Building agents

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.

cursorrules

5665

danfmaia/agent-teams

Cursor rule Cursor

Agency Swarm is a framework that allows anyone to create a collaborative swarm of agents (Agencies), each with distinct roles and capabilities. Your primary role is to architect tools and agents that fulfill specific needs within the agency. This involves.

not rated 2 1y ago A 3,600 tokens

loopath

5666

encircleacity2/loopath

Skill Codex

Interactive bilingual course skill for learning loop engineering through Loopath. Use when a user wants to start, continue, install, teach, study, verify, or be quizzed on the Loopath course; when they ask for an agent-guided course on coding-agent loops, harness design, AGENTS.md, action schemas, tool use, policy…

not rated 2 3mo ago A 103 tokens original MIT

codex-long-jobs

5667

zycdev/codex-long-jobs

Skill Codex

Run, supervise, or explicitly cancel long-running, background, async, or detached processes from OpenAI Codex CLI and wake or resume the owning Codex session on process completion, without LLM/model polling while the job runs. Use when asked to run something in the background, start or stop a long build, test…

not rated 2 26d ago A 131 tokens original MIT

skill-creator

5668

MikeManifold/codex-unified

Skill Codex

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

not rated 2 29d ago A 46 tokens copy · 70% Apache-2.0

ytunahankskn/oh-meine-excode

Skill Claude CodeCodex

Use when the user wants Codex to split work across multiple subagents, especially for implementation plus exploration or verification in parallel.

not rated 2 5mo ago A 31 tokens original MIT

david-skills

5670

edwardyen724-g/david-vscode

Plugin Claude Code

Bundles 3 skills, 3 hooks · 307 tokens together

David's built-in skills — create-agent, create-job, create-dashboard — bundled with the David VS Code extension and auto-loaded into every David-spawned agent's Claude Code session via --plugin-dir.

not rated 2 3mo ago A tokens not measured original MIT

token-rat-esp

5671

0xCyberBerserker/token-rat-esp

Skill Codex

Aggressive token and output minimization for coding agents. Use when the user wants concise technical Spanish, minimal useful output, small patches, and strict scope control.

not rated 2 3mo ago A 38 tokens original MIT

extension-expert

5672

thoreinstein/extension-creator

Skill Claude CodeCodex

Use this skill when the user wants to create, scaffold, or configure a new Gemini CLI extension. It provides expert guidance on manifest structure, MCP servers, Agent Skills, and release workflows.

not rated 2 7mo ago A 42 tokens original MIT

live-voice-agent

5673

davidjdseo/live-voice-agent

Skill Claude CodeCodex

A voice-control rule for a gated Korean-and-English voice assistant. It defines which wake phrases start listening and how spoken replies must be formatted.

not rated 2 29d ago A 23 tokens original MIT

rosetta

5674

tjboudreaux/rosetta

Plugin Claude Code

Bundles 1 skill, 3 commands · 331 tokens together

Reconcile every AI coding agent's conversations (Claude Code, Codex, Gemini, Cursor, Aider, opencode, Cline + 11 more) with git and docs into one cited ground truth, and distill durable ADR/PDR/BDR decision records.

not rated 2 1mo ago A tokens not measured original MIT

agent-security-audit

5675

dacuma-labs/agent-security-audit

Skill Claude CodeCodex

Audits AI agent projects for security risks in prompts, tools, memory, RAG, and permissions. Use when: the user asks to review agent security, harden an agentic system, check for prompt injection risks, audit tool permissions, or secure an AI assistant before deployment. Do NOT use for: projects with no agentic…

not rated 2 6mo ago A 82 tokens original MIT

agent-ops

5676

Vann-Dev/AgentBridge

Skill Claude CodeCodex

Agent Ops is the skill of managing and coordinating multiple agents to work together effectively. It involves assigning tasks, tracking progress, resolving conflicts, and ensuring that agents collaborate smoothly to achieve shared goals.

not rated 2 4mo ago A 42 tokens

init-agent-sync

5677

Hadi99K/AGENT_SKILLS

Skill Claude CodeCodex

Initializes the AGENTSYNC.md hub for AI agent coordination and task tracking.

not rated 2 4mo ago A 20 tokens original MIT

arco

5678

frankxai/claude-codex-gemini-opencode-settings

Skill Claude CodeCodex

Activate the Arcanea Orchestrator — the multi-CLI routing brain. Shows status, routes tasks to best model (claude/opencode/codex/gemini), runs plans and workflows, and delegates to sub-CLIs via Bash. Distinct from /ao (Composio session manager).

not rated 2 5mo ago A 62 tokens

boil-the-ocean

5679

rajkaria/boil-the-ocean

Plugin Claude Code

Bundles 1 skill, 3 commands, 2 hooks · 140 tokens together

Hand your agent an entire spec and walk away: autonomous multi-sprint execution with a decision journal, checkpointed file-based state, and a scheduler that relaunches fresh sessions whenever context or usage limits hit. Works with Claude Code, Codex, Gemini CLI, and any headless agent.

not rated 2 2mo ago A tokens not measured original MIT

clarify-question

5680

cyuanxv/agent-cockpit

Skill Claude CodeCodex

Use a fresh task profile and a four-level policy to turn material ambiguity into a precise, self-contained prompt without asking the user to make technical choices the agent can investigate.

not rated 2 1mo ago A 38 tokens original MIT

codeck

5682

isdou/codeck

Skill Codex

Route explicit requests from a host coding agent to one or more locally configured AI executors through Codeck, attach Markdown or other project files, moderate cross-model consultation, expose disagreements, and synthesize traceable results. Use when the user explicitly names Codeck or asks to consult, compare, or…

not rated 2 16d ago A 108 tokens original MIT

env-scanner

5683

pauldatta/gemini-cli-scanner

Skill Claude CodeCodex

Scan and audit Gemini CLI, Claude Code, Antigravity, Continue, Windsurf, JetBrains AI, and OpenCode environments. Discovers configurations, audits memory tiers, detects skill extraction state, analyzes behavioral tool chains, checks policy governance (v0.40+), and suggests reusable skills with evidence gating.…

not rated 2 1mo ago A 101 tokens original Apache-2.0

claude

5685

darshitpp/x-agent

Skill Claude CodeCodex

Delegate tasks or get a second opinion from Claude Code CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Claude Code, or offloading work to it. Do not use when already running inside Claude Code…

not rated 2 1mo ago A 81 tokens original MIT

live-neon/skills

Skill Claude Code needs its repo

Complete skill compression documentation — all options, modes, and calibration details (2,500 tokens).

not rated 2 3mo ago A 25 tokens original MIT

meta-cogbase

5687

d-wwei/meta-cogbase

Skill Claude CodeCodex

A package manager for installing and managing cognitive bases, which are add-ons that provide an AI agent with additional capabilities or instructions.

not rated 2 5mo ago A 41 tokens original MIT

workflow-kit

5688

moabualruz/agent-workflow-kit

Skill Claude CodeCodex

Run, inspect, resume, and stop Agent Workflow Kit workflows from Codex.

not rated 2 1mo ago A 19 tokens original MIT

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: