agentreflex docs

Every agentreflex command — init, add, new, install, uninstall, doctor, and dev.

The CLI is agentreflex, aliased to arx. Both names work.

agentreflex <command> [options]
arx <command> [options]

`init`

Scaffold .reflex/, detect installed agents, wire each one's native hook, and optionally drop in a starter reflex. Interactive.

npx agentreflex init

Add a reflex from the commons (by name), a GitHub path, a URL, or a local file. Writes it into .reflex/ and records it in config.json.

arx add no-force-push
arx add github:you/reflexes/no-secrets.mjs
arx add https://example.com/no-secrets.mjs
arx add ./no-force-push.mjs

Scaffold a new reflex file in .reflex/ and register it.

arx new my-reflex

Wire (or re-wire) the dispatcher into your agents — run it after cloning a repo that already has reflexes.

arx install                 # all detected agents
arx install --agent claude  # just one

Remove agentreflex's hooks from your agents. Your reflex files stay.

arx uninstall

Show which agents are wired and what each can enforce.

arx doctor

Run your reflexes against a command and print the verdict — no agent needed.

arx dev "git push --force origin main"

Flag	Applies to	Meaning
`--dir <path>`	all	Run as if in another directory.
`--agent <name>`	install, uninstall	Target specific agents (comma-separated).
`--scope <project\|global>`	install, uninstall	Wire the project or your whole machine.
`--global`	install, uninstall	Shorthand for `--scope global`.
`--registry <url>`	add	Resolve names against a different catalog.

arx hook --agent <name> also exists, but it's the machine-facing dispatcher each agent calls — you won't run it by hand.