19,479 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.
mhylle/claude-skills-collection
Plugin Claude Code
Bundles 35 skills, 16 agents, 5 hooks · 8,732 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, TaskTracker-native variants, and a HUD that shows a phase's progress and guards the orchestrator.
Plugin Claude Code
Bundles 1 skill · 237 tokens together
Autonomously watch a single pull request and drive its review feedback, failing CI checks, and merge conflicts to completion without supervision. Each round it fetches every unaddressed review and comment (from Claude, CodeRabbit, Copilot, other bots, and humans), the PR's check runs, and its mergeability; addresses…
d-padmanabhan/agent-engineering-handbook
Cursor rule Cursor needs its repo
Secure, idiomatic, maintainable Go with evidence-based performance; applies to generation and review.
Plugin Claude Code
Bundles 6 skills, 2 commands · 266 tokens together
Code quality, CLI, and test-writing guidelines with emoji enhancement.
Skill Claude CodeCodex needs its repo
Match functions between two builds of a program with Diaphora, recover symbol names from a build that has them onto stripped builds, and emit per-function pseudocode diffs documenting what changed. Use for version lineage archaeology, renaming stripped binaries from an unstripped sibling, and reconstructing…
PacktPublishing/The-Claude-Code-Operating-Model
Skill Claude Code
Review code for security vulnerabilities, performance issues, and coding best practices. Activate when the user asks to review code, check code quality, give feedback on code changes, or audit a file.
Skill Codex
For requested code audits or deep reviews, produce evidence-ranked findings across relevant risks.
Command Claude Code
Analyzes the codebase for correctness, architecture, quality, security, and performance, providing a prioritized list of actionable issues.
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.
Plugin Claude Code
Bundles 18 skills · 1,706 tokens together
easy-cheese. Cheese your code 🧀 — high-quality results as easy as cheese. A portable, harness-agnostic Agent Skills toolkit.
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…
olehsvyrydov/AI-development-team
Plugin Claude Code
Bundles 43 skills, 50 commands · 5,434 tokens together
A specialist agent team plus an enforced, proportional workflow: role agents that self-route to deep references, cross-cutting process skills for the gate contract, work-item lifecycle, proving a change landed, review tiering, model selection, research method, grounded-answer audit and pull-request completion, and…
Cursor rule Cursor
Apply language-agnostic clean-code discipline to all code writing, editing, reviewing, testing, and refactoring, including file placement, single responsibility, and verified completion.
Skill Claude CodeCodex
Review completed code or a plan with right-sized specialist agents.
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.
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.
prime-radiant-inc/parallel-adversarial-review
Plugin Claude Code
Bundles 2 skills · 213 tokens together
Two skills for adversarial code review. parallel-adversarial-review dispatches two same-model reviewer subagents in parallel under a competitive scoring frame, aggregating findings and taking the worst severity on disagreement. multi-model-adversarial-review extends this to N installed coding-agent CLIs (claude, codex.
Skill Claude CodeCodex
Compiled architectural rules and lessons from the Totem knowledge base. Load this when reviewing code for pattern violations or architectural drift.
Skill Claude CodeCodex
Perform thorough code review and audit of implemented features. Compares implementation against the technical plan, checks for AI-specific risks, and provides actionable feedback. Activate for: review, audit, code quality assessment, security review.
Skill Claude CodeCodex
Assistant-guided Claude Code lint-surface sweep for cclint: compare the changelog gap with an available installed binary, then review and update relevant schemas, lint rules, tests, and docs. Use when a new Claude Code version ships, the AGENTS.md surface row is stale, or a changelog claim needs checking.
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: