Privacy and advertising choices
Git-Stars uses essential storage for site operation. Optional analytics and ad-measurement scripts stay disabled unless you accept them; partners such as Google may then use cookies or similar identifiers where required. Privacy Policy
A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress
This repository page has enough original analysis, source evidence, and comparison context to be treated as an indexable Git-Stars review.
100
review score
Problem solved
Claude Code sessions are opaque—users can't easily see how full their context window is, which tools are running, or what subagents are doing. Claude HUD solves this by surfacing native token data, tool calls, agent states, and task progress directly in the terminal, reducing guesswork and surprise context overflows.
Deployment reality
The available setup signal starts with: /plugin marketplace add jarrodwatts/claude-hud && /plugin install claude-hud. Treat this as a starting point, then ask Codex or Claude to inspect the README, environment variables, runtime version, and deployment target before production use.
Commercial use
The recorded license is MIT. This is a useful commercial-use signal, but teams should still verify license text, dependencies, model/API terms, and trademark constraints.
Capability ceiling
Developers can build more transparent and controllable AI-assisted coding workflows. Real-world uses include monitoring context limits during long refactoring sessions, tracking parallel subagent tasks, and keeping an eye on tool execution order. The ceiling is a fully instrumented Claude Code environment where every resource usage and agent action is visible, enabling precise debugging and optimization of AI interactions.
Git-Stars is independent and not affiliated with GitHub or this project. Analysis may be AI-assisted and based on public repository metadata plus short README-derived summaries. We do not mirror full README files, docs, issues, or social comments.
jarrodwatts/claude-hud is tracked as a JavaScript project in the AI Agent, Developer Tool area. This evaluation combines public GitHub metadata, category signals, short source summaries, and Git-Stars editorial rules rather than copying project documentation.
Momentum check: the repository has 27k total stars, with +0 today, +289 this week, and +0 this month. These growth windows help distinguish durable adoption from short-lived visibility spikes.
Maintenance check: current activity is Moderate; the latest push was 33 days ago, and the open issue queue is 7, about 0.03% of total stars. Treat this as an adoption signal, not a substitute for engineering due diligence.
Adoption check: 1.2k forks and 27k watchers suggest how often the project is reused or followed. License signal: MIT. Always verify license compatibility before commercial or internal use.
Practical fit: this project is most relevant when you need developer workflow automation and command-line tooling. Be cautious when you need a legal review, security audit, or production SLA.
Source check: Git-Stars currently has 2 explicit source reference(s) for this report and a recent growth signal of 289. Follow the original GitHub repository for final install, security, and release information.
Analysis
ReadyOriginal problem, capability, and verdict guidance are available.
Sources
ReadyRepository metadata and README/source references are attached.
License
ReadyMIT is recorded for review.
Maintenance
ReadyRecent activity is visible in repository metadata.
Alternatives
ReadyEnough nearby projects exist for comparison.
Momentum
27k Stars
Reuse
1.2k Forks
Attention
27k Watchers
Maintenance
moderate
License
MIT
Open issues
7
Claude HUD is a plugin for Claude Code that displays real-time information about context usage, active tools, running agents, and todo progress directly below the input line in the terminal.
Key Features
- Real-time context health bar showing usage percentage with color thresholds - Live tool activity tracking (read, edit, search) and subagent status display - Todo progress tracking and customizable HUD layout (Full/Essential/Minimal presets)
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
Developer Tool
Tools that improve coding, testing, build, and local workflow
/plugin marketplace add jarrodwatts/claude-hud && /plugin install claude-hud70
Health Score
Moderate
Commit Activity
Jan 2, 2026
Created
Jul 21, 2026
Last push
+31
Today's growth
+31
7-day growth
+31
30-day growth
Forks
Open
Watchers
jarrodwatts
GitHub profilecodecrafters-io/build-your-own-x
Master programming by recreating your favorite technologies from scratch.
nilbuild/developer-roadmap
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
practical-tutorials/project-based-learning
Curated list of project-based tutorials
obra/superpowers
An agentic skills framework & software development methodology that works.
react/react
The library for web and native user interfaces.
✓
License
✓
Forked
~ Moderate
Maintained
Problem Solved
Claude Code sessions are opaque—users can't easily see how full their context window is, which tools are running, or what subagents are doing. Claude HUD solves this by surfacing native token data, tool calls, agent states, and task progress directly in the terminal, reducing guesswork and surprise context overflows.
Capabilities
Developers can build more transparent and controllable AI-assisted coding workflows. Real-world uses include monitoring context limits during long refactoring sessions, tracking parallel subagent tasks, and keeping an eye on tool execution order. The ceiling is a fully instrumented Claude Code environment where every resource usage and agent action is visible, enabling precise debugging and optimization of AI interactions.
Bottom Line
Claude HUD is ideal for Claude Code power users who want deep visibility into their AI sessions, especially those working on complex, long-running tasks. Minimalists or users who find extra UI distracting should skip it. The key trade-off is richer insight at the cost of a busier terminal display.