17,399 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.
Skill Claude CodeCodex
Generate an evidence-backed Assumptions ledger for a Git diff, feature, endpoint, worker, migration, or code path. Use when reviewing a change, asking what could break, preparing a release, finding edge cases, assessing deployment safety, analyzing retries or concurrency, or designing failure-focused tests.
MCP server Claude CodeCodexCursor +2
Deterministic local-first context and impact maps for coding agents from tasks, issues, and diffs. Runs locally from the @aryam/fixmap npm package.
Skill Claude CodeCodex
Audit code for concrete correctness, security, performance, UX, and maintainability risks within an agreed scope. Use for code audits, PR feedback, or adversarial review. Produce evidence-backed findings, focused verification, and a bounded independent review when permitted.
Plugin Claude Code
Bundles 4 skills · 424 tokens together
Iterative multi-agent code review. Four cross-agent skills: review-anvil (engine — requested rounds of parallel codex-exec/claude-exec reviewers, adaptive continuation up to maxrounds, synthesized findings, default-on batched reproduction, and optional fix commits), review-anvil-readonly (engine with commitmode=none).
Plugin Claude Code
Bundles 3 skills, 7 commands, 1 agent, 3 hooks · 206 tokens together
Use Gemini from Claude Code to review code or delegate tasks.
ai-analyst-lab/ai-analyst-plus
Skill Claude CodeCodex needs its repo
Independently validate the current analysis with a second model (OpenAI Codex). Codex re-derives the same answer from the same data — blind to Claude's SQL and numbers — and the skill reports AGREE / DISAGREE / PARTIAL per finding. Use when the user types "/codex-review", or says "validate with codex", "codex review"…
StefanTheCode/dotnet-ai-toolkit
Agent Claude Code
Assesses a legacy .NET codebase and produces a pragmatic, incremental modernization roadmap — from .NET Framework to modern .NET, monolith to modular, and toward testability, DI, async, and current patterns — prioritized by risk and value. Use when the user wants to modernize legacy code, migrate from .NET Framework…
Skill Claude Code
Run Salesforce Code Analyzer on Apex, Trigger, Flow, or metadata files. Use after writing or modifying .cls, .trigger, .xml, or flow files. Also use when asked to scan, lint, or check code quality.
Skill Codex
Verify and proofread C code with ACSL using this repository's Frama-C MCP workflow, Frama-C WP static proof, EVA alarms, and optional E-ACSL runtime checks. Use when asked to run Frama-C, check ACSL contracts, explain WP goals, inspect EVA alarms, validate C annotations, or state what a C proof does and does not…
kaisa-kucherenko/claude-code-flow
Agent Claude Code
Fast, focused code reviewer (Claude Sonnet) for a sharp third opinion on a diff. Diff-first and quick — reads surrounding files only when a finding needs the context. Complement to Agatha (deep Opus review) and Arthur (Codex, file-aware) — same-diff, different lens, so they catch different classes of issues. Invoke…
Plugin Claude Code
Bundles 1 skill · 25 tokens together
Enforce module boundary contracts (readonly, no-new-exports) on Claude Code edits.
Plugin Claude Code
Bundles 13 skills · 304 tokens together
Code analysis skills for active development: find bugs, assess impact, plan refactoring, audit architecture, and more.
Skill Claude CodeCodex
Code review checklist and PR review workflow for Fleet QA agents.
Plugin Claude Code
Bundles 18 skills · 1,670 tokens together
easy-cheese. Cheese your code 🧀 — high-quality results as easy as cheese. A portable, harness-agnostic Agent Skills toolkit.
mduongvandinh/ai-best-practices-skills
Skill Claude CodeCodex
Audit toàn diện Node.js project (Express/NestJS/Fastify + TypeScript). Phát hiện violations bằng regex patterns, chấm điểm theo domain có trọng số. Tất cả nội dung báo cáo bằng tiếng Việt.
Plugin Claude Code
Bundles 8 skills, 8 commands, 5 agents · 743 tokens together
Evidence-driven development pipeline with multi-model code review.
chrisallenlane/claude-swe-workflows
Plugin Claude Code
Bundles 17 skills, 40 agents · 2,687 tokens together
Software engineering workflows with skills for planning, implementation, quality review, and structured thinking, plus a suite of specialist agents.
Plugin Claude Code
Bundles 1 skill · 63 tokens together
Exhaustive production-readiness audit: diverse-angle discovery passes to convergence, evidence-grounded per-finding verification, claim-vs-code checks, one flat severity-tagged list with file:line evidence.
Puli-AI-com/Puli-dev-guard-public-readme
Cursor rule Cursor
Mandatory code review and validation using the MCP analysis tool after every code change.
Skill Claude CodeCodex
Interpret and act on a moire finding. Use when moire check or moire verify reports a CONFLICT or BROKEN result against another agent's worktree, or when deciding how to respond to an overlap with concurrent in-flight work.
mhylle/claude-skills-collection
Plugin Claude Code
Bundles 38 skills, 13 agents, 5 hooks · 4,417 tokens together
A verification-first development pipeline for Claude Code: brainstorm to plan to phased implementation, with quality gates (verification-loop, code-review, security-review), adversarial review, and TaskTracker-native variants.
dancingteeth/unified-code-review
Skill Claude CodeCodex
Risk-first code review for PRs and branch audits: blast-radius triage, agent-authored discipline (tests first, intent evidence), call-graph pincer for integration defects between modules, then structural code-judo bar. Use when reviewing PRs, auditing agent-written diffs, catching rubber-stamp green CI, or wiring bugs…
Plugin Claude Code
Bundles 5 skills, 1 MCP server · 484 tokens together
MINE Is Not Everyone's — architecture, planning, execution, and adversarial review skills.
esparkman/claude-rubycritic-skill
Plugin Claude Code
Bundles 1 skill · 68 tokens together
Claude Code Skill for Ruby code quality analysis with RubyCritic. Model-invoked - Claude autonomously analyzes code quality, identifies smells, and provides refactoring insights.
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: