agentleFS
zoo3323zoo3323/usage-statusline/skills/setup/SKILL.md

setup

Skill1 starsChanged 31 days agoMITView on GitHub

Turn on the usage-statusline status line and choose what it shows — folder, model, Claude and Codex usage gauges, context, countdowns, the in-use light. Run it again to change the choice.

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 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.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Read ~/.claude/settings.json if it exists.

    line 19
  2. Very specific:

    Read ~/.claude/codex-status/config if it exists.

    line 23
  3. Distinctive:

    Ask both in one AskUserQuestion call.

    line 29
  4. Very specific:

    Add that the icons need a terminal font with Nerd Fonts 3.5 glyphs — without one they show as empty boxes — and the one line Ghostty needs, …

    line 69

“Common” is measured: kept by at least 6 in 10 of the 171 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

Set up the status line

The status line is a script Claude Code runs for the bottom line of the screen. A plugin cannot switch a status line on by itself, so this skill does it: it copies the scripts to ~/.claude/scripts/, records what the user wants to see, and points statusLine in ~/.claude/settings.json at the script.

Talk to the user in their language. The option labels below are in English; translate them.

1. Look at what is there

  • Read ~/.claude/settings.json if it exists. If statusLine.command is set and does not contain statusline-codex.sh, the user already has a different status line. Tell them which command it is and ask whether to replace it. Stop if they decline: nothing has been changed.
  • Read ~/.claude/codex-status/config if it exists. It holds the current choice, one key=value a line (show=, countdown=, icons=, light=). Offer the current values as the starting point. Without the file everything is shown.

2. Ask what to show

Ask both in one AskUserQuestion call. Where that tool is not available, ask the same in plain text and wait for the answer.

  1. Session (several can be chosen): Folder name · Model and effort · Context gauge
  2. Usage (several can be chosen): Claude usage gauge · Codex usage gauge · Time until a window resets · In-use light

Say with the questions, briefly, that the Codex gauge only appears on a machine where the Codex CLI is logged in.

The gauges are labelled with icons (the OpenAI and Claude logos and a speech bubble). That is not a question: do not offer words instead.

At least one of the five segments (folder, model, context, Claude gauge, Codex gauge) has to be chosen. If none is, say so and ask again.

3. Apply

Turn the answers into three values:

  • show: the chosen segments out of folder model codex claude ctx, in that order
  • countdown: on if "Time until a window resets" was chosen, else off
  • light: on if "In-use light" was chosen, else off

Then run, with the values filled in:

bash "${CLAUDE_PLUGIN_ROOT}/install.sh" --plugin --show "folder model codex claude ctx" --countdown on --icons on --light on

The script fetches jq into ~/.local/bin if it is missing, backs up settings.json before changing it, and prints what it did. If it fails, show its output and stop.

4. Report

In a few lines: what is shown now, and that the line appears at the bottom within a couple of seconds — in a new session at the latest. To change the choice, run /usage-statusline:setup again. /usage-statusline:refresh fetches the usage numbers on the spot, /usage-statusline:uninstall removes everything this skill set up.

Add that the icons need a terminal font with Nerd Fonts 3.5 glyphs — without one they show as empty boxes — and the one line Ghostty needs, from the "Your choice" section of the plugin's README (${CLAUDE_PLUGIN_ROOT}/README.md).

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.