Building agents

38,381 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.

jules-dispatch

4465

Yuuqq/jules-dispatch

Skill Codex

Dispatch independent coding tasks to Google Jules through the jules-dispatch CLI or MCP server, then monitor sessions and report PR URLs. Use when Codex or Claude Code needs to fan out implementation, testing, refactoring, review, migration, or documentation work into parallel Jules sessions; when a user asks to use…

not rated 4 yesterday B 104 tokens original MIT

yaac

4466

amyodov/yet-another-agentic-chat

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 102 tokens together

Messaging between concurrent AI coding sessions, across clients, over MCP. Zero infrastructure. (YAAC: Yet Another Agentic Chat.).

not rated 4 changed 14d ago A tokens not measured original MIT

capsule

4467

dawitlabs/capsule

MCP server Claude CodeCodexCursor +2

Compact, source-linked context packs that reduce token waste for coding agents. Runs locally from the capsulectx npm package.

not rated 4 2mo ago A tokens not measured original MIT

canvas-mcp

4468

admin978/canvas-mcp

MCP server Claude CodeCodexCursor +2

Local-first MCP server for Canvas LMS. Stdio transport, no third-party broker. Runs locally from the canvas-local-mcp Python package. Needs 2 environment variables to run.

not rated 4 1mo ago A tokens not measured original MIT

agence

4470

l-agence/agence

MCP server Claude CodeCodexCursor +2

AI governance MCP server — policy enforcement, skills, memory, multi-LLM consensus. Runs locally from the @l-agence/mcp-server-agence npm package. Needs 1 environment variable to run.

not rated 4 4mo ago A tokens not measured

nexus-mcp

4471

j7an/nexus-mcp

MCP server Claude CodeCodexCursor +2

Model Context Protocol server for AI CLI agents. Runs locally from the nexus-mcp Python package.

not rated 4 3d ago A tokens not measured original MIT

mcp-server-template

4473

qmmughal/mcp-server-template

MCP server Claude CodeCodexCursor +2

Production-grade MCP Server Template for TypeScript and Node.js. Runs locally from the @qmmughal/mcp-server-template npm package.

not rated 4 1mo ago A tokens not measured original MIT

goodeye

4474

Goodeye-Labs/goodeye-cli

MCP server Claude CodeCodexCursor +2

Design, save, and run outcome-aligned AI workflows and verifiers, with reliable image output. Remote server at mcp.goodeye.dev.

not rated 4 3d ago A tokens not measured original MIT

pocketlantern

4475

pocketlantern/pocketlantern

MCP server Claude CodeCodexCursor +2

Blocker-aware decision layer for AI coding agents, grounded in source-linked, time-sensitive facts. Runs locally from the @pocketlantern/mcp-server npm package.

not rated 4 5mo ago A tokens not measured original MIT

formulahendry/mcp-server-mcp-registry

MCP server Claude CodeCodexCursor +2

MCP Server for MCP Registry to discover and search for available MCP servers in the registry. Runs locally from the mcp-server-mcp-registry npm package.

not rated 4 1y ago A tokens not measured

plumb-chat

4477

plumbkit/plumb

Skill Claude CodeCodex

Talk to another agent working the same plumb workspace — address a peer session by name, hand your turn over while waiting for its reply, and read silence correctly. Use when work has to be coordinated with a concurrent session.

not rated 4 changed 2d ago A 49 tokens original MIT

multi-agent-governance

4478

levelsofself/mcp-nervous-system

Skill Claude CodeCodex

Use this skill when building, managing, or auditing multi-agent AI systems. Provides governance patterns for behavioral enforcement, drift detection, audit trails, role management, and accountability across autonomous AI agents. Compatible with any orchestration framework.

not rated 4 2mo ago A 51 tokens original MIT

caliber

4479

JordanGrothentic/caliber

Skill Claude Code

Recommends which Claude model and effort level to fit a task, using cost of error as the deciding signal. Use when asked which Claude model or effort to use, or a task feels over or underpowered.

not rated 4 2mo ago A 46 tokens original MIT

actual

4480

actual-software/actual-skill-openclaw

Skill Claude Code

Feature-complete companion for the actual CLI, an ADR-powered CLAUDE.md/AGENTS.md generator. Runs and troubleshoots actual adr-bot, status, auth, config, runners, and models, and drives the Actual Advisor (login, advisor, whoami, logout) for org-scoped architecture questions. Covers all 5 runners (claude-cli…

not rated 4 22d ago A 159 tokens MIT-0

temper-skills

4481

CyrilLeMat/temper-skills

Skill Claude Code

Give an agent skill's decision logic a test suite and a deterministic implementation — a labeled validation dataset plus versionable Python — via an adversarial multi-persona loop that runs natively in Claude Code: proposer plus persona subagents through the Task tool, entirely on your Claude Code subscription, no…

not rated 4 1mo ago A 173 tokens original Apache-2.0

doa-workcopilot

4482

medalsoftchina/workcopilot

Skill Claude Code

A project-workflow station that coordinates agents and skills from project setup through delivery, including requirements, design, task planning, scaffolding, and engineering workflows.

not rated 4 3mo ago A 144 tokens original Apache-2.0

dsh-skills

4483

arch3rPro/dsh-skills

Plugin Claude Code

Bundles 15 skills · 1,163 tokens together

dsh-skills — generalized development-specification skills (defensive patterns, code conventions, testing tiers, prose standards, decision records, review/process discipline), extracted from DeepSeek Harness conventions and shaped by the mattpocock/skills architecture.

not rated 4 1mo ago A tokens not measured original MIT

cookbook

4484

DjordjeMojsilovic/Djordjes-Claude-Setup

Skill Claude CodeCodex

Use this skill whenever the user is building something with the Claude API and would benefit from a known-good reference implementation from Anthropic's official Claude Cookbooks. Trigger on any request that touches Claude API features — RAG, tool use, agents (Agent SDK or Managed Agents), vision/multimodal, prompt…

not rated 4 1mo ago A 0 tokens

mcp-audit

4485

saagpatel/MCPAudit

MCP server Claude CodeCodexCursor +2

MCP Permission Auditor — scan, enumerate, and risk-score all locally configured MCP servers. Runs locally from the mcp-audits Python package.

not rated 4 4d ago A tokens not measured original MIT

ai

4486

dysfunc/ai-plugins-cc

Plugin Claude Code

Bundles 7 commands, 1 hook · 123 tokens together

Umbrella plugin: dispatch /ai:review|rescue|gater across configured providers, plus /ai:compare for fan-out.

not rated 4 4mo ago A tokens not measured original Apache-2.0

agent-context-builder

4487

akhilkannur/marketing-agent-blueprints

Skill Claude CodeCodex

AI agents struggle when they don't know your project's structure. This agent scans your current directory, identifies key files/stacks, and generates an AGENTS.md file. This file acts as a 'ReadMe for Robots,' ensuring every future agent knows exactly how to work with your code.

not rated 4 7mo ago A 62 tokens

claude-power-skills

4488

irfad7/claude-power-skills

Plugin Claude Code

Bundles 20 skills · 1,846 tokens together

20 power-user skills for Claude Code — session management, multi-agent orchestration, adversarial testing, calibrated estimation, decision archaeology, and more.

not rated 4 1mo ago A tokens not measured 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: