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.
Skill Claude Code
Use when the user wants to set up, switch between, or manage aenv namespaces — named bundles of CLAUDE.md, skills, MCP entries, and other AI-coding-harness config — in a project OR globally across $HOME. Triggers include aenv … mentioned directly, "switch namespace/profile", "activate/deactivate", "create/snapshot a…
Skill Claude CodeCodex
Runs the vibe-check static analyzer on Claude skills, agents, and CLAUDE.md files, then fixes the findings and trims token cost. Use when the user wants to lint, score, review, fix, or improve a skill or agent file, asks why a skill scores badly, or wants to audit skills they installed.
Skill Claude CodeCodex
A tool for creating, checking, adding to, and formatting CLAUDE.md files, which give an AI coding assistant instructions about a project.
nikolamin/claude-coordinator-kit
Plugin Claude Code
Bundles 13 skills · 3,228 tokens together
Coordinator-role skills for turning a Claude Code session into a pure build/verify dispatcher, packaged from the claude-coordinator-kit file-copy install.
Skill Codex
Universal behavioral principles to reduce agent mistakes across ALL task types — coding, research, configuration, file operations, writing, and communication. Derived from Andrej Karpathy's observations on agent pitfalls. Use when the agent needs guidance on thinking before acting, keeping solutions simple, making…
Skill Claude CodeCodex
Contract-driven, design-first quality guardrails for AI-assisted full-stack development. Prevents project chaos at scale by enforcing a five-layer protection system: Design → Contract → Implementation → Verification → PM. Use when: starting a new full-stack project, planning a non-trivial feature, dispatching…
Plugin Claude Code
Bundles 1 skill · 71 tokens together
Fable-5-style persistence for Claude Code: a Stop-hook guard that blocks premature stops on unfinished work, plus the /fablicate single-turn marathon-mode skill.
Cursor rule Cursor
MANDATORY — delegate ALL tasks to subagents via the Task tool.
Skill Claude Code
A repository setup skill that adds a reusable structure for working with coding agents, including instructions, skills, hooks, shared session state, and code checks.
naoufalelh/cursor-langgraph-starter
Cursor rule Cursor
Expert guidelines for generating and modifying LangGraph.js workflows. Apply when working with graph state, nodes, edges, or workflow files.
Cursor rule Cursor
Self-adaptive behavior improvement through post-intervention analysis and proactive rule/skill/hook suggestions. Load when analyzing agent behavior or suggesting rule/skill updates.
Cursor rule Cursor
Cursor rule "meta-generator" from cmnemoi/cursor-rules, covering rule template, steps, 1. structure, 2. frontmatter header and 3. rule content.
Cursor rule Cursor
Auto-decide whether to use local skills templates.
chickensintrees/ai-coding-rules
Cursor rule Cursor
Core rules for safe AI-assisted coding. Prevents data loss, wasted work, and over-engineering.
Skill Claude Code
Initialize the AI agent harness for any project. Generates AGENTS.md (canonical), CLAUDE.md that imports it, scoped .cursor/rules/.mdc, a .agents/ context directory with on-demand refs, enforcement hooks, and bootstrap scripts — all tailored to the current codebase. Use when starting work on a new project or when the…
s1mpLyy/multi-agent-execution-logging
Plugin Claude Code
Bundles 1 skill · 59 tokens together
Enforce consistent AI execution logs — central change log + optional per-agent logs — across any agent environment.
Skill Claude CodeCodex
Generate AI agent config files for any project — Cursor, Claude Code, Copilot, Windsurf, Cline, AGENTS.md. Use when setting up a new project for AI agents.
Plugin Claude Code
Bundles 2 skills, 7 commands, 2 hooks · 165 tokens together
AgentSync integration for Claude Code — sync AI tool configs across harnesses.
Cursor rule Cursor
You are running with oh-my-cursor, a multi-agent orchestration layer inspired by oh-my-claudecode.
aigoooowork/project-rules-bootstrap
Skill Claude CodeCodex
Use when initially creating AI coding rules for an existing repository without a trusted project-rules-bootstrap v2 baseline.
Cursor rule Cursor
Agentic design patterns for SentinelMesh AI.
Skill Claude CodeCodex
Switches the active Personetta persona via set-active. The target tool is auto-detected from the host agent (Claude Code here), so no --format is needed. Use when the user asks to change recipe, switch persona, or set active role.
Cursor rule Cursor
Comprehensive MCP tool usage guide with performance-driven selection strategies.
Cursor rule Cursor
Source-first guide to understanding AI agents — when the user wants to build, debug, or reason about an agent's internals (tool calling, memory, subagents, teams, compaction, safety), route them to the corresponding nanoagent chapter (100 lines of Python each).
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: