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.
Skill Claude CodeCodex
Find duplicate functions and eliminate them so they stay gone. Triage tl dupes output by tier, apply the right consolidation pattern, and lock the win with a duplication-ratchet test. Use when asked to dedupe, remove duplication, consolidate copy-paste, clean up repeated helpers, or act on tl dupes output.
Johnny-zbb/code-quality-evaluator
Skill Claude CodeCodex
Evaluate repository or project code quality and produce an evidence-based scorecard. Use when asked to review code quality, score a project, assess maintainability, inspect technical debt, evaluate architecture/readability/refactoring health/engineering practices/code smells, compare project quality, or prepare a…
chriswritescode-dev/opencode-forge
Command Claude Code
You are reviewing a completed implementation against its original plan.
Skill Claude Code
Use when working in a repository that has jjj initialized (a .jj/jjj-meta directory), or when coordinating several agents on shared work — tracking problems, proposing competing solutions, critiquing them, and reaching decisions that survive history rewrites. Also use when asked to set up multi-agent collaboration…
Plugin Claude Code
Bundles 4 skills · 241 tokens together
Multi-angle project review covering expert audits, visitor comprehension testing, task-completion smoke tests, and adversarial nitpick passes. Use when you want a thorough pre-launch review or a targeted quality check from any angle.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when requesting a code review before pushing changes. Pre-commit verification pipeline — static security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. Use after code changes and before committing, pushing, or opening a PR.
Bastioned-successor320/learn-nanobot
Skill Claude CodeCodex
A code-review procedure for Python, JavaScript, and Go programs. It checks security, performance, maintainability, naming, error handling, and testing.
Plugin Claude Code
Bundles 3 skills, 7 agents · 641 tokens together
Comprehensive feature development workflow with specialized agents for 1C:Enterprise codebase exploration, architecture design, and quality review.
dangindev/antigravity-awesome-workspace-skill
Cursor rule Cursor
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Skill Codex
Run a skeptical Claude review over the current diff or branch range.
wezendy/elon-musk-algorithm-skills
Cursor rule Cursor
Musk 5-step engineering algorithm. Primarily for reviewing and cleaning up existing systems. Apply in strict order: question requirements, delete parts, simplify, accelerate, automate. Bias toward deletion. Never advance to a later step until earlier steps are visibly complete.
Plugin Claude Code
Bundles 1 agent, 3 hooks, 1 MCP server · 129 tokens together
Live code graph for Claude Code: exact references, structural grep, change impact and a post-edit check, from a local index with no model or network.
Skill Claude CodeCodex
Reserved-string and numeric-coercion check, inspired by the Big List of Naughty Strings. Finds where literal "null", "undefined", "None", "NaN", "proto", "NO", 1E02, 0x10, -0, or a 17-digit ID become a blank field, a wrong number, or a crash. Types each case into a live test environment's forms and submits it…
Metalnib/dotnet-episteme-skills
Plugin Claude Code
Bundles 14 skills, 3 commands, 2 hooks, 1 MCP server · 1,029 tokens together
Practical, production-tested .NET skills that provide enterprise-proven instructions for AI-assisted development.
Agent Claude Code
Reviews pull requests for security vulnerabilities, logic bugs, data loss risks, and API misuse. Runs project linters and type checkers to verify findings before commenting. Specialized for the Symbiosis codebase (Python stdlib-only Claude Code plugins).
Plugin Claude Code
Bundles 25 skills · 3,816 tokens together
Structured dev workflow with spec, user-global risk RAG, task breakdown, execution, verify, qa-gate, fix loops, and audits.
robertbagge/claude-roadhouse-plugin
Plugin Claude Code
Bundles 5 skills, 3 hooks · 160 tokens together
Iterative code improvement loop using /proud and /exquisite introspection. Run /rounds to polish your code until it's world class.
Skill Claude Code
Run code, architecture, systems, or proposed changes through a panel of world-class engineering perspectives. Each panelist reads the ACTUAL source files before judging. Use this skill whenever the user asks to: review code quality, get expert opinions, assess architecture decisions, evaluate a refactor plan, critique…
ensingm2/AI-threat-modeling-rulesets
Skill Claude Code
Adversarial validation for all stages. Detects fabrications, identifies analytical flaws, challenges assumptions, makes approval decisions. Seeks problems rather than confirming quality. Does NOT complete deliverables or fix issues.
Plugin Claude Code
Bundles 1 skill · 59 tokens together
Run independent Claude and Codex reviews, cross-pollinate findings, and return one synthesis.
Cursor rule Cursor
Radical-simplicity coding guidelines distilled from George Hotz's public philosophy. Use when writing, reviewing, refactoring, or porting code — to remove before adding, collapse duplication, keep interfaces narrow, and look at what code actually does instead of assuming.
Command Claude CodeCursor
This command performs comprehensive code quality checks. Use it before commits or when implementation is complete.
MCP server Claude CodeCodexCursor +2
One of 3 in claude_desktop_config.json
MCP server "unified-diff-mcp" as configured in gorosun/unified-diff-mcp. Launched with bun /Users/username/projects/unified-diff-mcp/src/index.ts. Needs 5 environment variables to run.
Skill Claude CodeCodex
Senior-QA review of a code change before you ship it. Sizes the diff, then launches QA reviewers — a regression hunter ("does this break anything that already worked?") and a change reviewer ("does this actually do what it claims, including edge cases?") — and consolidates ONE evidence-based SIGN OFF / SIGN OFF WITH…
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: