Debugging agents

2,740 tagged Debugging, measured the same way as everything else here.

Browse within: claude-code-plugin 180ai-coding 113code-quality 44agentic-coding 39plugin 35Multi-Agent 34agent-orchestration 34Autonomous Agents 29agentic-workflow 29claude-code-skills 28claude-ai 27github-copilot 27opencode 27copilot 26

gsd-debugger

481

rafreid/gsdview

Agent Claude Code

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

not rated 5 7mo ago A 30 tokens

bug-reporter

482

ArchAstro/archagents

Agent

Tracker-side specialist for the cross-team bug relay. It runs two of the relay's embedded stages.

not rated 5 18d ago A 0 tokens original MIT

bug-resolver

483

ArchAstro/archagents

Agent

Owning-side specialist for the cross-team bug relay. It runs the relay's Triage stage: reproduce the defect a partner team reported, classify the resolution, and write guidance the partner can act on without a meeting.

not rated 5 18d ago A 0 tokens original MIT

code-review

484

tigu77/tiguclaw

Agent

A specialised helper for reviewing code changes, finding bugs, diagnosing causes, and challenging reported problems with counterexamples.

not rated 5 4d ago A 97 tokens original Apache-2.0

explorer

485

vector233/repo-continuity

Agent Claude Code

Use proactively for read-only file and symbol discovery, execution tracing, log inspection, and evidence gathering before a change or review. Use @explorer when a cost-controlled exploration pass is required.

not rated 5 16d ago A 41 tokens original MIT

boualam

486

adriancarriger/lambda

Agent Claude Code

Handles routine code quality tasks (linting, formatting, type checking) and trivial busywork. Runs iteratively until all checks pass. Use for cleanup tasks you don't want cluttering your main context.

not rated 5 6mo ago A 43 tokens original MIT

tdd-guide

487

Wania-Kazmi/claude-code-autonomous-agent-workflow

Agent Claude Code

Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.

not rated 5 7mo ago A 42 tokens

uwuclxdy/agenticat

Agent

Evidence-first diagnosis of bugs with an unclear or disputed cause: multiple suspects, a 'started failing recently', symptoms across unrelated components. Builds repro harnesses, runs A/B and version-matrix experiments, returns a hypothesis ledger with an attributed cause. Never fixes or posts; writes only its harness…

not rated 5 4d ago A 72 tokens original MIT

debugger

489

IvanKuzyshyn/dotfiles

Agent Claude Code

Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.

not rated 5 2mo ago A 23 tokens copy · 89% Unlicense

gsd-debugger

490

KhanXBT/get-shit-done-antigravity

Agent

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

not rated 5 6mo ago A 30 tokens copy · 84% MIT

audiobash-perf

491

jamditis/audiobash

Agent Claude Code

You are a performance engineer specializing in Electron application optimization.

not rated 5 5d ago A 0 tokens original MIT

detective

492

mfmezger/ai_agent_dotfiles

Agent Claude Code

Identify code smells, best practices violations, and test smells across Python, Go, and Rust codebases with language-specific guidance and recommendations.

not rated 5 1mo ago A 30 tokens original MIT

code-review-fix

493

rshade/mcp-devtools-server

Agent Claude Code

You are a senior software engineer performing comprehensive code reviews and implementing fixes. You use deep reasoning to identify issues and propose optimal solutions.

not rated 5 4d ago A 0 tokens original Apache-2.0

dependency-manager

494

HKTITAN/cursor-best-practices

Agent

Reviews and manages dependencies including updates, security audits, and compatibility checks. Use to keep dependencies up-to-date and secure.

not rated 5 5mo ago A 27 tokens original MIT

go-coder

495

sergeyklay/.agents

Agent Codex

Implement features, fix bugs, and write production code following architectural constraints and best practices in Go. Use when asked to build, code, implement, develop a feature, execute a plan, or write production code. Also use when the user mentions Go, Golang, or specific Go libraries or frameworks. Do NOT use for…

not rated 5 changed today A 91 tokens original Apache-2.0

ts-coder

496

sergeyklay/.agents

Agent Codex

Implement features, fix bugs, and write production code following architectural constraints and best practices in TypeScript. Use when asked to build, code, implement, develop a feature, execute a plan, or write production code. Also use when the user mentions TypeScript, TS, or specific TypeScript libraries or…

not rated 5 changed today A 93 tokens original Apache-2.0

shell-runner

498

EmanuelVogt/skills

Agent

Runs a terminal command in this repo (test, typecheck, lint, build, script) without dumping the output into the main context — full log to a file, returns exit code + the literal failures. For the main window's gates: the orchestrator's Build gate per wave and the Verifier's Final gate; a spec-worker runs its own…

not rated 5 5d ago A 126 tokens original MIT

auditor

499

gapra/gp-nuxt-migration-mcp

Agent

Specialized agent for analyzing Nuxt 2 codebases and detecting migration patterns. Read-only operations only.

not rated 5 4mo ago A 24 tokens

Blazor Reviewer

500

srnichols/plan-forge

Agent

Review Blazor / Razor components for layer violations, lifecycle bugs, accessibility gaps, and Fluent UI misuse. Use for PR reviews on .razor / .razor.cs files.

not rated 5 yesterday A 40 tokens original MIT

quality-scout

501

honeycomb-Technologies/Mitsuro

Agent Cursor

Read-only scout for the quality-improve loop. Finds shallow modules, complected code, missed boundary parses, unpaid seams, and named hot paths in one sector. Use when quality-improve is running and a Scout Report is needed. Never edit files.

not rated 5 3d ago A 56 tokens original MIT

worker

502

markmhendrickson/ateles

Agent Claude Code

Implementation agent for code contributions to other agents' repos. Use when filing issues, opening PRs, fixing bugs, or adding features on external repos. Runs in isolated worktree to avoid conflicts.

not rated 6 today A 41 tokens original MIT

hunt

504

SukramJ/openccu-loom

Agent Claude Code

Adversarial read-only defect hunt over a named area — wire handling, resource leaks, concurrency, silently dropped events, unwired seams. Produces ranked candidates with a reproduction path. It finds and argues; it never fixes.

not rated 5 4d ago A 48 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: