Building agents agents

2,859 tagged Building agents, measured the same way as everything else here.

Browse within: agents 167claude-code-plugin 166agentic-ai 130ai-coding 116LLM 114cli 99agent 80agent-orchestration 68skills 57github-copilot 56spec-driven-development 55prompt-engineering 53Multi-Agent 49ai-tools 48

kit-arbiter

314

shousper/claude-kit

Agent Claude Code

Escalated reviewer/fixer for the final batch and failed verification of a kit build-flow run.

not rated 4 3d ago A 25 tokens original MIT

planner-agent

315

Tholem-AI/Tholem-Cursor-Kit

Agent Claude CodeCursor

Convert research inputs into an execution-ready plan, including the planning-phase innovate checkpoint for non-trivial changes.

not rated 4 4mo ago A 24 tokens original MIT

voro6yov/spec-driven-development

Agent Claude Code

Audits a single agent file for content that overlaps with the skills it explicitly references — verbatim duplication, conceptual restatement, inlined procedures that should defer to a skill, and duplicated examples/templates. Read-only; emits a severity-grouped report with before/after patch suggestions. Invoke with…

not rated 4 1mo ago A 81 tokens original Apache-2.0

agent-spawning

317

natea/fitfinder

Agent Claude Code

Guide to spawning agents with Claude Code's Task tool.

not rated 4 10mo ago A 0 tokens copy · 100% MIT

gse-orchestrator-lite

318

nicolasguelfi/gensem

Agent Claude Code

Condensed always-on identity of the GSE-One orchestrator, sized to fit context-file size limits (Codex AGENTS.md ≤ 32 KiB). Covers identity, the 16 principles, the command reference, the core invariants in brief, and the orchestration decision tree. The full orchestrator ships as a loadable skill (gse-orchestrator).

not rated 4 1mo ago A 82 tokens

metago-ai/metagolifeform

Agent Claude Code

MetaGO Team Lead - coordinates the entire 30-person guild, understands user intent, distributes tasks to members, integrates final outputs, embodies 19 Meta-Thought Systems, 43 Fundamental Attributes, 36 Core Axioms, and 31-Dimensional Value System.

not rated 4 7d ago A 63 tokens original MIT

architect

321

ntaffzii/Skill-Agents

Agent Claude Code

Technical architect. Handles all planning, spec-writing, requirement clarification, and plan revisions before any code is written. Use for any new feature, multi-file change, or ambiguous task.

not rated 4 changed today A 38 tokens original MIT

Library Curator

322

MarieLynneBlock/arcanum-artifex

Agent Claude Code

Curates changed skills, agents, instructions, workflows, and prompts in this lab by running frontmatter, link, and self-containment checks plus a README index sync, then proposes one fix list before editing anything.

not rated 4 +2 3d ago A 47 tokens

winterbim/wincreator

Agent Claude Code

Seul agent autorisé à réécrire le skill WinCreator lui-même. À invoquer quand EVOLUTIONQUEUE.md contient des propositions, ou sur demande explicite de l'utilisateur. Chaque opération est une boucle Meso complète avec ledger.

not rated 3 13d ago A 55 tokens original MIT

sensei

324

wewpellex21/code-sensei

Agent Claude Code

CodeSensei by Dojo Coding — AI mentor that teaches programming concepts during vibecoding sessions. Invoked automatically after code changes to explain what happened, why decisions were made, and test comprehension with micro-quizzes. Adapts to the user's belt level and background. Use this agent when the user asks to…

not rated 3 2d ago B 77 tokens original MIT

kpz

325

punt-labs/quarry

Agent Claude Code

ML engineering specialist sub-agent. Principles from Andrej Karpathy's work — micrograd, nanoGPT, llm.c, Tesla Autopilot, Stanford CS231n.

not rated 3 4d ago A 38 tokens copy · 91% MIT

research-orchestrator

326

weorbitant/claude-code-agentic-research-orchestrator

Agent Claude Code

Orchestrates Gemini CLI and Copilot CLI agents for comprehensive research, development, and analysis tasks. Coordinates multiple AI perspectives, consolidates findings, and provides consensus-based recommendations. Use PROACTIVELY for complex tasks requiring multi-agent collaboration.

not rated 3 9mo ago A 53 tokens original MIT

glean-expert

328

gleanwork/configure-mcp-server

Agent Claude Code

PROACTIVELY use this subagent when coding tasks would benefit from enterprise context—debugging, testing, understanding code, or researching features. This agent searches Slack/Jira/GitHub/Confluence/Drive via Glean, then chains read/quote or code lookup for precise, sourced answers.

not rated 3 7d ago A 66 tokens original MIT

agent-spawning

330

airmcp-com/mcp-standards

Agent Claude Code

Guide to spawning agents with Claude Code's Task tool.

not rated 3 9mo ago A 0 tokens copy · 100% MIT archived

codex-executor

331

tentenco/skills

Agent Claude CodeCodex

Delegate implementation work to the OpenAI Codex CLI to save Claude tokens. Use for bulk implementation, second-opinion diagnoses, and fresh-perspective problems. Treat Codex as a peer senior engineer, not a reviewer. Runs codex exec non-interactively and returns only the outcome.

not rated 4 +1 11d ago A 64 tokens original MIT

leader

332

k1wi777/my-harness-SDD

Agent Claude Code

Orquestador principal. Recibe la solicitud del usuario, selecciona el workflow adecuado y coordina a los subagentes. NUNCA implementa directamente.

not rated 3 +1 changed yesterday A 35 tokens

project-manager

333

prototypo/claude-dev-pipeline

Agent Claude Code

Orchestrates feature development across the project. Receives an approved implementation plan, identifies affected files, delegates work to the developer, routes changes through code review and security review gates, coordinates fixes when a gate fails, then hands off to the tester for a gated commit and the…

not rated 3 +1 21d ago A 104 tokens original MIT

README

334

Enovatr-Labs/SpecRoute

Agent Claude Code

This directory contains the 12 Claude Code agents that implement the SpecRoute skeleton. They are project-internal - they build SpecRoute itself, not consumer-facing templates that ship as artifacts.

not rated 3 1mo ago A 0 tokens original Apache-2.0

debate-orchestrator

335

Yorha9e/moamcp

Agent Claude Code

Coordinates multi-agent verification and review workflows — decomposes the goal, delegates to specialist subagents, and returns a structured verdict.

not rated 2 yesterday A 31 tokens original MIT

glm

336

djerok/glm-mcp

Agent Claude Code

Cost-saving delegate backed by the GLM model (Zhipu/Z.ai). It does real repo work — read, write, edit, run commands — but ALWAYS through GLM (via mcpglmglmagent), so the work runs on GLM tokens (10x cheaper than Opus), NOT Claude. Use PROACTIVELY for cheap, well-specified, self-contained subtasks: frontend/UI…

not rated 2 1mo ago A 151 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: