drafthq/draft

Agent

Part of draft

Structured Root Cause Analysis agent for bug investigation. Extends the debugger agent with RCA discipline for production bugs, Jira incidents, and distributed system failures.

rmartynenko/workflow-dev-1c-claude-code

Agent Claude Code

A performance-review agent for 1C code, the programming language and business-software platform used in many Russian-speaking organisations. It looks for slow parts and ranks possible improvements using measured impact, usage frequency, and data volume.

Kewton/CommandMate

Agent Claude Code

Bug investigation specialist. MUST BE USED when PM Bug Fix requests bug investigation. Reads context from investigation-context.json and outputs investigation-result.json. Analyzes error logs, identifies root cause, and recommends solutions.

IJONIS/geo-lint

Agent

Part of geo-lint

Autonomous content fixer for geo-lint violations. Resolves content slugs to file paths, applies fixes from violation suggestions, and iterates the lint-fix loop until clean or 5 passes exhausted.

fieldsphere/cursor-team-marketplace-template

Agent

Spawns a GPT-5.4-high agent for planning, review, analysis, and debugging of complex or difficult tasks—higher-quality reasoning, second opinions, or architectural guidance when ambiguity, risk, or failures appear. ONLY call this subagent when the user explicitly requests it. NEVER use the fast model for this…

Svenja-dev/claude-code-skills

Agent

Use this agent to detect and analyze code bloat, bundle size issues, and technical debt in your codebase. Trigger this agent when: (1) files exceed 500 LOC, (2) during weekly code health scans, (3) before major releases, (4) after adding new dependencies, or (5) when build times increase unexpectedly. Examples…

Oolab-labs/claude-ide-bridge

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.

ysicing/code-pilot

Agent

Part of code-pilot

A bug-fixing agent that investigates errors through messages, logs, stack traces, code paths, configuration, dependencies, and external-service connections before making a targeted code change. It also recognizes likely front-end issues in files and frameworks such as React, Vue, and Svelte.

ysicing/code-pilot

Agent

Part of code-pilot

A debugging coordinator that organizes several AI roles to investigate software problems. It combines architecture analysis, external research, coding, testing, and a final diagnosis before asking for confirmation to proceed with a fix.