ai-agents agents

5,649 tagged ai-agents, measured the same way as everything else here.

Browse within: agentic-ai 408LLM 307ai-coding 172cursor 150agents-md 149prompt-engineering 143claude-code-plugin 129ai-software-team 116agent-orchestration 115agentic 112cursor-rules 104Science 99ai-skills 92gemini-cli 87

worker

01

google-gemini/gemini-cli

Agent Claude CodeGemini CLI ✓ vendor

General purpose agent for any tasks that need a scoped context window.

not rated 107k +124 today A 15 tokens original Apache-2.0

creative-director

02

Donchitos/Claude-Code-Game-Studios

Agent Claude Code

Highest creative authority — vision, tone, aesthetic direction. Use when a decision affects game identity or department leads deadlock.

not rated 27k +651 changed 7d ago A 28 tokens original MIT

协调主代理

03

Ed1s0nZ/CyberStrikeAI

Agent Claude Code

Instructions for a coordinating agent that plans multi-agent security work, delegates separate tasks, combines evidence, and delivers the result. A multi-agent workflow uses several specialized agents on parts of one job.

not rated 7.6k 5d ago A 59 tokens original Apache-2.0

apm-expert

04

microsoft/apm

Agent Claude Code ✓ vendor

Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.

not rated 4.0k +31 today A 39 tokens original MIT

agents-module

05

foryourhealth111-pixel/Vibe-Skills

Agent Claude Code needs its repo

Automation scripts and agent helpers for the Digital Brain. Use these scripts for recurring tasks, summaries, and maintenance.

not rated 3.7k +82 2d ago A 25 tokens copy · 100% Apache-2.0

beads-warden

07

jeremylongshore/tons-of-skills-marketplace

Agent Claude Code

Guard the beads execution record: enforce the write-flush-verify discipline that defeats the bd rapid-write race, audit epic dependency graphs for cycles and orphans, catch closures whose title overstates what shipped, flag open beads carrying no disposition or a disproven premise, and reconcile bd against its GitHub…

not rated 2.8k +16 2d ago A 157 tokens original MIT

memorax-repo-memory

08

memorax-ai/memorax-code

Agent Claude Code

Build or update Repo Memory for an exact MemoraX delegation ticket.

not rated 2.0k +182 changed 10d ago A 20 tokens original MIT

e2e-tests-engineer

09

happier-dev/happier

Agent Claude Code

Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.

not rated 2.0k +61 changed 1mo ago A 24 tokens original MIT

agent-organizer

10

lst97/claude-code-sub-agents

Agent Claude Code

A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project requirements, defines a team of specialized AI agents, and manages their collaborative workflow to achieve project goals. Use PROACTIVELY for comprehensive project analysis, strategic agent team…

not rated 1.7k +1 1y ago A 66 tokens original MIT

agentlas-ai/Agentlas-OS

Agent Claude Code

Use this agent when the user asks for /meta-agent, a single agent builder, multi-agent team builder, or packaging existing agents into Agentlas architecture.

not rated 1.6k +13 today A 38 tokens original Apache-2.0

stack-auditor

12

RyanAlberts/best-of-Agent-Harnesses

Agent Claude Code

Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses the repo uses, flags dead or graveyarded ones, and names live replacements. Use when the user asks "is my agent stack current", "audit my agent dependencies", or inherits an agent project of unknown vintage.

not rated 1.2k +109 4d ago A 73 tokens CC-BY-SA-4.0

ap-route-analyst

13

Spielewoy/autoprompt-skill

Agent Claude Code

Inspect only enough read-only project information to recommend a route and list the facts behind that recommendation.

not rated 1.2k +3 12d ago A 25 tokens original MIT

Chorus-AIDLC/Chorus

Agent Claude Code

Final ship-time review of an Idea's aggregate code change — the whole feature across all its tasks, not one task. Read-only; posts a VERDICT comment on the Idea. Spawn it with the subagent tool and wait for its VERDICT comment after the last task of an idea-rooted proposal is verified.

not rated 1.2k +7 changed 6d ago A 69 tokens AGPL-3.0

ongridio/ongrid

Agent Claude Code

An incident-investigation worker that follows a chain of causes back to the original source of a system alert or failure.

not rated 1.2k +50 yesterday A 35 tokens AGPL-3.0

lee-to/ai-factory

Agent Claude Code

Coordinate parallel execution of independent plan tasks in Antigravity 2.0. Dispatches implement-worker workers and quality sidecars.

not rated 1.1k +10 changed today A 30 tokens

planner

17

asklokesh/loki-mode

Agent Claude Code

Breaks a goal into small ordered tasks with acceptance checks.

not rated 1.1k +6 today A 13 tokens

cs-cmo-advisor

18

borghei/Claude-Skills

Agent Claude Code

Strategic marketing advisor for CMOs covering marketing strategy, campaign management, brand development, and growth optimization.

not rated 920 +29 changed 18d ago A 26 tokens

agents-guide

19

alirezarezvani/claude-code-skill-factory

Agent Claude Code

Interactive guide for building custom Claude Code Agents and subagents. Asks straightforward questions, generates enhanced YAML frontmatter with tools/model/color/field/expertise, creates agent .md files, validates format, and helps install to .claude/agents/ or /.claude/agents/. Use when user wants to build workflow…

not rated 886 +4 11mo ago A 70 tokens original MIT

Explore

21

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 708 +3 changed 27d ago A 79 tokens original MIT

shinpr/claude-code-workflows

Agent Claude Code

Generates integration/E2E test skeletons from Design Doc ACs using ROI-based selection and journey-based E2E reservation. Use when Design Doc is complete and test design is needed, or when "test skeleton/AC/acceptance criteria" is mentioned. Behavior-first approach for minimal tests with maximum coverage.

not rated 698 +5 changed 2d ago A 68 tokens original MIT

lateral-thinker

23

samvallad33/vestige

Agent Claude Code

Subconscious subagent that surfaces cross-disciplinary structural parallels from the Vestige memory graph. Invoked by the preflight-swarm.sh UserPromptSubmit hook (Pre-Cognitive Triad v2.3 "Thalamus"). Fresh context, Haiku 4.5, Vestige MCP tool access. Outputs a single XML block or EMPTY.

not rated 650 +2 4d ago A 82 tokens AGPL-3.0

fable-advisor

24

kju4q/ai-weekend-builds

Agent Claude Code

Senior advisor for hard problems. Consult when stuck on architecture decisions, ambiguous tradeoffs, or when an approach isn't working. Returns guidance, not implementation.

not rated 640 +4 9d ago A 35 tokens

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: