← Back to Skills Marketplace
ajitsingh25

Claude Code Statusline

by Ajit Singh · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
175
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install claude-code-statusline
Description
Install and configure a custom Claude Code status line showing real-time token usage, context window percentage, git branch, and color-coded warnings. Use wh...
README (SKILL.md)

Claude Code Status Line

Install a security-hardened status line for Claude Code CLI that displays:

user@host:dir (branch) | Model | In:8.5K Out:1.2K Cache:7K [23%]

Prerequisites

  • Python 3 (standard library only, no pip dependencies)
  • git (optional, for branch display)

Script

scripts/statusline_installer.py -- Python 3, standard library only.

# Install with defaults
python3 scripts/statusline_installer.py install

# Install with custom thresholds
python3 scripts/statusline_installer.py install --threshold-yellow 30 --threshold-orange 50 --threshold-red 70

# Install with combined token display
python3 scripts/statusline_installer.py install --token-display combined

# Check installation
python3 scripts/statusline_installer.py status

# Update config
python3 scripts/statusline_installer.py configure --threshold-red 80 --color-green cyan

# Remove
python3 scripts/statusline_installer.py uninstall [--remove-config]

How It Works

  1. install -- Copies statusline.py to ~/.claude/scripts/, creates config at ~/.claude/statusline.config (perms 600), updates ~/.claude/settings.local.json with python3 ~/.claude/scripts/statusline.py command.

  2. status -- JSON output: script installed, config state, settings configured, git availability.

  3. configure -- Update thresholds (--threshold-yellow/orange/red), colors (--color-green/yellow/orange/red), display mode (--token-display separate|combined). Validates threshold ordering.

  4. uninstall -- Removes script, reverts settings. --remove-config also deletes config file.

Configuration

Config file: ~/.claude/statusline.config

Option Default Values
TOKEN_DISPLAY separate separate (In/Out/Cache), combined (total)
THRESHOLD_YELLOW 40 0-100
THRESHOLD_ORANGE 50 0-100
THRESHOLD_RED 70 0-100
COLOR_* standard ANSI Color name or ANSI code

Available colors: green, yellow, orange, red, blue, cyan, magenta, purple, white, pink, bright-green, bright-yellow, bright-red, bright-blue, bright-cyan, bright-magenta.

After Install

Restart Claude Code (exit then claude) to activate.

Usage Guidance
This skill appears to do what it claims: a local status line and installer that writes files under ~/.claude and updates your Claude Code settings.json. Before installing: (1) Inspect the bundled scripts (they're included) if you have any doubt. (2) Back up ~/.claude/settings.json (the installer modifies this file). (3) Note the documentation mismatch: SKILL.md mentions settings.local.json but the installer updates settings.json — expect the latter. (4) The installer and script run entirely locally (no network calls), but they will add persistent entries to your Claude Code config; uninstall removes those entries. If you want extra caution, run the installer in a controlled environment or review/execute the copy steps manually instead of running the install command.
Capability Analysis
Type: OpenClaw Skill Name: claude-code-statusline Version: 1.0.0 The skill bundle provides a utility to install and configure a custom status line for the Claude Code CLI. The implementation is high-quality and includes explicit security hardening measures such as strict file permission checks (600/400), symlink protection, input sanitization (stripping ANSI and control characters), and whitelisted configuration keys. No malicious behaviors like data exfiltration, unauthorized network access, or suspicious execution patterns were found; subprocess calls are restricted to local git commands with hardcoded arguments and no shell execution.
Capability Assessment
✓ Purpose & Capability
Name/description match the delivered artifacts: a statusline renderer (statusline.py) and an installer (statusline_installer.py). The code only touches ~/.claude, reads JSON from stdin (the expected Claude Code runtime input), optionally calls git for branch info, and writes a local config file. No unrelated credentials, binaries, or remote installs are requested.
ℹ Instruction Scope
SKILL.md's runtime instructions align with the installer usage (install/configure/status/uninstall). One small mismatch: SKILL.md says it 'updates ~/.claude/settings.local.json', but the installer updates ~/.claude/settings.json (and cleans settings.local.json). Apart from that documentation mismatch, the instructions do not ask the agent to read or transmit unrelated system data or external endpoints.
✓ Install Mechanism
There is no network download/install in the spec — installation is performed by running the bundled installer script which copies local files into ~/.claude. No package managers or external URLs are used, lowering install risk.
✓ Credentials
The skill requires no environment variables or external credentials. The scripts read USER and use standard os.environ when invoking git (to disable prompts) and operate only under the user's home directory. The workspace path is taken from the JSON input (expected for showing git branch).
ℹ Persistence & Privilege
The installer persistently writes files under ~/.claude, creates a config (~/.claude/statusline.config), and injects a statusLine command into ~/.claude/settings.json so the status line runs when Claude Code starts. This is expected for a UI plugin but is a persistent change to application settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install claude-code-statusline
  3. After installation, invoke the skill by name or use /claude-code-statusline
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
claude-code-statusline v1.0.0 - Initial release of a custom status line installer for Claude Code CLI. - Displays real-time token usage, context window percentage, git branch, and color-coded warnings. - Simple Python 3 script with no external dependencies. - Interactive options to install, check status, configure thresholds/colors, and uninstall. - Fully customizable through a security-hardened config file. - Includes support for combined or separate token display and multiple color options.
Metadata
Slug claude-code-statusline
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Claude Code Statusline?

Install and configure a custom Claude Code status line showing real-time token usage, context window percentage, git branch, and color-coded warnings. Use wh... It is an AI Agent Skill for Claude Code / OpenClaw, with 175 downloads so far.

How do I install Claude Code Statusline?

Run "/install claude-code-statusline" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Claude Code Statusline free?

Yes, Claude Code Statusline is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Claude Code Statusline support?

Claude Code Statusline is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Claude Code Statusline?

It is built and maintained by Ajit Singh (@ajitsingh25); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments