dEitY719dEitY719/claudecode-skills/skills/statusline-setup/SKILL.md

statusline-setup

Skill0 starsChanged 2 months agoMITView on GitHub

Install this repo's bundled Claude Code status line (model, branch, context, tokens) and set settings.json's statusLine. Use on "상태줄 설치해줘", "statusline 세팅", "/claudecode:statusline-setup". Custom status lines: the built-in `statusline-setup` agent.

Reads credentials
Installs packages

4 other projects use a version of this.

Adopted by

Most recently taken up by

paulCalvert/claude-code-skillstheir own version, first seen Aug 11, 2026
fotoflo/claude-skillstheir own version, first seen Jun 19, 2026
suhaasteja/claude-decktheir own version, first seen Mar 30, 2026
master5d/claude-personal-skillstheir own version, first seen Mar 28, 2026

Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
fotoflo/claude-skills★ 2same name
paulCalvert/claude-code-skills★ 1same name
suhaasteja/claude-deck★ 1same name
master5d/claude-personal-skills★ 0same name
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.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- cache-ttlSkill

The file

We split this skill into the rules it gives an agent

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

0
Common
Most of the 4 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
If the argument is -h, --help, or help, read references/help.md and follow it, then stop.
line 27
Very specific:
Only when the user asked for the cost segment or ~/.dotfiles-setup-mode reads internal, and .env.CLAUDE_STATUSLINE_USAGE_ID is absent from …
line 38
Very specific:
You: ask — the script never prompts (a read would hang).
line 44
Very specific:
Run --dry-run first with the same flags — a bare one hides the env keys — and show that output before writing.
line 62

“Common” is measured: kept by at least 6 in 10 of the 4 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

Status Line Installer

Copies two bundled scripts into the Claude config dir and sets statusLine (plus, on request, three env keys) in settings.json, preserving every other key.

Help

If the argument is -h, --help, or help, read references/help.md and follow it, then stop.

Step 1: Check the prerequisites

jq on PATH — the script exits 3 with an install hint otherwise.
bash 4.4+ — statusline-command.sh uses associative arrays under #!/bin/bash; check /bin/bash --version. macOS ships 3.2 and brew install bash cannot change that.

Step 2: Ask for the Bedrock cost values, if this machine needs them

Only when the user asked for the cost segment or ~/.dotfiles-setup-mode reads internal, and .env.CLAUDE_STATUSLINE_USAGE_ID is absent from ${CLAUDE_CONFIG_DIR:-$HOME/.claude}/settings.json: ask for the usage id, the usage-API URL, and a budget if not 175. Otherwise skip silently — omitted flags leave any usage keys already in settings.json, and the cost segment, untouched.

You ask — the script never prompts (a read would hang); pass the answers as Step 3 flags.

Step 3: Preview, then install

Paste the locator block from references/run-script.md (the only place this skill spells the path), then:

sh "$_SL" --dry-run                                      # then, to install:
sh "$_SL" [--usage-id ID --usage-api URL] [--budget N]   # flags only if Step 2 asked

Option	Description	Default
`--dry-run`	print what would happen, write nothing	off
`--usage-id ID`	set `env.CLAUDE_STATUSLINE_USAGE_ID`	unset — key left as-is
`--usage-api URL`	set `env.CLAUDE_STATUSLINE_USAGE_API`	unset — key left as-is
`--budget N`	set `env.CLAUDE_STATUSLINE_BUDGET`, positive integer	unset — key left as-is; the status line renders 175

Run --dry-run first with the same flags — a bare one hides the env keys — and show that output before writing. Target is ${CLAUDE_CONFIG_DIR:-$HOME/.claude}; export it per account. Never hand-write jq or copy the assets.

Step 4: Report

On exit 0, prefix [OK] to the script's own output and relay it verbatim:

[OK] statusLine.command = /home/you/.claude/statusline-command.sh
env.CLAUDE_STATUSLINE_USAGE_ID = <id>
file: /home/you/.claude/settings.json
Restart Claude Code to pick it up.

An env.* line appears only for a key that is set. On a non-zero exit print [FAIL] exit=<n> and relay stderr verbatim. Internals: references/behaviour.md.

Failure modes — read the exit, do not work around it

Exit	Meaning	Correct response
2	unknown argument, missing flag value, or a `--budget` that is not a positive integer	fix the invocation; see `--help`
3	`jq` not on PATH	relay the install hint the script printed; stop
4	`settings.json` is not valid JSON	a `.bak` was saved and nothing was written; tell the user to fix the JSON
5	a bundled asset is missing	the skill install is damaged; reinstall the plugin

Constraints

Touches statusLine and the three CLAUDE_STATUSLINE_* keys under env, nothing else — never model, hooks, permissions, or another env entry.
Self-contained: no dotfiles checkout, no file outside this skill; the status line calls the usage API only when --usage-id and --usage-api were given.
The assets are a point-in-time snapshot of dEitY719/dotfiles (commit b23e4d9) with one sanctioned deviation; they do not track upstream. Never patch a copied asset in place. Full rules: references/re-bundling.md.

Related Skills

claudecode:cache-ttl edits the same settings.json with the same lossless merge.

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.

Check your setup, free