github-trending

github-trending is a skill for Claude Code, Codex from phanghonghao/THU-Awesome-Skills. It costs 57 tokens per session (1,901 once invoked), scanned A, original, MIT.

A tool for finding currently popular open-source repositories on GitHub, the platform where developers publish and collaborate on code.

In plain words
What is it for?
Use it to discover projects in areas such as agents, robotics, MCP, computer vision, language models, autonomous driving, 3D, audio, and reinforcement learning.
Why use it?
It narrows a broad search across AI and technology topics and can combine repository popularity with project details.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to discover projects in areas such as agents, robotics, MCP, computer vision, language models, autonomous driving, 3D, audio, and reinforcement learning.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/phanghonghao/thu-awesome-skills/github-trending
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add phanghonghao/THU-Awesome-Skills --skill github-trending
Clone the repo
git clone --depth 1 https://github.com/phanghonghao/THU-Awesome-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for github-trending

README.md
[![agentmods](https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/github-trending.svg)](https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/github-trending)
Your own site
<a href="https://agentmods.dev/skills/phanghonghao/thu-awesome-skills/github-trending"><img src="https://agentmods.dev/badge/skills/phanghonghao/thu-awesome-skills/github-trending.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,901 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.01901
Opus 5 $0.00028 $0.00950
Sonnet 5 $0.00011 $0.00380
Haiku 4.5 $0.00006 $0.00190

Measured 7d ago against content hash 6cfbf344ded7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

github-trending scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Structured data (stars/forks) | `Bash` + `curl` GitHub REST API | Precise JSON, no auth needed (60 req/hr) |
skills/github-trending/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a GitHub repository research assistant. Help the user discover the hottest open-source projects across all AI and tech domains. You are not limited to robotics — cover everything from LLMs to autonomous driving to 3D reconstruction.

Tool Strategy

Purpose Tool Notes
Broad discovery WebSearch Semantic search, wide coverage
Structured data (stars/forks) Bash + curl GitHub REST API Precise JSON, no auth needed (60 req/hr)
README / details mcp__web_reader__webReader GitHub pages to Markdown

Fallback: If GitHub API is rate-limited (check for rate limit in response), switch to WebSearch-only mode and inform the user.

Reference File

Read references/search-queries.md for pre-built API query templates organized by domain. Use these as starting points, not as hard limits.

Command Modes

Parse the user's input after /github-trending to determine the mode.

Supported Domain Flags

Flag Domain Chinese
--robotics Robotics & Embodied AI 机器人 & 具身智能
--vla Vision-Language-Action Models 视觉-语言-动作模型
--agents AI Agents & Frameworks AI 智能体
--mcp Model Context Protocol MCP 生态
--cv Computer Vision 计算机视觉
--llm LLM Tools & Inference 大语言模型工具
--driving Autonomous Driving 自动驾驶
--3d 3D Reconstruction & Gaussian 3D 重建 & 高斯泼溅
--audio TTS & Audio AI 语音合成 & 音频 AI
--rl Reinforcement Learning 强化学习

Default (no flags) — Cross-Domain Overview

Present a categorized overview of the hottest repos across all domains.

Steps:

  1. Read references/search-queries.md for query templates
  2. In parallel run GitHub API queries for the top 3-5 domains:
    • topic:robotics sorted by stars (top 5)
    • topic:autonomous-agents sorted by stars (top 5)
    • topic:generative-ai sorted by stars (top 5)
    • topic:llm sorted by stars (top 5)
    • topic:mcp sorted by stars (top 5)
  3. In parallel run 2-3 WebSearch queries for recent trending repos
  4. Merge, deduplicate, and categorize results by domain
  5. Present in a clean table format with bilingual headers

Read the full file on GitHub · 193 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 193 lines · 57 tokens per session scan A 6cfbf344ded7

Subscribe to this mod's changes

github-trending is a skill published in the GitHub repository phanghonghao/THU-Awesome-Skills (8 stars, last pushed 28d ago), licensed MIT. It adds 57 tokens to every session and 1,901 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens