Skip to main content
neetorecord setup <assistant> writes the rules file that teaches an AI coding assistant how to use the CLI: how authentication works, what the global flags do, how output is shaped, and how to discover commands it has not seen before.

Set up an assistant

The Cursor, Windsurf, Copilot, and Codex files are written relative to the current directory, so run those from the root of the project you want them in. Cursor and Windsurf rules are left alone if the file already exists. The append mode commands replace their own section and leave the rest of the file untouched, so re-running them after a CLI upgrade is safe.

Claude Code

setup claude needs Claude Code to have been run at least once, so that ~/.claude/ exists. It extracts the plugin and then prints the slash commands to run inside Claude Code:
Claude Code installs plugins through those interactive commands, so there is no shell equivalent.

What makes the CLI work well for agents

Self describing

neetorecord commands prints the whole command tree with every flag as JSON. An assistant can read it instead of guessing at a flag.

Fewer tokens

--toon carries the same data as the JSON envelope in a compact encoding, which keeps large listings from filling the context window.

Predictable errors

Every command exits non-zero on failure and writes one line to stderr, so a failure is easy to detect and to act on.

Chainable output

--quiet prints just the identifier after a create or update, which is what an assistant needs to feed the next command.

MCP instead of the CLI

Assistants that speak the Model Context Protocol can talk to NeetoRecord directly, with no binary to install. See the MCP documentation for the hosted server and its per client setup.