Agent Claude Code
Owns the Zulip communication and owner-control plane for the current Claude Code session. Use proactively when work should stay synchronized with a Zulip topic.
not rated 27
+1 26d ago A 36 tokens
original MIT
Agent Claude Code
Workflow execution and verification specialist. Runs validatebeforeexecute, executes, and verifies outputs. Tests only; never modifies.
not rated 24 1mo ago A 29 tokens
original MIT
humanllm
99Agent Claude Code
An agent that passes coding tasks to human engineers through a separate service and later retrieves their results. It does not write code or edit files itself.
not rated 23
+1 19d ago A 109 tokens
original MIT
code-reviewer
100Agent Claude Code
Expert code reviewer focusing on correctness, maintainability, security, and adherence to project standards.
not rated 22 yesterday A 21 tokens
GPL-3.0
player-2v2
101Agent Claude Code
Clash Royale 2v2 player agent. Plays cards at maximum speed with deeper positioning for teammate coordination.
not rated 22 7mo ago A 28 tokens
original MIT
Agent
An update summary for a Pi Agent system, describing changes inspired by Claude Code version 2.1.19.
not rated 22 16d ago A 0 tokens
Agent
Use this agent to create audio and video assets using Google NotebookLM. Handles notebook creation, source uploads, Audio Overview generation (Deep Dive, Brief, Critique, Debate), video generation, interactive sessions, and custom persona configuration. Use when you need to transform documents into podcasts, explainer…
not rated 21 19d ago A 0 tokens
original MIT
research
104Agent Claude Code
Code and tech search expert. Pure research, no code modifications. Finds files, patterns, and tech solutions.
not rated 21 10d ago A 24 tokens
copy · 92% Apache-2.0
standard
105cuddly-guacamole/opencode-routing-suite
Agent
You are a helpful software engineer assistant.
not rated 21 12d ago A 112 tokens
planner
106Agent Claude Code
Breaks a complex goal into ordered, estimated steps with dependencies and risks. Use when a task needs 3+ steps, when sequencing or effort is unclear, or when the user says "plan this", "break this down", "how should we approach". Do NOT use for tasks with an obvious single path — plan overhead exceeds the value there.
not rated 20 1mo ago A 72 tokens
original MIT
Test Worker
107Agent Claude Code
Autonomous agent specialized in test development. Creates comprehensive test suites.
not rated 20 yesterday A 15 tokens
AGPL-3.0
base
108xt765/LangChain-Chinese-Comment
Agent
The base module for LangChain classic agents and the executor that runs them. An agent is a program where a language model chooses tools and their order while solving a task.
not rated 20 1mo ago A 0 tokens
original MIT
meta-creator
109Agent Claude Code
You are a conversion-focused copywriter specializing in creating high-performing meta titles and descriptions that maximize click-through rates from search engine results pages (SERPs).
not rated 20
+1 20d ago A 0 tokens
copy · 94% MIT
fixer
110TashanGKD/tashan-cursor-skills
Agent
A coding agent that fixes reported bugs using test-driven development, or TDD: reproduce the problem, write a failing test, change the code, and confirm the tests pass. It first checks what the affected feature is meant to do.
not rated 20
+1 5mo ago A 168 tokens
original MIT
Agent
Visual Communication + Presentation Expert.
not rated 20 6mo ago A 8 tokens
original MIT
custom_agent
112Agent
Execute a custom agent configuration by its UUID.
not rated 19 1mo ago A 0 tokens
original Apache-2.0
code-reviewer
113bonnguyenitc/antigravity-superpowers
Agent
Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication…
not rated 19 3mo ago A 234 tokens
copy · 100% MIT
upstream-watcher
114Agent
Status: V1 design (2026-07-08), pre-implementation. Owner: infra. Related: issue-tracker.md, triage-labels.md, domain.md.
not rated 19 yesterday A 0 tokens
pvf-safety-rules
115Qswhisper/PVF-Ai-Agent-Workbench
Agent
The authoritative safety policy is knowledge-pack/safety/README.zh-CN.md. Read it in full for every concrete PVF task. This file intentionally does not duplicate its field-level text, scope, cumulative-output, or client-deployment rules.
not rated 18 11d ago A 0 tokens
original MIT
Agent
Use this agent to orchestrate contracted implementation planning, executable tests, and enabled infrastructure/development capabilities.
not rated 18
+1 yesterday A 26 tokens
Explore
117Agent
Fast read-only codebase exploration that returns compressed findings.
not rated 18
+2 yesterday A 12 tokens
original MIT
analyzer
118Agent Claude Code
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
not rated 17 1mo ago A 0 tokens
copy · 100% MIT
wjx-cli-expert
119Agent Claude Code
A specialist assistant for Wenjuanxing, a Chinese online survey platform, using its command-line tool to manage surveys and related data.
not rated 16
changed yesterday A 35 tokens
original MIT
Agent
ServiceNow solution architect — design patterns, data models, integrations, scalability, migration planning.
not rated 16
+1 yesterday A 22 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: