Building agents

38,263 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.

claude-code-bridge

2810

constripacity/Claude-Bridge

MCP server Claude CodeCodexCursor +2

Local-first, cross-machine MCP relay for independent coding agents. Runs locally from the claude-code-bridge Python package. Needs 2 environment variables to run.

not rated 12 +1 23d ago A tokens not measured original MIT

jarviscore

2811

Prescott-Data/jarviscore-framework

Skill Claude CodeCodex

Build multi-agent AI systems with the JarvisCore Python framework. Use when writing, reviewing, or debugging code that imports jarviscore, defines AutoAgent or CustomAgent classes, runs a Mesh, or configures agent memory (Athena), P2P, Nexus credentials, or tracing.

not rated 12 changed 2d ago A 63 tokens

jiuge2467/dsh-studio

Skill Claude CodeCodex

Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted…

not rated 12 29d ago A 69 tokens copy · 97% MIT

G-Research/bobbit

Skill Claude Code

Configure the performance optimisation programme and idempotently adopt or create its two persistent staff agents.

not rated 12 today A 24 tokens original MIT

titanclip

2814

CES-Ltd/TitanClip

Skill Claude CodeCodex

Interact with the TitanClip control plane API to manage tasks, coordinate with other agents, and follow company governance. Use when you need to check assignments, update task status, delegate work, post comments, set up or manage routines (recurring scheduled tasks), or call any TitanClip API endpoint. Do NOT use for…

not rated 12 5mo ago A 87 tokens

gedd-chat

2815

aws-samples/sample-GEDD

Command Claude Code ✓ vendor

You are a GEDD coaching assistant. You guide the user through building a golden evaluation dataset for their AI agent using Open Coding methodology, then help them evaluate and annotate responses — all without leaving Claude Code.

not rated 12 1mo ago A 0 tokens MIT-0

agent-dev

2816

Abilityai/abilities

Plugin Claude Code

Bundles 46 skills · 1,987 tokens together

Develop and extend existing agents — add skills, memory systems, GitHub Issues development workflow (backlog, roadmap, groom, claim, autoplan, commit, sprint, work-loop — standalone skills the add-backlog installer copies), cross-actor project management (project-init / project-task / project-steward /…

not rated 12 +1 changed today A tokens not measured original MIT

architect

2817

LegalQuants/LQ-Architect

Skill Claude CodeCodex

Run the architect build discipline whenever the sponsor asks to build, design, architect, or rework something substantive — a system, tool, pipeline, document, integration, skill. Three sign-off gates (requirements, design+checks, verification) recorded as signoffs/gate{1,2,3}.md written by the SPONSOR; a regression…

not rated 12 1mo ago A 120 tokens original MIT

agency-icm-builder

2818

krsnczky/agency-icm-builder

Skill Claude CodeCodex

Build or audit an AI-runnable workspace for a client-service agency (marketing, PPC, design, consulting, dev shops). Folder structure does the orchestration - one agent, routing files, per-client folders, session capture. Use when the user wants to (1) set up an agency workspace an AI agent can operate ("build me an…

not rated 12 +1 1mo ago A 135 tokens original MIT

icm-builder

2819

carloswecare/icm-builder

Skill Claude CodeCodex

Build and reason about projects using Interpretable Context Methodology (ICM) — a filesystem-based way to structure AI work using numbered folders and markdown files (CLAUDE.md, CONTEXT.md) instead of code-heavy agent frameworks. Use this skill whenever the user wants to scaffold a new ICM workspace, set up a…

not rated 12 +1 2mo ago A 164 tokens original MIT

claude-watchdog

2820

Temikus/claude-watchdog

Plugin Claude Code

Bundles 1 skill, 1 agent, 4 hooks · 60 tokens together

Auto-runs a critical session post-mortem when Claude Code stops. Ships the analyze-session command, session-analyzer agent, and a Stop hook that triggers the review in-session (no external API calls). Requires Node.js 20 or newer on PATH.

not rated 12 changed 10d ago A tokens not measured original Apache-2.0

aid-guide

2821

agent-tools-org/ai-dispatch

Skill Codex

Official comprehensive operating guide for the AID multi-agent CLI. Use whenever a user asks how to install, configure, use, troubleshoot, automate, or safely operate AID; asks which AID command or workflow to choose; works with tasks, agents, worktrees, batches, groups, reviews, acceptance, custody GC, skills…

not rated 12 +1 changed 10d ago A SkillSpector: pass 111 tokens original MIT

create

2822

paulbaranowski/wild-horses

Skill Claude Code

Scaffold a Claude Code plugin marketplace with proper structure, schema validation, and CLAUDE.md conventions. Asks for the marketplace name and whether to import an existing skill. Use when starting a new marketplace repo or adding marketplace structure to an existing repo.

not rated 12 27d ago A 53 tokens original MIT

create-target

2823

fabis94/universal-ai-config

Skill Claude CodeCodex needs its repo

Scaffold a new target type (e.g., Zed, Windsurf) for universal-ai-config.

not rated 12 +1 19d ago A SkillSpector: pass 23 tokens original MIT

sheepdog

2824

avantsoftware/sheepdog

Plugin Claude Code

Bundles 1 skill, 3 hooks · 62 tokens together

Herds Claude Code through your project's conventions: injects a per-project task->skill routing table on every prompt and blocks edits to governed files unless the matching skill was invoked first. Project rules live in .claude/sheepdog/config.json (scaffold it with /sheepdog:setup); the plugin ships no…

not rated 12 2mo ago A tokens not measured original MIT

routiform-cursor-setup

2825

linhnguyen-gt/Routiform

Skill Claude CodeCodex

Point the Cursor editor at a running Routiform gateway through Settings → Models → OpenAI API Key, including the publicly reachable URL Cursor requires because it calls the endpoint from its own servers rather than from your machine. Use when someone asks to connect Cursor to Routiform, use custom or self-hosted…

not rated 12 +1 yesterday A SkillSpector: warn 80 tokens original MIT

cursor-codeatlas

2826

giauphan/codeatlas-platform

Cursor rule Cursor

CodeAtlas MCP Integration — Auto-read memory, use MCP tools before coding, sync after changes.

not rated 12 yesterday A 634 tokens original MIT

skill_search

2828

wxwsm666/GenericAgent-v1-web

Skill Claude CodeCodex needs its repo

A skill-search tool for finding relevant coding-agent skills from a collection of more than 105,000 entries using an English description of the task.

not rated 12 +1 4mo ago A 0 tokens original MIT

skill2gep

2829

EvoMap/skill2gep

Skill Claude CodeCodex

Generic skill distillation tool. Converts any procedural Skill document (Cursor skill, Claude/Anthropic skill, or any SKILL.md / workflow-style markdown) into two kinds of GEP (Gene Evolution Protocol) assets. Gene = compact strategy template (signals + strategy + AVOID + validation). Capsule = audit record of a real…

not rated 12 2mo ago A 165 tokens original MIT

skill-evaluator

2830

lanyasheng/skill-evaluator

Skill Claude CodeCodex

A tool for evaluating and improving other coding-agent skills through benchmarks, adversarial tests, and repeated improvement cycles.

not rated 12 5mo ago A 31 tokens

install-agent-scaffold

2831

DongLiStudio/personal-agent-foundation

Skill Codex

An installation coordinator for Personal Agent Foundation, a set of shared files and tools for running personal AI-agent projects. It creates a new base, installs its global rules, and guides first-time setup.

not rated 12 +1 changed yesterday A 133 tokens original Apache-2.0

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: