agentleFS
its-everdredits-everdred/skills/setup-switch-login/SKILL.md

setup-switch-login

Skill2 starsChanged 20 days agoMITView on GitHub

Set up a second Claude Code account on this machine for the switch-login skill (claude / claude2, with an optional machine-local named command). Use only when the user runs /setup-switch-login.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Never read, copy or print .credentials.json, .claude.json or sessions/ in either profile.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Set up switch-login

  1. Find the installer, switch-login/scripts/setup.sh: ~/.claude/skills/switch-login/scripts/setup.sh if that exists, otherwise the copy in the user's clone of the skills repo. If the user named a profile directory, pass it as the argument (default ~/.claude-2). If they gave the second account a short name, pass --name NAME; this stores it in the shell rc as CLAUDE_LOGIN2_NAME and exposes claude-NAME.
    bash <path>/setup.sh [PROFILE_DIR] [--name NAME]
  2. Report what it changed (its "changed:" list), or that nothing changed. If it refused, show the "Found:" lines and stop. Don't fix them yourself without asking.
  3. Give the user the one step it cannot do, as a code block:
    claude2
    Then /login with the second account. They have to run this in a new shell so the rc lines are loaded.

Never read, copy or print .credentials.json, .claude.json or sessions/ in either profile.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.