Code review

26,083 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

antonbabenko/deliberation

Instructions file Claude CodeCodex

Claude Code instructions for antonbabenko/deliberation, covering claude.md, what this is, development commands, test plugin locally (loads from working directory) and run setup to test installation flow.

not rated 143 +5 changed today B 9,363 tokens original MIT

drift

338

fiberplane/drift

Skill Claude Code

Drift doc-to-code anchor conventions. Use when editing code that is bound by drift docs, updating docs, working with drift.lock, or when drift check reports stale anchors.

not rated 141 +2 2mo ago A 38 tokens original MIT

pr-verify

339

docglow/docglow

Skill Claude Code

Verify a Docglow change actually works before submitting or merging a PR. Runs the conformance suite, then a behavioral verification pass (flag matrix, artifact-join spot checks, pipeline contract sweep, payload budget). Use when reviewing a PR, self-reviewing a branch before opening a PR, or when asked to "verify…

not rated 141 +2 24d ago A 79 tokens original MIT

sortie-ai/sortie

Instructions file GitHub Copilot

Copilot instructions for sortie-ai/sortie, covering sortie coding & review standards, 1. layered imports (downward only; violation is critical), 2. concurrency safety, 3. workspace path safety (critical: security boundary) and 4. persistence (sqlite).

not rated 139 +4 yesterday A 1,030 tokens original Apache-2.0

beava-pr-review

342

beava-dev/beava

Skill Claude Code

Reviews a beava PR diff for real bugs, beava-specific architectural invariants, and AI-generated "slop" patterns (hollow code, phantom imports, inflated comments, disconnected pipelines). Produces a structured BLOCK / WARN / NIT report keyed by file:line. Use when asked to "review this PR", "check for AI slop", "PR…

not rated 138 +1 3mo ago A 119 tokens original Apache-2.0

verification

343

AI45Lab/Code

Agent Claude Code

You are an adversarial verification specialist. Your job is to find evidence, not to reassure.

not rated 137 2mo ago A 0 tokens original MIT

grix-code-review

344

askie/grix

Skill Codex

Audit Grix diffs and pull requests for correctness, regressions, security, lifecycle safety, and cross-component contract consistency. Use when reviewing backend, Flutter frontend or admin, voicebridge, database migration, Kubernetes, protocol, agent-adapter, bug-fix, feature, or refactor changes in the Grix…

not rated 137 +7 today A 70 tokens original Apache-2.0

review_prs

346

aws-samples/sample-autonomous-cloud-coding-agents

Command Claude Code ✓ vendor

Hold the same bar as reviewpr: a Principal AWS Solutions Architect who is direct, specific, justifies every concern with a concrete risk and a file:line, distinguishes blocking issues from nits, and never rubber-stamps. This command orchestrates that single-PR review across a set of PRs — it does not restate the…

not rated 136 +4 yesterday A 0 tokens MIT-0

codex-guard

347

Akimiya-z/codex-guard

Skill Claude CodeCodex

Pre-submit hygiene check for AI-agent-authored pull requests. Use this skill whenever you are about to open or update a pull request: it runs the codex-guard CLI locally, verifies the diff contains no leftover TODO/FIXME/XXX markers and no hardcoded secrets, checks that commit subjects follow conventional commits, and…

not rated 136 +37 2d ago A 85 tokens original MIT

github-review

348

holon-run/holon

Skill Claude CodeCodex

Review a GitHub pull request by collecting GitHub context, applying evidence-backed review rules, and optionally publishing one review.

not rated 134 changed 2d ago A 27 tokens original Apache-2.0

code-review

349

terryso/AutoQA-Agent

Command Claude Code

Perform an ADVERSARIAL Senior Developer code review that finds 3-10 specific problems in every story. Challenges everything: code quality, test coverage, architecture compliance, security, performance. NEVER accepts looks good - must find minimum issues and can auto-fix with user approval.

not rated 134 7mo ago A 58 tokens original MIT

repo-explorer

350

Mor-Li/ccblog

Agent Claude Code

Use this agent when you need to analyze a GitHub repository by cloning it and performing deep code analysis. This agent should be called when the user provides a GitHub (or GitLab) repository URL and wants to understand its architecture, core modules, and implementation details for writing a technical blog…

not rated 134 1mo ago A 500 tokens original MIT

code-reviewer

351

Koomook/fastcampus-ai-agent-vibecoding

Agent Claude Code

Use this agent when you need to review recently written code for quality, best practices, potential bugs, or improvements. This agent should be called proactively after completing a logical chunk of code implementation, such as:\n\n- After writing a new function or class\n- After implementing a feature or fixing a…

not rated 134 7mo ago A 0 tokens

spotpatch

352

huanglvjing/spotpatch

Skill Codex

A development workflow for React that connects a selected page element to its JSX or TSX source code and gathers context for review.

not rated 134 +2 yesterday A 93 tokens original MIT

verify-pr

353

go-to-k/cdkd

Skill Claude Code

Comprehensive PR readiness check before merge. Run quality checks, tests, CI, documentation, AWS resource cleanup, and code review.

not rated 132 +10 changed 2d ago A 29 tokens original Apache-2.0

adversarial-reviewer

354

302ai/302-AI-Studio

Skill Claude CodeCodex

Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's…

not rated 131 5d ago A 69 tokens AGPL-3.0

review-pr

355

zetaalphavector/RAGElo

Skill Claude CodeCodex

Reviews pull requests for code quality, pattern conformance, architecture alignment, security, and completeness. Use when asked to review a PR, validate code changes, or check if a PR is ready for merge.

not rated 131 +1 24d ago A 44 tokens original Apache-2.0

appautomaton/agent-designer

Skill Claude CodeCodex

Delegate tasks to Codex CLI for prototyping, debugging, code review, implementation handoff, cross-model second opinions, and multi-turn Codex sessions via SESSIONID.

not rated 130 18d ago A 42 tokens

PeakCode AGENTS.md

357

PeakCode-AI/PeakCode

Instructions file CodexOpenCode

Instructions for PeakCode-AI/PeakCode, covering agents.md, task completion requirements, pr review, project snapshot and core priorities.

not rated 129 +2 1mo ago A 1,493 tokens original MIT

framework-review

358

lync-cyber/CataForge

Skill Claude Code

A review process for the configuration that makes an agent framework work, including agents, skills, hooks, rules, and workflows. It checks whether these pieces are complete, consistent, connected, and compliant with the framework’s rules.

not rated 128 1mo ago A 118 tokens original MIT

kngwyc3/Agent-Learning-Hub

Skill Claude CodeCodex

Use when reviewing a code diff or pull request for correctness, regressions, safety issues, and missing tests.

not rated 128 +2 1mo ago A 27 tokens original MIT

aaddrick/claude-pipeline

Agent Claude Code

Frontend CSS/HTML craftsman specializing in bulletproof, flexible, progressively-enhanced interfaces. Use for CSS architecture, responsive design, Blade templates, and frontend code review. Prioritizes semantic CSS over utility frameworks. Defers to laravel-backend-developer for PHP, controllers, and server-side logic.

not rated 128 +2 6mo ago A 69 tokens original MIT

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: