skills/statusline-setup/SKILL.md
This skill should be used when the user asks to "create a status line", "customize status line", "set up statusline", "configure Claude Code status bar", "install ccstatusline", "add project colors to status line", "show git branch in status", "display token usage", or mentions Peacock colors, powerline, or status line configuration.
npx skillsauth add b-open-io/prompts statusline-setupInstall 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.
Create and customize Claude Code status lines to display contextual information like model name, git branch, token usage, project colors, and more.
Claude Code supports custom status lines displayed at the bottom of the interface. Status lines update when conversation messages change, running at most every 300ms.
When setting up a status line, first check for existing configuration and use AskUserQuestion to gather preferences.
# Check for existing configuration
if [[ -f ~/.claude/settings.json ]]; then
EXISTING=$(jq -r '.statusLine // empty' ~/.claude/settings.json)
if [[ -n "$EXISTING" ]]; then
# User has existing status line - ask about backup
fi
fi
Create a shell script that receives JSON data via stdin and outputs a single line with ANSI colors.
Quick setup:
cat > ~/.claude/statusline.sh << 'EOF'
#!/bin/bash
input=$(cat)
MODEL=$(echo "$input" | jq -r '.model.display_name')
DIR=$(basename "$(echo "$input" | jq -r '.workspace.current_dir')")
echo "[$MODEL] $DIR"
EOF
chmod +x ~/.claude/statusline.sh
Configure in settings:
{
"statusLine": {
"type": "command",
"command": "~/.claude/statusline.sh",
"padding": 0
}
}
Use the third-party ccstatusline for a widget-based approach with TUI configuration.
Quick setup:
bunx ccstatusline@latest
Configure in settings:
{
"statusLine": "bunx ccstatusline@latest"
}
The status line command receives structured JSON via stdin:
| Field | Description |
|-------|-------------|
| model.id | Model identifier (e.g., "provider/model-id") |
| model.display_name | Human-readable name (e.g., "Opus") |
| workspace.current_dir | Current working directory |
| workspace.project_dir | Original project directory |
| cost.total_cost_usd | Session cost in USD |
| cost.total_duration_ms | Total session duration |
| context_window.context_window_size | Max context size |
| context_window.current_usage | Current token usage object |
| transcript_path | Path to session transcript JSON |
| session_id | Unique session identifier |
if git rev-parse --git-dir > /dev/null 2>&1; then
BRANCH=$(git branch --show-current 2>/dev/null)
DIRTY=""
git diff --quiet HEAD 2>/dev/null || DIRTY="*"
echo "[$MODEL] $BRANCH$DIRTY"
fi
USAGE=$(echo "$input" | jq '.context_window.current_usage')
if [ "$USAGE" != "null" ]; then
TOKENS=$(echo "$USAGE" | jq '.input_tokens + .cache_creation_input_tokens + .cache_read_input_tokens')
SIZE=$(echo "$input" | jq -r '.context_window.context_window_size')
PERCENT=$((TOKENS * 100 / SIZE))
echo "Context: ${PERCENT}%"
fi
SETTINGS=".vscode/settings.json"
if [[ -f "$SETTINGS" ]]; then
COLOR=$(jq -r '.["peacock.color"] // empty' "$SETTINGS")
fi
FILE_URL="vscode://file${LAST_FILE}"
echo -e "\033]8;;${FILE_URL}\a${FILENAME}\033]8;;\a"
For detailed implementation guidance, consult:
references/json-input-schema.md — Complete JSON input documentation with all fields, extraction examples in Bash/Python/Node.js, and null-value handlingreferences/scripting-patterns.md — ANSI color codes (256-color and true color), Powerline separators, Git integration patterns, project detection, clickable links (OSC 8), terminal integration, and formatting helpersreferences/ccstatusline-guide.md — Complete widget documentation, installation, configuration options, available widgets, multi-line setup, and troubleshootingtools
This skill should be used when a Claude Code session needs to keep working after Anthropic usage runs out, or when the user asks to run the Claude Code harness on GPT-5.6 Sol. Trigger phrases include "my Anthropic usage ran out", "I'm out of Claude usage", "usage limit reached, what now", "keep working on another model", "run Claude Code on GPT-5.6 Sol", "use GPT-5.6 Sol as the model", "set up claudex", "claudex isn't working", "route the harness through CLIProxyAPI", or "bill against my ChatGPT/Codex subscription". It stands up a local proxy so the Claude Code CLI runs on OpenAI's Codex backend as an escape hatch, and diagnoses that setup when it drifts. macOS + Homebrew.
testing
This skill should be used when the user asks to "open Visual Wayfinder", "answer a Wayfinder ticket visually", "turn this decision into a configurator", "show Wayfinder choices as a dashboard", "prototype the Wayfinder questionnaire", or wants interactive choice cards, tradeoff controls, rankings, ranges, toggles, and consequence previews for one active Wayfinder decision. It wraps the Wayfinder skill and JSON Render; it never replaces the tracker or resolves more than the active decision.
development
This skill should be used when the user asks to "make a visual proposal", "write this up so I can share it", "present these options visually", "diagram the trade-offs", "turn this plan into something reviewable", or requests a shareable design pitch, architecture proposal, RFC, options comparison, or visual roadmap for work that has not been built. It produces one self-contained, theme-aware HTML page led by grounded diagrams. Use visual-review instead for completed code changes; do not use this skill for internal task tracking.
tools
This skill should be used when the user asks to "add plugin settings", "make a plugin configurable", "store per-project plugin configuration", "use settings.local.json", "create a plugin state file", "expose skill settings in Agent Master", or "add a skill interface". Distinguishes official Claude Code settings from project-owned configuration and documents bOpen Agent Master skill interface discovery.