by domanski-ai · Codex Skill · ★ 99
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Track and rotate your Claude & Codex usage across accounts from one live dashboard — read live, never spending a token.
| Stars | 99 |
| Forks | 10 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 54.0431458849492/100 |
| Open Issues | 4 |
| Last Updated | 2026-08-25 |
| Created | 2026-07-12 |
| Platforms | claude-code, cli, codex, python |
| Est. Tokens | ~13k |
Looking for a headroom alternative? If you're comparing headroom with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
macOS menu bar & Windows tray app pinning Claude Code, Codex & Antigravity quota, burn rate, and cost to your
10 Claude sessions running. What are they doing? Live dashboard — monitor, cost tracking, search, sub-agent vi
Local-first Windows tray app for monitoring Claude Code and Codex tokens, costs, sessions, and rate limits
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
Claude Code multi-account manager, usage monitor (CLI, TUI & MCP cross-account delegation)
Monitor Claude Code sessions, costs, config, hooks, agents & MCP servers from a single Rust binary — TUI (9 ta
Explore other popular codex skill tools:
headroom is Track and rotate your Claude & Codex usage across accounts from one live dashboard — read live, never spending a token.. It is categorized as a Codex Skill with 99 GitHub stars.
headroom is primarily written in Python. It covers topics such as anthropic, claude, claude-code.
You can find installation instructions and usage details in the headroom GitHub repository at github.com/domanski-ai/headroom. The project has 99 stars and 10 forks, indicating an active community.
headroom is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to headroom on Agent Skills Hub include usage, claude-view, WhereMyTokens. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: