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
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- WALKERKILLER/Look-Tongji-Notestheir own version, first seen Nov 8, 2026
- steerlabs/opensteertheir own version, first seen Nov 8, 2026
- ansvisor/ansvisortheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- anombyte93/prd-taskmastertheir own version, first seen Nov 8, 2026
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.
juancruzmunozalbeloSkilladd-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
MicrosoftSkilladd-discord
Add Discord bot channel integration via Chat SDK.
Also in 11 projects that use this
MicrosoftSkilladd-slack
Add Slack channel integration via Chat SDK.
Also in 11 projects that use this
juancruzmunozalbeloSkilladd-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
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- anthropics/knowledge-work-plugins★ 35ksame name
- garrytan/gbrain★ 32ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- Q00/ouroboros★ 6.3ksame name
- pytorch/executorch★ 5.2ksame name
- agenticnotetaking/arscontexta★ 3.5ksame name
- aws/agent-toolkit-for-aws★ 3.4ksame name
- spotify/portal-ai-plugins★ 2.8ksame name
181 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
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
- Very specific: line 19
Read ~/.claude/settings.json if it exists.
- Very specific: line 23
Read ~/.claude/codex-status/config if it exists.
- Distinctive: line 29
Ask both in one AskUserQuestion call.
- Very specific: line 69
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, …
“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.
Files
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.jsonif it exists. IfstatusLine.commandis set and does not containstatusline-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/configif it exists. It holds the current choice, onekey=valuea 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.
- Session (several can be chosen): Folder name · Model and effort · Context gauge
- 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 offolder model codex claude ctx, in that ordercountdown:onif "Time until a window resets" was chosen, elseofflight:onif "In-use light" was chosen, elseoff
Then run, with the values filled in:
bash "${CLAUDE_PLUGIN_ROOT}/install.sh" --plugin --show "folder model codex claude ctx" --countdown on --icons on --light onThe script fetches jq into ~/.local/bin if it is missing, backs up settings.json
before changing it, and prints what it did. If it fails, show its output and stop.
4. Report
In a few lines: what is shown now, and that the line appears at the bottom within a
couple of seconds — in a new session at the latest. To change the choice, run
/usage-statusline:setup again. /usage-statusline:refresh fetches the usage numbers
on the spot, /usage-statusline:uninstall removes everything this skill set up.
Add that the icons need a terminal font with Nerd Fonts 3.5 glyphs — without one they
show as empty boxes — and the one line Ghostty needs, from the "Your choice" section of
the plugin's README (${CLAUDE_PLUGIN_ROOT}/README.md).
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
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.

