claude hud

Other Community

Skill notes

Step 1: Understand the HUD Architecture

Component · What It Shows · Data Source Context meter · Tokens used / remaining · Agent API response headers Tool tracker · Active tool calls + history · Hook into tool execution Sub-agent panel · Spawned agents + status · Agent orchestration layer Task progress · Todo items + completion · Parse agent task lists

Example 1: Monitor a Claude Code Refactoring Session

A developer launches the HUD while Claude Code refactors a large codebase:

Example 2: Multi-Agent Workflow Dashboard

A team runs 3 agents in parallel and monitors all of them on one HUD:

Guidelines

Keep the HUD lightweight — avoid heavy polling; use WebSocket push for real-time updates Set context alerts at 80% — warn developers before hitting the context window limit Log all events to disk — enable session replay for debugging and optimization Support multiple agents — design the dashboard to handle parallel agent workflows Customize per workflow — different tasks benefit from different widget layouts

References

jarrodwatts/claude-hud — original inspiration blessed-contrib — terminal dashboard widgets Anthropic API usage headers — token counting

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Other
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@TerminalSkills · no license declared
Token usage
Lean
Setup complexity
Guided setup
External API key
Not required
Operating systems
macOS · Linux · Windows
Runtime requirements
No explicit requirements detected
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
Network behavior
Local-only
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

01
Step 1: Understand the HUD Architecture

Component · What It Shows · Data Source Context meter · Tokens used / remaining · Agent API response headers Tool tracker · Active tool calls + history · Hook into tool execution Sub-agent panel · Spawned agents + status · Agent orchestration layer Task progress · Todo items + completion · Parse agent task lists

02
Step 2: Set Up the Project

Step 2: Set Up the Project

03
Step 3: Build the Context Usage Monitor

Step 3: Build the Context Usage Monitor

04
Step 4: Build the Tool Call Tracker

Step 4: Build the Tool Call Tracker

05
Step 5: Build the Terminal Dashboard

Step 5: Build the Terminal Dashboard

06
Step 6: Connect via WebSocket

Step 6: Connect via WebSocket

07
Step 7: Add Cost Tracking

Step 7: Add Cost Tracking

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.