Repo Tokens: GitHub Action Adds Token Count Badge for LLM Context Window Awareness

Repo Tokens is a GitHub Action that calculates the token count of your codebase and adds a visual badge to your README indicating how much of a large language model's context window your repository occupies. The goal is to make token size a visible metric, similar to bundle size badges for JavaScript libraries, encouraging leaner codebases that are more compatible with AI coding agents.
How It Works
The action uses tiktoken for tokenization. It runs approximately 60 lines of inline Python and takes about 10 seconds to execute. It's implemented as a composite action.
Configuration and Output
The context window size is configurable, defaulting to 200,000 tokens (matching the size of Claude models). The badge color reflects the percentage of the configured context window your codebase fills:
- Green: Under 30%
- Yellow: 50-70%
- Red: 70%+
The action updates the README file but does not automatically commit the changes, allowing your workflow to control the git strategy.
This type of tool is useful for developers working with AI assistants, as keeping a codebase within an LLM's context window allows the agent to maintain full awareness of the project structure and dependencies during coding tasks.
📖 Read the full source: HN AI Agents
👀 See Also

OpenClaw Skill Pack: A 2,500+ Command Set for Real Autonomous Operations on Ubuntu
A new skill package for OpenClaw AI agents introduces over 2,500 execution skills for DevOps operations like Docker management, networking configuration, CVE response, and system automation on Ubuntu environments.

Quick-Question Plugin Automates Unity Development with Claude Code
A developer has released quick-question, a macOS plugin for Unity 2021.3+ that automates compilation, testing, and cross-model code review when using Claude Code. The tool includes 20 slash commands and uses a 'Tribunal' pattern where Codex and Claude review each other's findings.

Homebutler: OpenClaw Skill for Homelab Management via Telegram
Homebutler is a single Go binary (~13MB, zero dependencies) that works as an OpenClaw skill to manage homelabs from Telegram chat. It monitors servers, restarts Docker containers, wakes machines, scans networks, and alerts on resource spikes without SSH sessions or dashboard logins.

Equibles: Self-Hosted MCP Server for U.S. Financial Data – SEC Filings, 13F, Insider Trades, FRED
Equibles is an open-source MCP server that scrapes public U.S. financial data (SEC filings, 13F, insider/congressional trades, short data, FRED) and exposes it as MCP tools for any local LLM agent.