# The Grammar of Coding Agents

> A living field guide to command languages, sigils, skills, subagents, and harnesses across OpenAI Codex, Claude Code, OpenCode, Cursor, and GitHub Copilot.

This living reference compares the interactive command languages, context sigils, skills, subagents, planning, review, and harness boundaries of OpenAI Codex, Claude Code, OpenCode, Cursor, and GitHub Copilot. The detailed report is maintained as Markdown and rendered as a browser-readable HTML document.

## Primary document

- [Complete LLM-readable report](https://grammar-of-coding-agents.pages.dev/llm.txt): Full Markdown content, including comparison tables, command references, recommendations, maintenance notes, and sources.
- [Human-readable HTML report](https://grammar-of-coding-agents.pages.dev/coding-agent-command-language-comparison.html): Styled, responsive browser presentation with navigation and visual diagrams.

## Source

- [Editable Markdown source](https://grammar-of-coding-agents.pages.dev/coding-agent-command-language-comparison.md): Authoritative source used to generate both the HTML report and the LLM-readable document.

## Optional

- [Open Graph preview](https://grammar-of-coding-agents.pages.dev/coding-agent-open-graph-preview.html): Social-sharing image preview for the report.