Building agents

40,000 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.

typeagent-setup

409

microsoft/TypeAgent

Skill Claude Code ✓ vendor

Configure TypeAgent integration mode and settings.

not rated 748 +1 changed 1mo ago A SkillSpector: pass 12 tokens original MIT

mcp-scripting

411

Zhou-Shilin/Aether

Skill Claude CodeCodex

Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.

not rated 742 +10 yesterday A SkillSpector: pass 21 tokens GPL-3.0

anythingmcp

412

HelpCode-ai/anythingmcp

MCP server Claude CodeCodexCursor +2

Self-hosted MCP gateway: turn any API, database or MCP server into AI connectors — no code. Remote server at cloud.anythingmcp.com.

not rated 741 +47 yesterday A tokens not measured AGPL-3.0

claude-plugin

413

2aronS/Duel-Agents

Plugin Claude Code

Bundles 1 skill, 1 command · 48 tokens together

Route IDE and agent prompts through Duel Agents: concurrent model routing with a single API key.

not rated 734 +11 3mo ago A tokens not measured original MIT

skillgrade-graders

414

mgechev/skillgrade

Skill Claude CodeCodex needs its repo

Authors deterministic, LLM rubric, and human graders for skillgrade evaluations. Use when creating scoring scripts, writing evaluation rubrics, setting up human review workflows, or combining multiple graders with weighted scoring. Don't use for setting up eval pipelines, configuring eval.yaml defaults, or general…

not rated 731 +5 changed 13d ago A SkillSpector: pass 63 tokens original MIT

repo-task-proof-loop

415

DenisSergeevitch/repo-task-proof-loop

Skill Codex

Repo-local workflow skill for large coding tasks. Initializes .agent/tasks/TASKID artifacts, installs project-scoped Codex and Claude subagents, updates AGENTS.md plus the repo's Claude guide file with the workflow, and runs a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.

not rated 729 +1 6mo ago A 69 tokens original Apache-2.0

skysynth

417

skydiscover-ai/skydiscover

Plugin Claude Code

Bundles 2 skills, 1 command, 2 hooks · 204 tokens together

/skysynth: coding agents build a system specialized for your workload, checked by tests or machine-checked proofs. Includes the /skysynth skill, the agent roles (Spec Builder, Planner, Coding Agent, Evaluator, Critic, Auditor), and the hook that runs the tests before anything is delivered. Also install the skydiscover.

not rated 726 +6 1mo ago A tokens not measured original Apache-2.0

zavora-ai/adk-rust

Skill Codex

Implement realtime voice agents with ADK-Rust, including audio formats, event handling, and streaming reliability. Use when building or debugging voice interactions in adk-realtime.

not rated 720 +4 today A 43 tokens

capabilities-manager

419

infragate/capa

Skill Claude CodeCodex

Manage capa CLI configuration — capabilities.yaml / capabilities.json, skills, MCP servers, tools, hooks, sub-agents, rules, plugins, AGENTS.md / CLAUDE.md, security options, tool exposure modes, capa wrap shadow workspaces, --passthrough native writes, registries (including Claude marketplaces), activity traces, and…

not rated 718 +7 changed 1mo ago A 270 tokens original MIT

skills

420

coleam00/skills

Plugin Claude Code

Bundles 36 skills · 3,410 tokens together

The PIV loop (plan, implement, validate, review, commit, PR) plus priming, planning, worktrees, and the meta-skills for building your own AI Layer.

not rated 718 +9 changed 17d ago A tokens not measured original MIT

ruvnet/metaharness

Plugin Claude Code

Bundles 14 skills, 1 plugin · 711 tokens together

MetaHarness — mint a custom AI agent harness from any repo. Paste a GitHub URL or start blank; output runs on Claude Code, OpenAI Codex, pi.dev, Hermes, OpenClaw, or RVM. WASM kernel (Rust → wasm-bindgen + NAPI-RS), 6 hosts, witness-signed Ed25519 releases, GCP Secret Manager validation. Browser Studio + npx metaharne.

not rated 716 +10 yesterday A tokens not measured original MIT

chisle

422

JayPokale/Chisle

Plugin Claude Code

Bundles 4 skills · 335 tokens together

Maximum-efficiency dev mode. Zero-fluff prose combined with YAGNI/ladder-first code decisions. One persona: the senior dev who deletes code for fun and bills by the syllable.

not rated 714 +29 changed 6d ago A tokens not measured original MIT

looper

423

ksimback/looper

Skill Claude CodeCodex

Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council. Use when the user wants to design, build, or set up an agent loop, iterative agent workflow, self-review loop, LLM-as-judge loop, multi-model council, reviewer/judge gate, or /goal-style looping process. Start from a…

not rated 713 +1 2mo ago A 157 tokens original MIT

Explore

424

Nanako0129/pilotfish

Agent Claude Code

Read-only search agent for broad fan-out searches - when answering means sweeping many files, directories, or naming conventions and you only need the conclusion, not the file dumps. It reads excerpts rather than whole files, so it locates code; it doesn't review or audit it. Specify search breadth - "medium" for…

not rated 711 +3 changed 1mo ago A 79 tokens original MIT

ms-teams-apps

425

alinaqi/maggy

Skill Claude Code needs its repo

Microsoft Teams bots and AI agents - Claude/OpenAI, Adaptive Cards, Graph API.

not rated 711 +2 changed 1mo ago A SkillSpector: warn 22 tokens original MIT

helloagents

426

hellowind777/helloagents

Plugin Claude Code

Bundles 25 skills · 889 tokens together

HelloAGENTS — The orchestration kernel that makes any AI CLI smarter. Adds intelligent routing, unified QA gates, safety guards, and notifications.

not rated 707 +1 1mo ago A tokens not measured

find-skills

427

theniceboy/.config

Skill Claude CodeCodex

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

not rated 707 1mo ago A 67 tokens

durable-executor

429

modiqo/skillspec

Skill Claude CodeCodex

Universal first-hop for any tool-backed request that may execute, inspect, mutate, automate, browse, call, fetch, generate, install, test, run, or create artifacts through CLI, shell, API, adapter, browser, provider, local process, or external tool, with trace, alignment, evidence capture, and future recall. Use for…

not rated 699 +9 2mo ago A SkillSpector: pass 175 tokens original Apache-2.0

skill-creator

430

swarmclawai/swarmclaw

Skill Claude CodeCodex

Create, edit, improve, or audit skills for SwarmClaw agents. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory. Triggers on phrases like "create a skill", "author a…

not rated 697 +5 3mo ago A SkillSpector: warn 107 tokens original MIT

arcjet/arcjet-js

Skill Claude CodeCodex

Integrate Arcjet security into a Vercel AI SDK (v7) application using @arcjet/guard — wrap agent tools with guard checks, enforce rules on risky app actions, and emit audit events joined by one correlation ID. Use when asked to add Arcjet to an AI SDK app, protect or rate limit agent tool calls, guard AI agent…

not rated 693 changed 10d ago A SkillSpector: pass 91 tokens original Apache-2.0

hello2cc

432

hellowind777/hello2cc

Plugin Claude Code

Bundles 1 agent, 11 hooks · 58 tokens together

Claude Code alignment plugin that drives third-party models toward Opus-compatible workflows, tool usage, and output style.

not rated 689 +1 5mo ago A tokens not measured 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: