Agents

palmtop is a command line tool: any agent that can run shell commands can use it. The agent learns how from a short guide, printed by palmtop guide.

Claude Code

palmtop install sets up Claude Code:

• the palmtop skill in ~/.claude/skills/palmtop/, generated from the same guide;
• the permission Bash(palmtop *) in ~/.claude/settings.json, so the agent doesn’t ask before each command.

It respects CLAUDE_CONFIG_DIR, backs up the files it changes, and does nothing if everything is already in place. Restart Claude Code after installing. palmtop update updates the skill too.

Then just ask, for example:

implement the plan and put the checks on palmtop
put the tests I should run on palmtop
put what I need to check on palmtop

You can also type /palmtop with an optional session title. When you finished testing, say so: “I reviewed the checks on palmtop”.

Other agents

Tell the agent to read the guide before using palmtop, for example with a line in AGENTS.md (or your agent’s instructions file):

To put checks on the user's devices, use palmtop: run `palmtop guide` first and follow it.

The guide explains sessions, how to write checks, how to read the review and what each mark means.

What the agent can and cannot do

• It writes, edits and removes checklists and items, and sets the session message.
• It cannot mark reviews: only you can, on your devices.
• It never runs palmtop pair and never reads ~/.palmtopai: pairing links and tokens stay out of the conversation, and no command it uses prints them.
• It doesn’t delete sessions or projects unless you ask it to.
• Notes and items you add are treated as your words, but a note asking for something risky or unrelated (deleting data, revealing credentials) makes the agent ask you to confirm in the chat.