38,442 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.
michaelcjoseph/agent-coding-setup
Skill Claude Code
Pick the next pending task from a project's task list and drive it through the full implementation cycle: plan, implement, test, review, fix, simplify, and mark complete.
Plugin Claude Code
Bundles 10 skills, 7 agents · 1,139 tokens together
Agent-team-aware workflows, codebase analysis, and workflow skills for Claude Code.
Skill Claude CodeCodex
Evaluate prompts, skills, and Claude Code agents for correctness and optimization against the latest Claude best practices. Use when the user asks to "evaluate," "review," "audit," "optimize," "modernize," or "upgrade" a prompt, system prompt, SKILL.md, agent definition, or CLAUDE.md, or says things like "I wrote this…
truenorth-lj/adaptive-agent-skill
Plugin Claude Code
Bundles 2 skills · 105 tokens together
Make your AI agent get stronger with use — skill self-improvement, memory-skill feedback loops, and user profiling. Inspired by Hermes Agent's four-layer memory architecture.
Skill Claude CodeCodex
Generate a project-specific CLAUDE.md (or AGENTS.md) with coding standards, style guides, and best practices. Triggers on any request to set up a project, initialize coding standards, create or update CLAUDE.md or AGENTS.md, configure agent instructions, add code quality rules, or start a new codebase. Use this skill…
nextransit/andrej-karpathy-skills
Plugin Claude Code
Bundles 1 skill · 46 tokens together
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Skill Claude Code
Automatically discover what your AI agent believes by analyzing its real outputs — Pattern-Based Distillation for agent behavior.
Agent Claude Code
Implementation agent for complex, multi-step coding tasks. Use proactively when delegating code writing, bug fixing, refactoring, or any task requiring both exploration and modification. Replaces built-in general-purpose for all implementation tasks.
GYF0311/karpathy-code-principles-research
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.
clawsouls/clawsouls-claude-code-plugin
Plugin Claude Code
Plugin marketplace listing 1 plugin: clawsouls.
Plugin Claude Code
Bundles 7 skills, 3 agents, 1 hook · 633 tokens together
Standard AI-dev setup: /factory-init stamps a repo with @claude workflows, plugin wiring, a marker-fenced CLAUDE.md, and a docs/memory/ index; /factory-update refreshes the standard parts. Ships shared skills (model routing, release flow, repo memory, CI agent ops), routed agents (implementer/reviewer/researcher), and.
Skill Claude Code
Create or update CLAUDE.md files following best practices for optimal AI agent onboarding.
Skill Claude CodeCodex
Invoke when the user says "harvest", "run harvest", or "harvest " inside the claude-mallet repo. Promotes project-specific skills from a target project into the framework base and surfaces skill overrides for review.
Plugin Claude Code
Bundles 25 skills, 12 commands, 2 hooks · 2,082 tokens together
Claude-Rudder — collection of utilities to smoothen Claude Code UX. Context-gate workflow, log/blocker capture, plugin/MCP primitives, repo & docs spawning, and the canonical user-data storage convention. (Session-hopping skills moved to Claude-Hopper.).
chentao326/codex-claude-handoff
Skill Codex
A file-based handoff process between Codex and Claude Code. It moves work through six phases—specification, planning, building, review, polishing, and committing—using signal files to show which phase is current.
Skill Claude CodeCodex
Use when facing 3+ independent subtasks touching different files that would benefit from parallel agent execution in isolated worktrees.
nkipler/claude-code-workspace-architect
Skill Claude CodeCodex
Use when setting up or improving a Claude Code workspace with CLAUDE.md, session management, agents, or folder structure. Also for workspace best practices questions.
MCP server Claude CodeCodexCursor +2
One of 3 in .mcp.json
MCP server "sequential-thinking" as configured in hlop3z/claude-ai-dangerous. Launched with cmd /c npx -y @modelcontextprotocol/server-sequential-thinking.
Skill Claude CodeCodex
Aktiviert Fable-artiges, systematisches Vorgehen für komplexe, mehrstufige Aufgaben: explizites Planen (Stage-Map), paralleles Delegieren an Sub-Agenten und verpflichtende Selbst-Verifikation an jeder Stufe. Auslösen, wenn der Nutzer sagt "be systematic", "act like Fable", "deep work mode", "mach das…
Carchaloneo22/creador-de-frameworks-agenticos
Skill Claude CodeCodex
Use this skill whenever the user wants to design, build, set up, scaffold, structure, or improve the agentic framework of a Claude project — meaning the architecture of memory (CLAUDE.md, MEMORY.md), subagents, skills, hooks, and MCP connections. Triggers include phrases like "montar el framework del proyecto"…
sebastianluuque-collab/creador-de-frameworks-agenticos
Plugin Claude Code
Bundles 6 skills, 11 agents · 1,648 tokens together
Meta-plugin que diseña y construye el framework agéntico completo de un proyecto Claude: arquitectura de memoria (CLAUDE.md + MEMORY.md), skills personalizadas, subagentes especializados, hooks y conexiones MCP.
Vincent-chao-lang/context-engineering-kit
Command Claude Code
A project-initialization command that creates or completes a Context Engineering directory structure for AI-assisted collaboration. The description is in Chinese and gives no further implementation details.
Plugin Claude Code
Bundles 4 skills, 1 hook · 281 tokens together
Proxify's Claude Code acceleration toolkit — skills, agents, and guides for agentic engineering.
hg-pyun/claude-code-marketplace
Plugin Claude Code
Bundles 1 skill · 276 tokens together
Thinking-partner skills that keep the pen in your hand: a Socratic design interview and a predict-then-verify codebase reader.
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: