Debugging agents

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.

fusengine/agents

Agent

Part of fuse-ai-pilot

Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…

fusengine/agents

Agent

Part of fuse-ai-pilot

Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.

vasu31dev/playwright-ts-lib

Agent

Use this agent when you need to debug and fix failing Playwright tests.

crouton-labs/crouton-kit

Agent

Part of devcore

Expert analysis agent. Use for plan review, debugging hard problems, or architectural decisions. Read-only.

johnlindquist/claude

Agent

Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development.

korovin-aa97/talkthrough-mcp

Agent

Turns one narrated screen recording (processed by the talkthrough MCP server) into precise, evidence-backed findings plus a numbered confirm digest. Never files issues itself — it produces the findings JSON; filing happens only after the recording author approves.

lossless-claude/lcm

Agent

Part of lcm

Use this agent for deep investigation of lossless-claude health issues — goes beyond the doctor checklist to find root causes. Examples.

lossless-claude/lcm

Agent

Part of lcm

Use this agent when transcript ingestion fails, messages are missing after ingest, or JSONL parsing errors occur. Examples.

URaux/ArchViber

Agent Claude Code

Product slice analyst for ArchViber deepanalyze. Reviews the IR from a product/feature perspective: feature completeness, user journey gaps, missing feedback loops, and UX-visible technical debt.

raphaelmansuy/adk-code

Agent

Debug assistant that helps identify and fix bugs, errors, and unexpected behavior. Use when encountering failures, crashes, or unexpected behavior in code or tests.

Pinperepette/context-kernel

Agent

Part of context-kernel

T2 della pipeline kernel. Usalo quando serve il working set di un repo per un bug: dato un sintomo (stack trace/errore/path), esegue lo slicer deterministico sul grafo degli import e ritorna il manifest ordinato (seed, dipendenze, importatori, test correlati) con le esclusioni dichiarate. Read-only, non modifica nulla.

strelov1/diffray

Agent

Detects bugs, logic errors and runtime issues.

HypoxanthineOvO/Hypo-Workflow

Agent Claude Code

Part of hw

Hypo-Workflow Claude Code debug subagent.

Manikantareddy941-hash/Scorpion

Agent Claude Code

Use when a scan job (DAST/SBOM/Docker/Falco) is stuck, failing, or producing wrong results, to trace state across BullMQ queues, ioredis, and Dockerode container execution.

AndyShaman/senior-fable

Agent

Part of senior-fable

Long, context-heavy investigations that would pollute the main context - exploring a large slice of a codebase, grinding through logs, multi-file debugging, background research. Returns a distilled conclusion, not raw material. Used by senior-fable mode for digging work; not for quick lookups or mechanical edits.

nociza/cuti

Agent Claude Code

Code refactoring specialist for improving code quality, performance, and maintainability.

0p9b/TLDR

Agent

Part of tldr

Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is tldr-compressed so the main thread eats fewer tokens. Refuses to suggest fixes.

pvillega/claude-templates

Agent

Part of ct

Autonomous runtime failure debugger. Use when diagnosing errors, test failures, crashes, flaky tests, or unexpected runtime behavior — distinct from fixer (which fixes static review findings). Use when the user says "debug this", "why is this failing", "find the bug", "this test is flaky", or when stacktrace-triage /…

pvillega/claude-templates

Agent

Part of ct

Autonomous code-level security auditor. Use when reviewing code for OWASP Top 10, STRIDE categories, authentication/authorization bugs, unsafe deserialization, SSRF, IDOR, XSS, SQL injection, crypto misuse, secret handling, or supply-chain red flags in source code. Use after feature implementation, before merge, or…

code-payments/code-android-app

Agent Claude Code

Use this agent when bumping a dependency or evaluating the impact of a library update. It traces which modules depend on the library, checks for breaking API changes, identifies affected code paths, and suggests targeted test runs. Examples: user: "what's the impact of bumping compose to 1.12?" assistant: "I'll…

realgarit/fable-baton

Agent

Part of fable-baton

Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or security-sensitive changes (auth, billing, migrations, concurrency, caching, data consistency, public APIs). Also reviews work from cheaper agents for hidden flaws.

hamr0/liteagents

Agent

Implement code, debug, refactor, optimize.