plugins/statusline/skills/statusline-customization/SKILL.md
Configuration reference and troubleshooting for the statusline plugin — sections, themes, bar widths, and script architecture
npx skillsauth add madappgang/claude-code statusline-customizationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Location: ~/.claude/statusline-config.json
{
"sections": {
"model": true, // Model name (Opus/Sonnet/Haiku)
"branch": true, // Git branch name
"worktree": true, // Worktree indicator (wt:name)
"cost": true, // Session cost ($X.XX)
"duration": true, // Session duration (Xm Xs)
"context_bar": true, // Context window usage bar
"plan_limits": true // Plan limit bars with reset countdowns
},
"context_bar_width": 12, // Width of context bar in chars (8-20)
"plan_bar_width": 10, // Width of plan limit bar in chars (6-16)
"theme": "default" // Color theme name
}
All fields are optional. Missing fields use defaults shown above.
| Section | Color | Description |
|---------|-------|-------------|
| model | Cyan (bold) | Shortened model name with * prefix |
| branch | Green | Current git branch or short commit hash |
| worktree | Orange (bold) | wt:name — only shown when inside a linked worktree |
| cost | Yellow | Cumulative session cost in USD |
| duration | Magenta | Session duration in minutes/seconds |
| context_bar | Green→Red gradient | Visual bar + token count (90k/200k) + compaction indicator (⟳) |
| plan_limits | Teal→Red gradient | Dual bar: top=5h, bottom=7d plan usage with reset countdowns |
█ — both 5h and 7d usage at this position▀ — only 5h usage (top half)▄ — only 7d usage (bottom half)- — empty (unused capacity)After each percentage, a countdown shows when the limit resets:
↻1h40m — resets in 1 hour 40 minutes↻3d12h — resets in 3 days 12 hours↻now — resetting nowExample: █▄▄------- 5h:18% ↻1h40m 7d:35% ↻3d12h
After the percentage, a dim token count shows current/max context usage:
45% 90k/200k — 90k tokens used out of 200k window72% 144k/200k — approaching limitA bold magenta ⟳ appears after the token count when auto-compaction is detected:
25% 50k/200k ⟳ — compaction just happened (tokens dropped)total_input_tokens between renders; a drop means compaction occurred~/.claude/.statusline-token-cache| Theme | Description |
|-------|-------------|
| default | Warm/cool ANSI palette — bright cyan, green, yellow, orange, red |
| monochrome | White and gray only — no colors |
| minimal | Muted dim ANSI colors (30-series) — subtle and low-contrast |
| neon | 256-color bright variants — vivid and high-contrast |
~/.claude/statusline-config.jsonjqcwd~/.claude/.statusline-usage-cache.json( ... ) & fires API call; current render uses stale cachesecurity find-generic-password -s "Claude Code-credentials")https://api.anthropic.com/api/oauth/usage{
"model": { "display_name": "Claude Opus 4.6" },
"cost": { "total_cost_usd": 1.23, "total_duration_ms": 180000 },
"context_window": { "used_percentage": 45.2 },
"cwd": "/path/to/project"
}
The script requires jq for JSON parsing. Install with:
brew install jq
ls -la ~/.claude/.statusline-usage-cache.jsonsecurity find-generic-password -s "Claude Code-credentials" -w | head -c 20jq . ~/.claude/statusline-config.json/statusline:install-statuslinechmod +x ~/.claude/statusline-command.sh
# or for project-level:
chmod +x .claude/statusline-command.sh
resets_at field in the usage API responsejq '.five_hour.resets_at, .seven_day.resets_at' ~/.claude/.statusline-usage-cache.jsontesting
A test skill for validation testing. Use when testing skill parsing and validation logic.
tools
--- name: bad-skill description: This skill has invalid YAML in frontmatter allowed-tools: [invalid, array, syntax prerequisites: not-an-array --- # Bad Skill This skill has malformed frontmatter that should fail parsing. The YAML has: - Unclosed array bracket - Wrong type for prerequisites (should be array, not string)
tools
Plugin release process for MAG Claude Plugins marketplace. Covers version bumping, marketplace.json updates, git tagging, and common mistakes. Use when releasing new plugin versions or troubleshooting update issues.
testing
Fetch trending programming models from OpenRouter rankings. Use when selecting models for multi-model review, updating model recommendations, or researching current AI coding trends. Provides model IDs, context windows, pricing, and usage statistics from the most recent week.