agentleFS
its-everdredits-everdred/skills/new/SKILL.md

new

Skill2 starsChanged 20 days agoMITView on GitHub

Use when the user says "/new" or asks to open/start a new Claude chat or session in a folder (e.g. "/new open a new chat in ../folder", "... with my other account") so they can reach it from the Claude app without SSH. Launches claude in that directory inside tmux on either Claude account, with Remote Control on, and opens a terminal window when there is a desktop.

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use upgrade, gate and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • agenticnotetakingSkill

    upgrade

    Apply plugin knowledge base updates to an existing generated system. Consults the Ars Contexta research graph for methodology improvements, proposes skill upgrades with research justification. Never auto-implements. Triggers on "/upgrade", "upgrade skills", "check for improvements", "update methodology".

    Also in 4 projects that use this

  • synaptiaiSkill

    gate

    Create a BDSK review_gate artifact. Defines a checkpoint that controls whether generated output may proceed toward acceptance. Use when defining quality, security, or scope gates for execution plans.

    Also in 3 projects that use this

  • kt057Skill

    check

    lint, typecheck, test を一括実行して結果をサマリーする

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 5 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 1

    Distinctive

    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. Distinctive:

    If it doesn't exist, stop and say so.

    line 13
  2. Very specific:

    Add --no-rc only if the user asks for Remote Control off.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “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

New chat in a folder

Open a new Claude Code session in a directory on this machine and turn on Remote Control, so the user can pick it up from the Claude app.

Steps

  1. Resolve the directory from the request, relative to the current working directory (../folder means a sibling of cwd). ~ means the home directory.
    • If it doesn't exist, stop and say so. Don't create it unless the user asked for that.
  2. Pick the account. By default, the new chat uses the same login as this session (--account current, the script's default): a session on the second profile opens the new chat there too. Add --account default for "my main/default account" (claude); add --account second for "my other/second account", "claude2", or the optional name in CLAUDE_LOGIN2_NAME; add --account other for "the account this session isn't on". If the current session predates setup, read the exact CLAUDE_LOGIN2_NAME export from ~/.bashrc or ~/.zshrc. The second account is the switch-login profile in CLAUDE_LOGIN2_DIR; if it isn't set up, say so and point to /setup-switch-login.
  3. Run the launcher (it ships with this skill):
    <skill dir>/scripts/new-chat.sh [--account current|default|second|other] <resolved dir>
    Add --no-rc only if the user asks for Remote Control off.
  4. Report the session name, the account, the folder, the inherited permission flags, the remote: link, and the attach command. Tell the user the chat should now be in the Claude app. If it exited saying claude is waiting on a prompt (for example a first /login on the second account), relay that: the user has to answer it once at the machine, or attach to it.

What the script does

  • Names the conversation <machine> - <project>, for example PC - Aiur or NUC - GM, with scripts/convo-name.sh. The machine is PC on orangekid and NUC on a host whose name contains "nuc", or $CLAUDE_MACHINE_LABEL. The project is the repository's main checkout name (a worktree names its repo): aiur → Aiur, open-game-maker → GM, khala → Khala, others capitalized, or $CLAUDE_PROJECT_LABEL. Remote Control uses the same name.
  • Starts claude (or claude2) in the folder inside a detached tmux session named claude-<folder>-<time>. It goes through the switch-login wrapper when that's installed, so /switch-login works in the new chat.
  • Inherits permission flags from the calling claude session: --dangerously-skip-permissions and --permission-mode are passed on only if this session has them. It never adds them.
  • Answers the folder-trust prompt, because the user named the folder. It does not answer any other startup prompt. If one blocks startup, the script exits and prints tmux attach -t <name>, so the user can answer it.
  • Starts claude with --remote-control, which is the same as typing /rc, and prints the session link.
  • Opens a gnome-terminal window attached to the session when a desktop display is available.

Requirements

tmux, claude on PATH, and Linux (/proc). The terminal window is optional. The second account needs the switch-login setup (/setup-switch-login).

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.