Project: [Brief description] Status: [Development/Production/Research] Primary Goal: [What are you building?] Core Components: - [Component 1]: [Purpose, location] - [Component 2]: [Purpose, location] - [Component 3]: [Purpose, location] This project uses fractal documentation - information organized by attention level: When you start a session: 1. Check systems/ for deployment context 2. Check modules/ for code you're working on 3. Use integrations/ if touching external systems The context router will automatically: - Keep recently mentioned files HOT (full content) - Keep…
SEOmator is a comprehensive SEO audit tool (@seomator/seo-audit) with 373 rules across 20 categories. It ships as both a CLI tool (published to npm) and an Electron desktop app (local only). It fetches web pages, parses HTML with Cheerio, optionally measures Core Web Vitals via Playwright, and scores pages against SEO best practices. The package.json serves both the npm CLI package and the Electron desktop app. These fields have strict requirements: If you change main to anything other than the…
The single source of truth for how to work in this repo is spec/ (kvx). This file is a GENERATED pointer to it. Do not hand-edit it; edit spec/workflow.kvx and run spec/specgen. spec/ (kvx). Per-IDE rule files are GENERATED pointers — never hand-edit; run cg spec render && cg commit -m \"Specgen re-render\" to regenerate.
This repository contains the speaker project and its shared skill implementation. Claude Code users can invoke the project skill as: The Claude Code project-skill entry is available at: The canonical…
snip is a CLI proxy written in Go that reduces LLM token consumption by 60-90% by filtering shell output before it reaches the LLM context. Inspired by rtk (Rust Token Killer), snip improves on the concept with a declarative filter DSL — filters are YAML config files, not compiled code. The binary (snip) is the engine. Filters are data files. The two evolve independently. Anyone can contribute a filter without knowing Go. - snip is usually installed as a hook…
See .claude/extensions/nvim/context/project/neovim/standards/documentation-policy.md for README requirements, structure template, and style guidelines. This CLAUDE.md is the root configuration file for the Neovim configuration repository.
AI-powered Instagram carousel builder. Next.js 16 + React 19 + TypeScript + Tailwind v4. All at localhost:3000: Slides store body-level HTML only (no <html>, <head>, <!DOCTYPE>). The wrapSlideHtml() function adds the full document structure, font loading, and dimension constraints. Slides should:
This file is for LLM coding agents and repo-reading assistants. It is meant to help you answer questions about Sponsio accurately and make code changes without breaking the architecture. Sponsio is a runtime contract layer for LLM apps and agents. Its core job is pre-execution enforcement for LLM tool/action behavior: before a model-driven system calls a tool, edits a file, hits an API, writes to a database, issues a refund, approves a loan, or triggers any side effect, Sponsio checks…
Claude Data Analysis Assistant is an intelligent data analysis platform that leverages Claude Code's sub-agents, slash-commands, and hooks to provide a comprehensive data analysis workflow. Based on the successful DATAGEN…
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
GMaN1911CLAUDE.md
