Building agents

38,494 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.

sf-summon

6841

anrylu/soul-forge

Command Claude Code

Soul Forge — Summon a new agent character.

not rated 1 5mo ago A 9 tokens

stannum2/letstalk-master

Skill Codex

Build or update privacy-first AI-assistant configuration and reusable preference skills for Codex, Claude Code, Cursor, Gemini CLI, and similar tools. Use when the user provides explicit preferences, existing config files, example rules, or asks to optimize AGENTS.md, CLAUDE.md, assistant rules, memory files, or…

not rated 1 1mo ago A 81 tokens original MIT

creating-skills

6843

lufermalgo/ai-for-non-developers

Skill Claude CodeCodex

Generates high-quality, predictable, and efficient skill directories based on user requirements, enforcing strict structural and formatting standards.

not rated 1 5mo ago A 27 tokens original MIT

orchestrator-agent

6844

VictorTomaili/agent-cli

Agent Claude Code

AI agent manager — the host/main agent in any agentic CLI tool. Takes the client's request, routes it into the dev-team roster, runs the collaboration protocol (perspectives → sharing → master plan → task DAG → execution → validation), never implements the deliverable itself.

not rated 1 3d ago A 60 tokens original MIT

guiju

6845

arctan303/guiju.skill

Skill Claude CodeCodex

A pragmatic working-rules skill for agents. It makes agents more direct, judgment-oriented, less repetitive, and more careful before executing complex tasks.

not rated 1 3mo ago A 32 tokens original MIT

agent-native-cli

6846

Mauricecolorful3388/agent-native-cli

Skill Codex

Use when designing, reviewing, or refactoring a CLI that must serve AI agents alongside humans, or when converting an API or SDK into an agent-usable CLI interface.

not rated 1 yesterday A 38 tokens original MIT

public

6847

to-agent/agent-exec

Skill Claude CodeCodex

Skill "public" from to-agent/agent-exec, covering skill: agent-exec, endpoint: get /, what is this?, root surface and start.

not rated 1 4mo ago A 0 tokens original Apache-2.0

builder-kit

6848

gabonio/agent-operator-toolkit

Plugin Claude Code

Bundles 5 skills · 336 tokens together

An explicitly invoked, token-efficient harness for planning, implementing, and reviewing agent-driven software. It helps technical and non-technical users produce sustainable code through approval-gated specifications, pragmatic repository-aware standards, conditional expert lenses, safe Git workflows, and…

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

agent-run-viewer

6849

hcw67/agent-run-viewer

Skill Codex

Analyze AI coding-agent runs and generate user-facing replay reports. Use when Codex needs to review Codex, Claude Code, OpenCode, Gemini CLI, or other coding-agent transcripts/logs; debug agent behavior; summarize file changes, commands, failures, interruptions, verification, and risks; or create Markdown/HTML…

not rated 1 4mo ago A 92 tokens

find-vetted-skill

6851

rawrkit/skills-radar

Skill Claude CodeCodex

Find an agent skill that a human actually reviewed, instead of guessing from a dump of thousands of unfiltered links. Use whenever a user asks "is there a skill for X", "what should I install to do X", wants to extend what their agent can do, is frustrated that their agent handles some task badly, or asks which skills…

not rated 1 yesterday A 109 tokens original MIT

vibe-harness

6852

myshkin451/vibe-harness

Skill Codex

Turn a human project plan into a lightweight agent-ready repository harness for sustainable AI coding. Use when bootstrapping a new project, retrofitting an existing repo for AI coding agents, creating or refreshing AGENTS.md/docs/index.md/progress.md, diagnosing context loss across sessions, designing verification…

not rated 1 4mo ago A 73 tokens original MIT

run

6853

mystilleef/spae-framework

Command Claude Code

Execute a named subagent with optimized instructions.

not rated 1 1mo ago A 9 tokens original MIT

agente-de-projeto

6854

GabrielPazBR/agente-de-projeto

Skill Codex

Cria, implanta ou repara um agente de projeto no Codex, com MemPalace local, Graphify, RTK, servidores MCP, skills, perfil funcional e AGENTS.md persistente. Use na configuração inicial de um workspace ou para diagnosticar uma implantação existente.

not rated 1 changed 8d ago A 63 tokens

gemini-omni

6855

runapi-ai/gemini-omni

Plugin Claude Code

Bundles 1 skill · 76 tokens together

RunAPI Gemini Omni skill for audio, character, and video workflows in Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents.

not rated 1 changed 12d ago A tokens not measured original Apache-2.0

skill-creator

6856

priyanshuchawda/tracepilot-gemini-cli

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 Gemini CLI's capabilities with specialized knowledge, workflows, or tool integrations.

not rated 1 3mo ago A 46 tokens copy · 100% Apache-2.0

Skill Authoring

6857

Razaib-khan/ForgeWeave

Skill Claude Code

Create or revise a ForgeWeave skill — from identifying the repeatable job to writing the bundle and validating it with eval checks.

not rated 1 3mo ago A 30 tokens original MIT

cf

6858

leiseek/context-flow

Skill Claude Code

Use when switching AI coding tools (Claude Code, Codex, Cursor, OpenCode, Copilot CLI, Gemini CLI) due to rate limits, cost optimization, or model capability gaps. Triggers on "/cf save", "/cf load", "/cf status", "/cf diff", "/cf validate" commands. Also use when the user mentions losing context, repeating work…

not rated 1 4mo ago A 97 tokens

agent-evolutions

6859

fmind/agent-evolutions

Plugin Claude Code

Bundles 3 skills · 211 tokens together

Genetic exploration of solution spaces for AI coding agents — gather a verifiable objective, evolve variants, apply the winner.

not rated 1 3mo ago A tokens not measured original MIT

loop-engineering

6860

imMamdouhaboammar/loop-engineering-skill

Skill Claude CodeCodex

Use when designing, orchestrating, or executing autonomous multi-agent coding loops with financial budget caps, minimal fixes, and continuous dev-QA gates.

not rated 1 1mo ago A 33 tokens original MIT

idd

6861

SoliEstre/idd

Plugin Claude Code

Bundles 1 skill · 110 tokens together

Implementation-Driven Development skill for isolated probes, human decisions, contracts, and independent verification.

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

loop-governor

6862

gengshirong1128-boop/loop-governor

Skill Claude Code

A safety and decision layer for autonomous loops, where agents repeat work across multiple rounds. It sets limits, budgets, stop rules, file boundaries, and review points for workers such as Claude Code, Codex, and Gemini CLI.

not rated 1 3mo ago A 100 tokens original MIT

orchestrator

6863

barisgorgun/ai-dev-team-workflows

Agent Claude Code

Feature geliştirme sürecini yöneten baş koordinatör. "geliştir", "ekle", "yap", "implement et", "feature", "özellik" gibi yeni bir iş başlatıldığında devreye girer. architect, code-reviewer, test-engineer, security-reviewer agent'larını doğru sırayla çağırır, kullanıcıdan onay gereken noktalarda durur.

not rated 1 1mo ago A 95 tokens original MIT

ex-example_xiaoming

6864

M00NZ1/Persona-Distill-skill

Skill Claude Code

An example relationship-memory and persona package for an AI agent, written in Chinese. It contains placeholder details and explicitly does not describe a real person.

not rated 1 5mo ago A 10 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: