Code review agents

jarrodwatts/claude-code-config

Agent

Use this agent when the user needs to find files, locate code implementations, or discover where specific functionality exists in the codebase. This includes questions like 'Where is X implemented?', 'Which files contain Y?', 'Find the code that does Z', or any request requiring searching through the codebase to…

K9i-0/ccpocket

Agent Claude Code

An agent that reviews code changes for bugs, design problems, readability, and framework-specific issues. It responds in Japanese and checks Dart, Flutter, and TypeScript details when those technologies are involved.

microsoft/agentrc

Agent ✓ vendor

Code review following VS Code contribution standards — correctness, lifecycle, naming, layering, accessibility, and security.

microsoft/agentrc

Agent ✓ vendor

Code review following VS Code contribution standards — correctness, lifecycle, naming, layering, accessibility, and security.

microsoft/agentrc

Agent ✓ vendor

Code review following VS Code contribution standards — correctness, lifecycle, naming, layering, accessibility, and security.

AlmanacCode/codealmanac

Agent Claude Code

Architectural code reviewer for codealmanac. Use after meaningful code changes, before merging, or whenever code shape feels off.

zhu1090093659/spec_driven_develop

Agent

Part of spec-driven-develop

Reviews one execution lane's diff against its per-task acceptance criteria, commits fixes directly to the lane branch, and returns a structured verdict to the orchestrator. Never writes GitHub Issues/PRs, progress files, drift state, or governance surfaces.

classmethod/tsumiki

Agent

Part of tsumiki

A code-review agent that checks files for OS command injection, a security flaw where outside input can make a program run unintended operating-system commands. It uses rules and guidance from Japan’s IPA web-security documents.

classmethod/tsumiki

Agent

Part of tsumiki

A specialized code-review agent that checks for cross-site scripting, a web vulnerability where untrusted content is executed as code in another user’s browser. It follows Japanese IPA web-security guidance.

getsentry/skills

Agent

Part of skills

Based on Anthropic's code-simplifier subagent: https://github.com/anthropics/claude-plugins-official/blob/main/plugins/code-simplifier/agents/code-simplifier.md -->.

piratuks/invoice-builder

Agent

Use this agent when reviewing a change for correctness, regressions, and verification in Invoice Builder.

Spielewoy/autoprompt-skill

Agent

L4 terminal leaf - GOAL-CHECK. Independent, adversarial, default-FAIL. Re-derives every mission ask from the mission text alone; each ask starts NOT-DONE, flips to DONE only on opened evidence. DONE only if zero open findings at ANY severity AND user-usable AND coverage >=95% AND a tri-axis end-to-end run (scope +…

guanyang/open-agent-hub

Agent

Part of open-agent-hub

Senior Technical Lead and Security Auditor specializing in code quality, correctness, and security audits.

kdcokenny/ocx

Agent

Expert code reviewer for security, performance, and philosophy compliance.

JuliusBrussee/caveman-code

Agent

Adversarial review of a plan or implementation. Pokes holes; assumes the author was over-confident.

JuliusBrussee/caveman-code

Agent

Critique a diff or a slice of code. Returns prioritized findings with file:line citations and suggested fixes.

Auties00/Cobalt

Agent Claude Code

Validates cross-cutting architectural patterns that span multiple files (delegation refactors, type mismatches across module boundaries, batched-vs-per-item call patterns) and applies fixes that no single-file validator can perform.

Auties00/Cobalt

Agent Claude Code

Performs a whole-codebase dead-code sweep across the discovered file set, identifying and removing fields/methods/classes that have no Cobalt references and no WA Web counterpart.

SethGammon/Citadel

Agent

Part of Citadel

Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…

solatis/claude-config

Agent

Reviews code and plans for production risks, project conformance, and structural quality.

stencila/stencila

Agent

Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.

Azure/azure-sdk-for-rust

Agent ✓ vendor

Azure SDK for Rust PR reviewer focused on API safety, guideline conformance, packaging, and release-readiness.

pydantic/pydantic-ai-harness

Agent Codex

Use as the final documentation gate before a capability PR merges. Verifies that a user-facing change keeps the capability README and its unified-docs page in sync with each other and with the code, that every snippet is runnable, and that links follow repo convention. Reports gaps; does not edit.

lucky-aeon/AgentX

Agent Claude Code

Use this agent when you need to review code structure, naming conventions, class/method organization, and directory hierarchy issues in your project. Examples: Context: User has just refactored a service layer and wants to ensure proper DDD layering and naming conventions are followed. user: "I just refactored the…