Building agents

40,198 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.

frankbria/ralph-claude-code

Instructions file

Instructions for frankbria/ralph-claude-code, covering claude.md, repository overview, core architecture, main scripts and library components (lib/).

not rated 9.6k +4 1mo ago B 9,464 tokens original MIT

anthropics/claude-for-legal

Instructions file ✓ vendor

Claude Code instructions for anthropics/claude-for-legal, covering claude.md, layout, validation — run before opening a pr, 3. json/yaml sanity and marketplace invariants (i1–i11).

not rated 9.4k +7 13d ago A 1,479 tokens original Apache-2.0

gen-agent

123

higress-group/higress

Command

You are a specialized prompt engineer tasked with generating high-quality, structured prompts for AI agents based on user descriptions. Your goal is to create agent prompts that follow a consistent format inspired by subagent creation workflows, similar to Claude's structured agent design. When you receive an input in…

not rated 9.3k yesterday A 0 tokens original Apache-2.0

README

124

jasontang-ai/Context-Engineering

Command Claude Code

This directory contains a growing library of modular, customizable, and extendable agents and harnesses embedded as slash commands, forming an Agentic Operating System (AgenticOS) designed for enhancing the capabilities of Claude Code and other frontier systems, such as OpenCode, Amp, Kiro, Codex, Gemini CLI, and…

not rated 9.2k +4 6mo ago A 0 tokens original MIT

alignment

125

jasontang-ai/Context-Engineering

Command Claude Code

Command "alignment" from jasontang-ai/Context-Engineering, covering /alignment.agent system prompt, slash command invocation, context clarification, risk mapping and failure/adversarial simulation.

not rated 9.2k +4 6mo ago A 0 tokens original MIT

jasontang-ai/Context-Engineering

Instructions file

Claude Code instructions for jasontang-ai/Context-Engineering, covering claude.md - cognitive operating system, 1. core meta-cognitive framework, context schemas, code understanding schema and troubleshooting schema.

not rated 9.2k +4 6mo ago A 5,062 tokens original MIT

jasontang-ai/Context-Engineering

Instructions file Gemini CLI

Gemini CLI instructions for jasontang-ai/Context-Engineering, covering gemini.md - cognitive operating system, core reasoning frameworks, systematic problem solving, code analysis & generation and technical research.

not rated 9.2k +4 6mo ago A 4,417 tokens original MIT

harness

128

revfactory/harness

Plugin Claude Code

Bundles 1 skill · 170 tokens together

A tool that turns a description of a work area into a coordinated team of AI agents and the skills they need. It offers six ways to divide and review the work.

not rated 8.9k +17 1mo ago A tokens not measured original Apache-2.0

adk-sample-creator

129

google/adk-go

Skill Claude CodeCodex ✓ vendor

Author or rework a runnable example under examples/ in the ADK Go repository — the directory, main.go, the README with its Mermaid diagram and real transcript, and the index row. Use when adding a sample for a feature (workflow graph, tool, registry client, model backend, server), when asked to "add an example" for…

not rated 8.7k +13 today A 94 tokens original Apache-2.0

feynman AGENTS.md

130

companion-inc/feynman

Instructions file CodexOpenCode

Instructions for companion-inc/feynman, covering agents, pi subagents, what belongs here, feature scope and pi runtime changes.

not rated 8.8k +33 8d ago A 1,610 tokens original MIT

skill-creator

131

CoreBunch/Instatic

Skill Claude CodeCodex

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 8.4k +58 yesterday A 46 tokens copy · 83% MIT

flue AGENTS.md

132

withastro/flue

Instructions file CodexOpenCode

Instructions for withastro/flue, covering flue, contributing, terminology, project structure and development.

not rated 8.1k +25 7d ago A 912 tokens original Apache-2.0

nullclaw AGENTS.md

133

nullclaw/nullclaw

Instructions file CodexOpenCode

Instructions for nullclaw/nullclaw, covering agents.md — nullclaw agent engineering protocol, 1) project snapshot (read first), 3) engineering principles (normative), 3.1 kiss and 3.2 yagni.

not rated 8.1k +3 1mo ago A 4,131 tokens original MIT

Upsonic CLAUDE.md

134

Upsonic/Upsonic

Instructions file

Claude Code instructions for Upsonic/Upsonic, covering claude.md, project overview, ai operational guides, default pre-work consultation and keep documents/ai/explanation/ in sync with code.

not rated 7.9k 2mo ago A 2,950 tokens original MIT

sandcastle AGENTS.md

135

mattpocock/sandcastle

Instructions file CodexOpenCode

Instructions for mattpocock/sandcastle, a project described as: Orchestrate sandboxed coding agents in TypeScript with sandcastle.run().

not rated 7.8k +49 2mo ago A 4 tokens copy · 100% MIT

mattpocock/sandcastle

Agent

This document is for contributors adding support for a new agent (e.g. Claude Code, Codex, gemini-cli) as a built-in agent provider. It covers.

not rated 7.8k +49 2mo ago A 0 tokens original MIT

refly

137

refly-ai/refly

Skill Claude CodeCodex

Base skill for Refly ecosystem: creates, discovers, and runs domain-specific skills bound to workflows. Routes user intent to matching domain skills via symlinks, delegates execution to Refly backend. Use when user asks to: create skills, run workflows, automate multi-step tasks, or manage pipelines. Triggers: refly…

not rated 7.5k +3 1mo ago A 94 tokens

star-office-ui

138

ringhyacinth/Star-Office-UI

Skill Claude CodeCodex

A setup tool for a visual pixel-art office dashboard where multiple coding agents can appear with their current status. It also supports viewing the dashboard on a phone and reaching it over the public internet.

not rated 7.5k +5 5mo ago A 40 tokens

free-llm-apis

139

mnfst/awesome-free-llm-apis

Skill Claude CodeCodex

Guide users through obtaining and configuring free API keys for LLM providers. Use when the user wants to set up a free LLM API, get a free API key, connect to a free model provider, configure an OpenAI-compatible endpoint at no cost, or asks about free tiers for AI models. Triggers on "free API key", "free LLM", "set…

not rated 7.3k +55 14d ago A 116 tokens original CC0-1.0

plano-agent-skills

140

katanemo/plano

Skill Claude CodeCodex

Best practices for building agents and agentic applications with Plano, including configuration, routing, orchestration, guardrails, observability, and deployment.

not rated 7.0k +12 15d ago A 35 tokens original Apache-2.0

cursor_rules

141

superdesigndev/superdesign

Cursor rule Cursor

Guidelines for creating and maintaining Cursor rules to ensure consistency and effectiveness.

not rated 6.9k +5 2mo ago A 375 tokens

self_improve

142

superdesigndev/superdesign

Cursor rule Cursor

description: Guidelines for continuously improving Cursor rules based on emerging code patterns and best practices. globs: / alwaysApply: true.

not rated 6.9k +5 2mo ago A 530 tokens

overview

143

GoogleCloudPlatform/agent-starter-pack

Agent

The Agent Starter Pack follows a "bring your own agent" approach. It provides several production-ready agent templates designed to accelerate your development while offering the flexibility to use your preferred agent framework or pattern.

not rated 6.5k +2 1mo ago A 0 tokens original Apache-2.0

workspace-dispatch

144

outsourc-e/hermes-workspace

Skill Claude CodeCodex

Single-agent mission orchestrator. Decomposes a mission into tasks, spawns one worker per task using the default model, verifies exit criteria, and chains tasks with retry. No critic pattern — each worker self-verifies. Simple, fast, works with any model config.

not rated 6.6k +6 13d ago A 59 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: