agentleFS
freemafreema/ai-skills/skills/usage-statusline/SKILL.md

usage-statusline

Skill5 starsChanged 19 days agoMITView on GitHub

Install a Claude Code status line that shows the model, context fill as a coloured bar with tokens used, and on Pro/Max plans the 5-hour and 7-day usage with time until each limit resets. One install script copies it to a stable path and sets statusLine in ~/.claude/settings.json, backing the file up first. Use when the user wants to see context or plan usage at a glance, asks when their limit resets, or wants the same status line on another machine. Triggers: 'status line', 'statusline', 'show context usage', 'when does my limit reset', 'how much of my plan is left', 'install my status line', 'kolik mám kontextu', 'kdy se resetuje limit', 'dej mi statusline'.

1 other project uses a version of this.

Adopted by

Most recently taken up by

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:

    If a different status line is already configured, the script stops with exit code 2 and prints the current command.

    line 39

≈ “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

Usage Status Line

One line under the prompt:

Opus 5.5 │ ctx ████░░░░░░ 42% 84k/200k │ 5h 31% ↻2h13m │ 7d 12% ↻4d3h
PartMeaning
Opus 5.5Current model
ctx ████░░░░░░ 42%Context window fill. Green below 50 %, yellow to 80 %, red above
84k/200kTokens in the current context / window size
5h 31% ↻2h13mShare of the 5-hour plan limit used, time until it resets
7d 12% ↻4d3hThe same for the 7-day limit

The 5h and 7d parts come from the rate_limits field Claude Code passes to status lines on Pro and Max plans. They appear after the session's first response; API-key sessions never show them.

Install

Requires jq. Run:

"${CLAUDE_PLUGIN_ROOT}/scripts/install.sh"

It copies scripts/statusline.sh to ~/.claude/usage-statusline.sh and sets the top-level statusLine in ~/.claude/settings.json. A plugin cannot set that key itself, and the plugin's own path changes with every update, hence the copy. Re-run the script after updating the plugin.

If a different status line is already configured, the script stops with exit code 2 and prints the current command. Show it to the user and run with --force only if they want it replaced; settings.json is backed up to settings.json.bak.<timestamp> before any change. Honours CLAUDE_CONFIG_DIR.

The line shows up on the next refresh — after the next message, or after a restart of Claude Code.

Verify

Feed the script sample input; it should print one coloured line:

echo '{"model":{"display_name":"Opus 5.5"},"context_window":{"used_percentage":42,"context_window_size":200000,"current_usage":{"input_tokens":84000}}}' \
  | ~/.claude/usage-statusline.sh

usage-statusline: jq not installed means jq is missing from the PATH Claude Code runs the status line with.

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.