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.

vector

6865

pharosone/vector-plugin

Plugin Claude Code

Bundles 4 skills, 1 MCP server · 267 tokens together

Red-team scanning for LLM agents — integrate Vector in your repo, harden against findings, generate agent profiles.

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

agysafe

6866

qiufeng662/AgySafe

Skill Claude CodeCodex

Delegate an explicit user-requested task to official Antigravity through AgySafe.

not rated 1 20d ago A 21 tokens

index

6867

jaydubya818/governed-claude-subagents

Agent Claude Code

Agent "index" from jaydubya818/governed-claude-subagents, covering claude code sub-agent index, 🎯 orchestration & management (8 agents), 🏗️ development & architecture (32 agents), 🎨 design & ux (8 agents) and 🔧 quality assurance & testing (18 agents).

not rated 1 21d ago A 0 tokens original MIT

yu-iskw/openspec-skills

Skill Cursor

Implements new Agent Skills for the project. Identifies the AI coding tool (Cursor, Claude Code, Gemini CLI), ensures specification compliance, and provides specialized templates. Use when creating, authoring, or adding a new skill, or when the user asks about Agent Skills format or SKILL.md.

not rated 1 6mo ago A 66 tokens

skill-creator

6869

Fantasia1999/skills-zh

Skill Claude CodeCodex

A skill for creating new skills and communicating with users about what they need. Its description also mentions capturing intent, interviewing, and research.

not rated 1 6mo ago A 0 tokens

ponponusa/agent-context-maintainer

Skill Codex

Create, update, and validate repository-local AI agent context files such as AGENTS.md, .agents/core.md, .agents/routing.md, provider-specific profiles, and task SKILL.md routing. Use when an AI coding agent (Codex, Claude Code, Gemini, Copilot, Cursor, or others) is asked to make AGENTS.md or SKILL instructions…

not rated 1 1mo ago A 107 tokens original MIT

claude-audit-config

6871

sdolard/awesome-claude-config

Skill Claude CodeCodex

Exhaustive audit of your Claude Code configuration against the official docs of the latest version: settings, permissions, hooks, agents, rules, skills, mcp, statusline, output-styles, memory. Detects non-conformities, staleness, over-engineering, cross-file inconsistencies; produces a correct / missing / incorrect…

not rated 1 2mo ago A 121 tokens

skill-pool

6874

AlataChan/skill-pool

Skill Claude CodeCodex

A meta-skill that indexes, searches, and recommends Claude skills from both local directories and external registries like awesome-claude-skills. Use this skill when searching for skills by capability or keyword, listing available skills, matching user intent to appropriate skills, or discovering new skills from…

not rated 1 8mo ago A 64 tokens

claude-flow

6876

anti-enterprises/proj-init

MCP server Claude CodeCodexCursor +2

Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code. Runs locally from the @claude-flow/cli npm package. Needs 6 environment variables to run.

not rated 1 5mo ago A tokens not measured

openpets

6877

andyluu98/awesome-petdash

Skill Claude CodeCodex

Use when the user asks to install, configure, verify, troubleshoot, or understand OpenPets; install or select a pet; connect Claude Code, OpenCode, Cursor, Codex, or MCP clients; configure a project to use a specific pet; or debug openpetsstatus, openpetsreact, or openpetssay.

not rated 1 3mo ago A 70 tokens copy · 100% MIT

goal

6878

roarista/awesome-harness

Skill Claude CodeCodex

Turn a fuzzy objective into a running, self-verifying loop. Use when Ro wants to "create a loop", run something "until it's done", or hand off a multi-step objective instead of hand-prompting each step ("/goal", "loop until", "keep going until tests pass", "build X autonomously"). The skill manufactures a strong SEED…

not rated 1 5d ago A 142 tokens original MIT

copilot-to-codex

6880

Kenrick-Zhou/copilot-to-codex

Skill Claude CodeCodex

Migrate GitHub Copilot customizations (copilot-instructions.md, applyTo .instructions.md files, .agent.md custom agents, SKILL.md skills) to OpenAI Codex equivalents (AGENTS.md, .codex/agents/.toml, .agents/skills). Scripts provide safe dry-runs, source-digest verification, and deterministic conversions; the skill…

not rated 1 3mo ago A 122 tokens original MIT

orchestrator

6881

arkatom/ai-instructions

Agent Claude Code

Master orchestrator that coordinates multiple sub-agents for complex multi-domain tasks.

not rated 1 10mo ago A 18 tokens original MIT

batonq-skills

6882

Salberg87/batonq-skills

Plugin Claude Code

Bundles 5 skills · 399 tokens together

Multi-CLI role skills for batonq autonomous coding agents — worker, judge, pr-runner, explorer, reviewer.

not rated 1 4mo ago A tokens not measured

Project Architect

6883

CypBnk/CoPilot-instruction-generator-system

Agent Claude Code

Master orchestrator agent that scaffolds production-ready VS Code GitHub Copilot configurations. Analyzes any project, delegates to specialized sub-agents, and delivers a complete instruction set tailored to the detected technology stack.

not rated 1 6mo ago A 46 tokens original MIT

make-harness

6884

parkjangwon/make-harness

Skill Codex

Use when the user wants to set up, install, audit, update, repair, or sync a project-local AI harness for the current repository. Inspect the repo, run a short interview for durable defaults and execution guardrails, then create or update synchronized AGENTS.md, CLAUDE.md, GEMINI.md, PROJECTHARNESS.md…

not rated 1 5mo ago A 83 tokens original MIT

universal-skill-router

6885

MMStudioCreations/skill-router

Skill Claude CodeCodex

Use at the start of any session, or when a prompt arrives without an explicit skill named. Reads the installed skill library at runtime, matches prompt intent against skill descriptions, resolves prerequisite chains, and outputs the correct skill sequence with a ready-to-execute trigger — without requiring the user to…

not rated 1 5mo ago A 104 tokens

ruleferry

6886

starinzlob/ruleferry

Skill Codex

Audit and synchronize coding-agent instruction files across AGENTS.md, CLAUDE.md, Cursor rules, GitHub Copilot instructions, GEMINI.md, and OpenCode. Use when a user wants to consolidate project rules, find conflicting or duplicate agent instructions, detect embedded secrets or non-portable paths, migrate rules…

not rated 1 2mo ago A 83 tokens original MIT

worker

6887

ai-awesome/.claude

Agent Claude Code

Use this agent PROACTIVELY for all implementation tasks including code changes, file creation, and refactoring.

not rated 1 5mo ago A 24 tokens

copilot-setup-audit

6888

trsdn/github-copilot-cli

Skill Claude CodeCodex

Audit a repository's Copilot CLI customization setup and suggest improvements. Use when the user wants to review their Copilot configuration, find gaps, validate agents, skills, instructions, hooks, plugins, or MCP setup, or optimize their CLI customization setup.

not rated 1 3mo ago A 57 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: