Debugging Subagents
290 debugging subagents for Claude Code and AI agents, ranked by real installs from npm, PyPI and skills.sh.
#Type
- 1debuggerRoot-cause analysis, regression isolation, stack trace analysis, build/compilation error resolutionJul 2026
- 2exploreCodebase search specialist for finding files and code patternsJul 2026
- 3tracerEvidence-driven causal tracing with competing hypotheses, evidence for/against, uncertainty tracking, and next-probe recommendationsJul 2026
- 4performance-analystThe Performance Analyst profiles game performance, identifies bottlenecks, recommends optimizations, and tracks performance metrics over time. Use this agent for performance profiling, memory…May 2026
- 5debuggerUse this agent when encountering errors, test failures, unexpected behavior, or any issues that require root cause analysis. The agent should be invoked proactively whenever debugging is needed.Jul 2026
- 6explorerRead-only code exploration sub-agent. Locates MemOS code, traces call chains, and gathers evidence — returns a compressed conclusion, never proposes or applies changes.Jul 2026
- 7auto-error-resolverAutomatically fix TypeScript compilation errorsJul 2026
- 8frontend-error-fixerUse this agent when you encounter frontend errors, whether they appear during the build process (TypeScript, bundling, linting errors) or at runtime in the browser console (JavaScript errors, React…Jul 2026
- 9debuggerProduction debugger — investigates issues using logs, CI data, metrics, and AWS infrastructure. Spawn this agent to diagnose build failures, runtime errors, or infrastructure problems. It reports…Jul 2026
- 10debuggerDebugging specialist for errors, test failures, and unexpected behaviorJul 2026
- 11debug-agentInvestigate issues using codebase exploration, logs, and code searchJan 2026
- 12profilerPerformance profiling, race conditions, memory issuesJan 2026
- 13sleuthGeneral bug investigation and root cause analysisJan 2026
- 14crash-analysis-agentAnalyze security bugs from any C/C++ project with full root-cause tracingJul 2026
- 15crash-analyzer-agentAnalyze crashes using rr recordings, function traces, and coverage data to produce root-cause analyses.Jul 2026
- 16crash-analyzer-checker-agentCarefully analyze root cause analysis reports for crashes to make sure they are correctJul 2026
- 17function-trace-generator-agentGenerate function-level execution traces for debugging and analysis.Jul 2026
- 18debuggerSpecialized debugging agent. Use when facing hard bugs, test failures, or runtime errors that need systematic investigation.Jul 2026
- 19verdict-auditorIndependent auditor that checks whether the agent's stated verdict — claims like "the fix works", "tests pass", "root cause is X", "deploy is healthy", "found N issues" / "no issues", "<thing> is…Jul 2026
- 20malware-analystDelegates to this agent when the user asks about malware analysis, reverse engineering, binary analysis, disassembly, debugging, sandbox analysis, static analysis, dynamic analysis, or suspicious…Jun 2026
- 21reverse-engineerDelegates to this agent when the user asks about static reverse engineering, working with Ghidra, Radare2, IDA, JadX, decompiling Android APKs, analyzing firmware with Binwalk, reading disassembly,…Jun 2026
- 22debuggerUse this agent when you need to diagnose and fix bugs, identify root causes of failures, or analyze error logs and stack traces to resolve issues.Jul 2026
- 23bug-triageTriages GitHub issues by investigating whether they've been resolved in the codebase, recommending closures, and helping craft polite closure messages. Use when doing bug triage sessions or cleaning…Jul 2026
- 24deep-exploreDeep codebase exploration using grepai semantic search and call graph tracing. Use this agent for understanding code architecture, finding implementations by intent, analyzing function relationships,…Jun 2026
- 25deep-reflectorComprehensive session analysis and learning capture specialist. Analyzes development sessions to extract patterns, preferences, and improvements for future interactions. Use after significant work…Jul 2026
- 26scout-report-suggest-fastUse proactively to quickly scout codebase issues, identify problem locations, and suggest resolutions. Specialist for read-only analysis and reporting without making changes.Feb 2026
- 27debuggerExpert debugging specialist for errors, test failures, crashes, segmentation faults, memory leaks, timeouts, race conditions, deadlocks, and unexpected behavior. Use PROACTIVELY when encountering any…Jul 2026
- 28performance-auditorPerformance optimization specialist focusing on speed, efficiency, and resource usage. Use PROACTIVELY for code handling large datasets, complex algorithms, or user-facing performance. MUST BE USED…Mar 2026
- 29trigger-boundary-auditorAudits the trigger boundaries of the six brooks-lint skills for false-triggering risk and routing collisions. Use before a release, or after editing any SKILL.md `description:` field. Read-only —…Jul 2026
- 30vc-debuggerUse this agent when you need to investigate issues, analyze system behavior, diagnose performance problems, examine database structures, collect and analyze logs from servers or CI/CD pipelines, run…Jun 2026
- 31bug-analyzerAnalyze root cause of bugs after location is identified. Second step in bug investigation.Jul 2026
- 32bug-fixerImplement bug fixes after analysis is complete. Third step in bug fix pipeline.Jul 2026
- 33bug-locatorLocate the source of bugs in the codebase. First step in bug investigation.Jul 2026
- 34bug-verifierVerify bug fixes by running tests. Final step in bug fix pipeline.Jul 2026
- 35log-analyzerAnalyze log files and extract actionable insights. Use when troubleshooting issues or investigating incidents.Jul 2026
- 36agent-debuggerPrincipal Diagnostics Engineer specializing in root cause analysis, error troubleshooting, and hotfixes.Jul 2026
- 37performance-reviewerUse this agent when you need to analyze code for performance issues, bottlenecks, and resource efficiency. Examples: After implementing database queries or API calls, when optimizing existing…Jul 2026
- 38verify-agent구현 완료 후 fresh-context 검증 전용. typecheck → lint → build → test 파이프라인 독립 실행. 단순 에러(import·타입) 자동 수정, 비수정 가능 에러 분류 보고. Use proactively — 비단순 코드 변경 완료 직후 사람 호출("검증해줘"·"빌드 확인")을 기다리지 말고 자율 spawn한다. 완료 주장 전…Jul 2026
- 39sast-danger-mapperMaps dangerous operations in a source file: memory ops, type casts, arithmetic near trust boundaries, free/dealloc patterns. Pattern matching task — list what you see, don't speculate. Use via /sast…Jun 2026
- 40sast-entry-mapperMaps entry points where untrusted data enters a source file. Lists every function that receives external input with data type, size constraints, and initial validation. Use via /sast command.Jun 2026
- 41sast-flow-tracerTraces data flow from entry points to dangerous operations. Cross-file reasoning to determine which entries can reach which dangers, and what validation exists in between. MUST run on Opus for…Jun 2026
- 42sast-gap-analyzerAnalyzes 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…Jun 2026
- 43debuggerBug investigation and root cause analysis. Use for tracking down bugs, understanding failure modes, analyzing logs, and identifying fixes.Jul 2026
- 44scoutRead-only code exploration and repo scanning. Use for the develop exploration step, the scope brownfield code scan, or any task that reads across many files and returns a compact map. Never edits.Jul 2026
- 45build-error-resolverBuild and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting…Jan 2026
- 46semble-searchCode search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for…Jul 2026
- 47investigatorComprehensively collects problem-related information and creates evidence matrix. Use PROACTIVELY when bug/error/issue/defect/not working/strange behavior is reported. Reports only observations…Jul 2026
- 48incident-investigator告警根因诊断 worker，顺因果链溯源到根因（0 号病人），不止于症状摘要Jul 2026
- 49bug-reproducerHarnessFlow worker subagent — spawn only from a HarnessFlow workflow step, never by autonomous delegation. Runs target scripts to attempt to reproduce a bug, captures all output, and summarizes the…Jul 2026
- 50robustness-analystHarnessFlow worker subagent — spawn only from a HarnessFlow workflow step, never by autonomous delegation. Identifies robustness issues, potential bugs, and proposes improvements to make the codebase…Jul 2026
- 51skill-effectiveness-analyzerAnalyzes skill effectiveness data to identify failure patterns and recommend improvements. Use after /skill-monitor flags underperforming skills.Jul 2026
- 52godot-performance-profilerUse this agent when the user reports lag, stutter, frame drops, draw call spikes, GC pauses (C#), physics slowdowns, or any other performance issue in their Godot 4.x project. The agent reads code,…Jul 2026
- 53workflow-debuggerHypothesis-driven debugging with structured evidence loggingJul 2026
- 54debuggerDebugs errors, test failures, and unexpected behavior. Knows PromptScript architecture.Jul 2026
- 55debuggerDebugging specialist for root cause analysis, investigating defects, and tracing execution flow. Use when encountering bugs, test failures, or unexpected behavior that requires systematic…Jul 2026
- 56playwright-test-healerUse this agent when you need to debug and fix failing Playwright testsJul 2026
- 57issue-tracerUse proactively when the user asks to trace, investigate, root-cause, plan, close, or prepare a PR for a GitHub issue or bug report. Produces an evidence-backed root cause and critic-reviewed fix…Jul 2026
- 58explorerRead-only codebase explorer on Sonnet at high effort. Use to locate files, symbols, call paths, tests, uncertainties, and candidate affected surfaces before implementation or judgment.Jul 2026
- 59root-cause-proverBugfix diagnosis and pre-fix evidence specialist on Opus at high effort. Use to prove a concrete root cause, reproduce it, add a candidate regression guard, and capture the existing four-field Root…Jul 2026
- 60layout-detective-agent`layout-detective-agent` 是 PaperFit 的视觉诊断 Agent。它的职责只有一个：基于 PDF 页图、交叉引用与日志线索，判断论文当前到底有哪些可见排版问题，以及这些问题的严重程度。Jun 2026
- 61testing-bug-fixerBug修复与根因分析专家，负责问题定位、二分法缩小范围、最小化修复、回归测试编写，确保每个修复都精准且不引入新问题Jul 2026
- 62debuggerDebugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues, build failures, runtime errors, or unexpected test results.Jul 2026
- 63debuggerUse this agent when you need to investigate issues, analyze system behavior, diagnose performance problems, examine database structures, collect and analyze logs from servers or CI/CD pipelines, run…Mar 2026
- 64audit-deepDeep single-subsystem audit that reasons about state over time (caches, upserts, migrations, concurrent scans) rather than pattern-matching lines. Used by /bug-audit on the riskiest subsystems; runs…Jul 2026
- 65audit-scannerFast, wide sweep of one audit dimension across the codebase. Returns candidate findings with file:line evidence for the verifier to confirm. Used by /bug-audit; runs on Sonnet for breadth per token.Jul 2026
- 66audit-verifierAdversarially verifies one candidate finding from /bug-audit — tries to REFUTE it by reading the code and, where cheap, reproducing it with a throwaway script. Kills false positives before they reach…Jul 2026
- 67debuggerDebug engineer and log analyst. Systematically finds the root cause of bugs: reads logs, narrows scope, builds hypotheses, verifies, fixes. Also analyzes PM2 / Docker / systemd / Nginx logs for error…Apr 2026
- 68build-error-resolverBuild and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting…Jul 2026
- 69error-whispererHata mesajlarını analiz eder, kök nedeni tespit eder ve kopyala-yapıştır düzeltme sunar. Kullanıcı bir hata mesajı, stack trace veya build hatası paylaştığında kullanılır. Genel tıkanıklık veya karar…Apr 2026
- 70rubber-duckSokratik düşünce ortağı. Kullanıcı mimari karar, özellik tasarımı veya teknik ödünleşme üzerinde düşünürken doğru soruları sorarak netlik sağlar. Cevap vermez, cevabı buldurur. Hata çözümlemesi veya…Apr 2026
- 71claworc-dev-troubleshooterUse this agent when the user reports issues with the local Claworc development environment, encounters unexpected behavior in the control plane backend, frontend, LLM proxy, or running OpenClaw…Jul 2026
- 72playwright-test-healer.agentUse this agent when you need to debug and fix failing Playwright testsJul 2026
- 73brahma-investigatorRoot cause analysis and debugging specialist with Anthropic think protocol and 3-retry limit. Focuses on systematic problem diagnosis, error tracing, and fix validation. Use for complex bugs and…Nov 2025
- 74hive-scoutHoney hive subagent. Read-only code locator — finds where symbols, callers, configs, or patterns live across the repo and returns the map to the orchestrator as a compact, id-keyed handoff (Honey…Jul 2026
- 75performance-optimizerPerformance optimization expert. Identifies N+1 queries, memory leaks, and slow queries.Jul 2026
- 76proxy-analyzer프록시 캡처 트래픽 분석 에이전트. 5가지 메커니즘(CLAUDE.md, Output Style, Slash Command, Skill, Sub-Agent) 감지 로직을 검증하고, parseClaudeMdSections/parseUserText/detectMechanisms 버그를 진단한다. 원인이 불명확할 때는 ACH(경쟁 가설 분석) 프레임워크로 병렬…Apr 2026
- 77ui-debuggerindex.html UI 버그 진단 전문 에이전트. CSS/JS 문제를 분석하고 수정 방안을 제시한다. 진단 먼저 수정은 한 번에 원칙: 부모→자식 CSS 체인 전체를 분석한 후 단일 수정 제안. 추측 금지. 확인된 원인에만 수정 적용.Apr 2026
- 78git-detectiveGit archaeology agent. Digs through commit history to answer 'when/why/who' questions about code changes. Give it a question and it will search logs, blames, and diffs to find the answer.Apr 2026
- 79eval-improverImprover role of the D365FO agent eval loop. Reads the corpus of run records, ranks failure clusters, reproduces a TOOL_DEFECT/KNOWLEDGE_GAP/VALIDATOR_GAP as a minimal VM-free repo test, fixes it,…Jul 2026
- 80fatal-error-checkFast pre-review check for fatal errors in LaTeX papers. Launch BEFORE\Jul 2026
- 81performance-auditorPerformance analysis and optimization expertJul 2026
- 82investigatorUse when investigating bugs, errors, test failures, or unexpected behavior. Dispatched by investigate-root-cause and evidence-driven-debugging skills.Jul 2026
- 83al-triageReactive diagnosis specialist for EXISTING Business Central AL code — reproduce, localize, root-cause, and recommend a minimal fix for bugs, regressions, and incidents. Read-only on code: produces a…Jul 2026
- 84al-triage.agentReactive support for EXISTING Business Central AL code — reproduce, localize, root-cause, and recommend a minimal fix for bugs, regressions, and incidents. Read-only on code: produces a diagnosis and…Jul 2026
- 85auto-error-resolverFix compilation errors, build failures, type errors, or test failures. Systematically identifies root causes and fixes them in order.Jul 2026
- 86genesis-investigatorDiagnoses Genesis subsystem failures. Use when something is broken, degraded, or reporting unexpected state. Knows the full observability stack, event schema, and where to look for root causes.Jul 2026
- 87code-explainerExplains complex code in clear, understandable terms. Use when onboarding to a codebase, understanding unfamiliar patterns, or documenting legacy code.Jul 2026
- 88debugging-specialistSystematic 4-phase debugging for complex and intermittent issues. Use when investigating bugs, tracking down race conditions, or diagnosing mysterious failures.Jul 2026
- 89gsd-debuggerInvestigates bugs using scientific method, manages debug sessions, handles checkpoints. Spawned by /gsd:debug orchestrator.Jul 2026
- 90bug-fix-planner-agentExpert in creating detailed technical plans for bug fixes. Use when a triaged bug report needs an implementation plan before development can start.Jan 2026
- 91bug-reporter-agentExpert in creating comprehensive bug reports. Use when a user needs to report a bug to guide them through capturing all necessary details.Jan 2026
- 92bug-triage-agentExpert in bug triage and root cause analysis. Use when a bug report needs to be analyzed, prioritized, and prepared for development.Jan 2026
- 93gsd-debug-session-managerManages multi-cycle /gsd:debug checkpoint and continuation loop in isolated context. Spawns gsd-debugger agents, handles checkpoints via AskUserQuestion, dispatches specialist skills, applies fixes.…Jul 2026
- 94gsd-debuggerInvestigates bugs using scientific method, manages debug sessions, handles checkpoints. Spawned by /gsd:debug orchestrator.Jul 2026
- 95autopsyFull codebase health assessment — quantified health scores (0-100) per module across 6 dimensions. Identifies highest tech debt. Use for rescue RECON or project diagnosis.Jul 2026
- 96debugRoot cause analysis ONLY — investigates errors, traces stack traces, forms/tests hypotheses. Does NOT fix code. Hands diagnosis to fix. Use when root cause is unknown.Jul 2026
- 97fixApply code changes from diagnosis or review findings. Locate → change → verify → report. Does NOT investigate — that's debug's job. Use after debug diagnosis or review findings.Jul 2026
- 98logic-guardianProtects complex business logic from accidental deletion — maintains logic manifest, pre-edit gates (state what you'll preserve), post-edit validation. Use on trading bots, payment systems, state…Jul 2026
- 99perfPerformance regression gate — detects N+1 queries, sync-in-async, missing indexes, memory leaks, bundle bloat. Investigate only, does NOT fix. Use before commit or deploy.Jul 2026
- 100problem-solverStructured reasoning — applies McKinsey-grade frameworks (5 Whys, Fishbone, First Principles, SCAMPER) with mandatory bias detection. Use for complex multi-factor problems, not simple linear analysis.Jul 2026
