analyzer
193Agent Claude Code
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
not rated 281 2mo ago A 0 tokens
solver
194Agent Claude Code
You are vix, running as the solver agent for a coding benchmark trial. The current working directory is $(workingdirectory) (no need to cd into it for bash commands).
not rated 274
+1 2d ago A 1 tokens
AGPL-3.0
super-dev
195Agent Claude Code
Activate the Super Dev pipeline for research-first, commercial-grade project delivery. Use when user says /super-dev or super-dev: followed by a requirement.
not rated 274
+1 2mo ago A 0 tokens
original MIT
router-agent
196Agent Claude Code
You are a specialized AI assistant that serves as a routing agent for a system of 25 specialized AI agents. Your primary responsibility is to analyze user requests, determine which specialized agent would be most appropriate to handle the request, and provide the agent ID along with a brief explanation of why that…
not rated 271 3mo ago A 0 tokens
meta-artisan
197Agent Claude Code
Match the right skills, tools, and capability packages for a MetaKim agent or workflow.
not rated 268
+2 yesterday A 23 tokens
original Apache-2.0
coding_agent
198Agent Claude Code
Writes and edits code. Stores strategies and implementation decisions.
not rated 265
+1 7d ago A 11 tokens
AGENTS
199Agent Claude Code
Crate: aghub-agents — Agent descriptors, models, and format serializers\ Role in monorepo: The single source of truth for all agent-specific behavior. aghub-core re-exports this crate's public API.
not rated 264
changed 2d ago A 0 tokens
original MIT
leader
200Agent Claude Code
Orquestador. Recibe la tarea principal, divide el trabajo y lanza subagentes. NUNCA escribe código directamente.
not rated 262
+3 3mo ago A 29 tokens
kernelgen
201Agent Claude CodeOpenCode
An agent that discusses computational-operator designs, generates their code, and repeatedly checks and repairs the result until validation succeeds or the process stops.
not rated 259 26d ago A 44 tokens
original Apache-2.0
skill-updater
202Agent Claude Code
Expert Sentry SDK skill author that updates and creates SDK skill bundles. Specializes in researching SDK changes, verifying APIs against official docs and source code, and producing high-quality wizard flows with deep-dive reference files. Use when updating skills after SDK changes, creating new skills for new…
not rated 258
+3 yesterday A 68 tokens
original MIT
deepseek_harness
203Agent Claude Code
Usually, running uvx stata-mcp install -c dsh installs the project into DeepSeek Harness Web.
not rated 255
+2 3d ago A 0 tokens
AGPL-3.0
implementer
204Agent Claude Code
Implements a discrete, already-planned change.
not rated 254 4d ago A 12 tokens
original MIT
starmynd-org/infinite-brain-os
Agent Claude Code
A subagent that retrieves relevant knowledge nodes by reading the local git tree, supplements with a web search, and produces a structured research summary with citations and suggested follow-up nodes.
not rated 245
+2 10d ago A 39 tokens
original MIT
README
206Agent Claude Code
AgentSpec deploys 58 specialized agents across 8 categories, each built on a three-tier template system with mandatory KB-First knowledge resolution. Every agent carries a cognitive framework that enforces structured confidence scoring, provenance tracking, and explicit stop conditions -- turning raw LLM capability…
not rated 245
+1 3d ago A 0 tokens
original MIT
codex
207Agent Claude CodeCodex
Agent "codex" from yzhao062/anywhere-agents, covering bootstrap: shared config and skills, bootstrap block for project repos, shared agent config (auto-fetched), what gets shared and override rules.
not rated 243
+3
changed today F 0 tokens
original Apache-2.0
openclaw-expert
208Agent Claude Code
Use this agent when the user has any question about OpenClaw — how it works, how to configure it, how to use specific features, what APIs are available, how agents are structured, or any other OpenClaw-related inquiry. This agent should be used proactively whenever OpenClaw-specific knowledge is needed.\n\n \nContext…
not rated 242 yesterday A 510 tokens
Agent Claude Code
For package-ready/runtime guidance, see documentation/contributors/guides/agent-extension-playbook.md.
not rated 239 3mo ago A 0 tokens
original Apache-2.0
domain
210Agent Claude Code
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
not rated 237
+17 3d ago A 0 tokens
original MIT
Agent Claude Code
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
not rated 235 today A 30 tokens
GPL-3.0
conclusion
212Agent Claude Code
A code-analysis agent that documents the structure, files, statistics, and implementation details of an agents directory in a Python project.
not rated 227
+8 today A 0 tokens
original Apache-2.0
analyzer
213zacharyfmarion/openscad-studio
Agent Claude Code
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
not rated 226
+2 17d ago A 0 tokens
GPL-2.0
kiro
214Agent Claude Code
Agent "kiro" from symposium-dev/symposium, covering kiro, skills, hooks and mcp servers.
not rated 225 9d ago A 0 tokens
skills
215Agent Claude Code
Health.md publishes Agent Skills from .agents/skills. A skill is an instruction bundle for a compatible coding agent; it does not install the healthmd binaries, configure MCP, pair a phone, or grant access to health data.
not rated 224
+4 today A 0 tokens
AGPL-3.0
switchboard
216Agent Claude Code
This project uses the Switchboard protocol for cross-IDE agent collaboration.
not rated 214
+1 today A 0 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: