Comparisons

Side-by-side comparisons of Claude Code, Codex CLI, and Kimi Code CLI, built only from the verified research notes in ../research/. Each page lists its official sources and the date it was last verified.

Pages

• Feature Matrix — one big table of major capabilities (plan mode, subagents, skills, MCP, sandbox, hooks, and more) across all three tools, with notes where the comparison is not 1:1.
• Command Equivalents — “how do I do X” command mapping (start, resume, compact, plan, review, MCP setup, non-interactive runs) plus behavior differences that matter.
• Project Instructions: CLAUDE.md vs AGENTS.md — CLAUDE.md vs AGENTS.md: file locations, precedence, override mechanisms, size caps, /init behavior, and how to port instructions between tools.
• Permissions and Security Models — security models: permission modes, sandbox availability per platform, rule syntax, bypass flags, and safe-default recommendations.
• Context Management — compaction (auto/manual), context inspection, session resume/fork, and undo/rewind per tool.

Legend

Symbol	Meaning
✅	Supported
⚠️	Partial or different implementation
❌	Not supported
?	Unable to verify

---

Last verified: 2026-09-07

Official sources:

• https://code.claude.com/docs/en/cli-reference.md
• https://code.claude.com/docs/en/commands.md
• https://developers.openai.com/codex/cli/slash-commands
• https://developers.openai.com/codex/config-reference
• https://www.kimi.com/code/docs/en/kimi-code-cli/reference/slash-commands.html
• https://www.kimi.com/code/docs/en/kimi-code-cli/reference/kimi-command.html

AI coding tools evolve quickly. If you find outdated information, please open an issue or pull request.