code analysis agents

elbruno/graphify-dotnet

Agent

Your AI team. Describe what you're building, get a team of specialists that live in your repo.

camilooscargbaptista/architect

Agent

╔══════════════════════════════════════════════════════════════╗ ║ ║ ║ ANTES de escrever QUALQUER linha de código, os seguintes ║ ║ artefatos DEVEM existir e ser APROVADOS pelo humano: ║ ║ ║ ║ 1. 🎨 MOCKUP (se tem UI) ║ ║ → Todas as telas, estados, erros, modais, mensagens ║.

camilooscargbaptista/architect

Agent

Agent "QA-TEST-ENGINEER" from camilooscargbaptista/architect, covering 🧪 qa test engineer, metas inegociáveis, ⚠️ módulos sem cobertura de teste, pirâmide de testes and processo.

camilooscargbaptista/architect

Agent

Agent "TYPESCRIPT-BACKEND-DEVELOPER" from camilooscargbaptista/architect, covering 🔧 typescript backend developer, stack, domínio & contexto de negócio, princípios (solid + clean architecture) and módulos do projeto.

luuuc/sense

Agent Claude Code

Adversarial Loop 3 evaluator for the vertical bench. Diagnoses sub-floor verdicts through the six-branch taxonomy, standing only on mechanical verifier output. WIN confirmation lives in bench-win-confirm.

luuuc/sense

Agent Claude Code

Reads any bench run (validation or paid, win or loss) and returns the material for a better scenario - where the baseline struggled and what Sense reached that it did not. Never issues a verdict; never diagnoses a loss (that is bench-evaluator).

luuuc/sense

Agent Claude Code

WIN-confirmation vertex for the vertical bench. Runs the five mechanical DoD checks on a WIN verdict and confirms or bounces. Never diagnoses a sub-floor verdict; never fault-finds a clean win.

MercurieVV/ScalaSemantic

Agent Claude Code

Implements a single coding task end-to-end in an assigned git worktree for this Scala project. Owns the FULL lifecycle — create worktree, implement, self-sanity-check, commit, push, merge, report. Use as the "claude" worker engine in the orchestration pool ONLY for hard Scala tasks (deep type/implicit reasoning…

MercurieVV/ScalaSemantic

Agent Claude Code

Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.

MercurieVV/ScalaSemantic

Agent Claude Code

Cheap per-issue classifier for recursive task planning. Reads one GitHub issue, checks task-tree markers, and returns whether to skip, mark as an implementation-ready leaf with executor routing, or send to the smart planner for subtask expansion.

graphpilot-oss/graphpilot

Agent

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

graphpilot-oss/graphpilot

Agent

Issues and PRDs for this repo live as GitHub issues at graphpilot-oss/graphpilot. Use the gh CLI for all operations.

graphpilot-oss/graphpilot

Agent

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

Loctree/loctree

Agent

Use this agent immediately before performing an Edit, Write, or MultiEdit on a non-trivial source file when the parent agent needs structural orientation it doesn't have. Returns a concise briefing of file dependencies, consumers, exports, hub status, and recent activity. Trigger when the user says "before I edit X…

Loctree/loctree

Agent

Use this agent BEFORE planning a refactor — module split, module merge, signature change to a public API, file rename, dependency direction reversal, framework migration. Returns a migration plan with: blast radius (transitive consumers), twins to consolidate or split, hotspots that must be touched together, cycles…

Loctree/loctree

Agent

Use this agent for senior-level structural review of a codebase or a specific change set, focused on architectural integrity rather than line-level style. Trigger when the user asks for "structural review", "architecture audit", "senior review", "is this well-designed", "review this refactor", "/structural-review"…

armelhbobdad/oh-my-skills

Agent Claude Code

Act as an information extraction and compression specialist. Your sole purpose is to produce a lossless, token-efficient distillate from source documents.

armelhbobdad/oh-my-skills

Agent Claude Code

Act as a document reconstruction specialist. Your purpose is to prove a distillate's completeness by reconstructing the original source documents from the distillate alone.

gupta29470/codewalk

Agent

AI-powered codebase intelligence assistant.

MohmmedAshraf/symbiote

Agent

Use this agent to validate architectural integrity, detect structural issues, and enforce layer boundaries. Examples.

MohmmedAshraf/symbiote

Agent

Use this agent to review code changes using Symbiote's code knowledge graph for deep, context-aware analysis. Examples.

MohmmedAshraf/symbiote

Agent

Use this agent to plan safe refactoring operations using dependency analysis. Examples.

rhi-zone/normalize

Agent Claude Code

does exactly the one thing asked, checks before it claims, and stops when the answer is given.

semihkayan/codeweave-mcp

Agent Claude Code

Executes the plan literally. Uses a light model — the plan must be straightforward and unambiguous.