Install
$ agentstack add skill-assertchris-claude-skills-custom-usage-statusline ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Usage Statusline Setup
This skill configures Claude Code's statusline to display your usage limits (session 5h / weekly 7d) alongside the context window bar.
What It Does
- Reads your OAuth token from the system keychain (no separate login needed)
- macOS: Reads from the macOS Keychain via
security find-generic-password - Linux: Reads from GNOME Keyring via
secret-tool, with fallback to~/.claude/.credentials.json
- Calls the usage API (
GET https://api.anthropic.com/api/oauth/usage) with a 3-second timeout - Caches the response at
/tmp/claude-statusline-usage.jsonfor 60 seconds to avoid hammering the API - Displays context, session, and week percentages in the statusline, each color-coded green/yellow/red based on usage level
- Fails gracefully — if the token is missing, the API is unreachable, or anything errors, the usage section is simply omitted
Requirements
jqmust be installedcurlmust be installed- A valid Claude AI OAuth session (you must be logged into Claude Code)
Instructions
When the user invokes this skill, do the following:
Step 1: Copy the statusline script
Copy the companion script from this skill's directory to ~/.claude/statusline-command.sh:
- Read the file
statusline-command.shfrom this skill's base directory (shown at the top of the skill prompt) - Write its contents to
~/.claude/statusline-command.sh
Step 2: Configure settings.json
Ensure ~/.claude/settings.json contains the statusline configuration. If the file already exists, merge in the statusline key without overwriting other settings:
{
"statusLine": {
"type": "command",
"command": "sh ~/.claude/statusline-command.sh"
}
}
Use the absolute path with $HOME expanded (e.g. sh /Users/username/.claude/statusline-command.sh).
Step 3: Verify
Run the script with test input to confirm it works:
echo '{"model":{"display_name":"Opus 4.6"},"context_window":{"used_percentage":42}}' | sh ~/.claude/statusline-command.sh
The output should show the model name, context bar, and (if authenticated) usage percentages.
Sharing
To share this with colleagues:
- Copy the
~/.claude/skills/custom-usage-statusline/directory to their~/.claude/skills/folder - They can then run
/usage-statuslinein Claude Code to set it up
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: assertchris
- Source: assertchris/claude-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.