claude-hud-statusline
A Claude Code plugin that displays a real-time HUD showing context usage, active tools, running agents, and todo progress in your terminal statusline.
What this skill does
# Claude HUD
> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.
Claude HUD is a Claude Code plugin that adds a persistent statusline to your terminal showing real-time context window usage, active tool calls, running subagents, and todo progress — always visible below your input prompt.
## What It Does
| Feature | Description |
|---------|-------------|
| **Context health** | Visual bar showing how full your context window is (green → yellow → red) |
| **Tool activity** | Live display of file reads, edits, and searches as they happen |
| **Agent tracking** | Shows which subagents are running and what they're doing |
| **Todo progress** | Real-time task completion tracking |
| **Usage limits** | Claude subscriber rate limit consumption |
| **Git status** | Current branch, dirty state, ahead/behind remote |
## Requirements
- Claude Code v1.0.80+
- Node.js 18+ or Bun
## Installation
Run these commands inside a Claude Code session:
**Step 1: Add the marketplace**
```
/plugin marketplace add jarrodwatts/claude-hud
```
**Step 2: Install the plugin**
```
/plugin install claude-hud
```
> **Linux users**: If you get `EXDEV: cross-device link not permitted`, set TMPDIR first:
> ```bash
> mkdir -p ~/.cache/tmp && TMPDIR=~/.cache/tmp claude
> ```
**Step 3: Configure the statusline**
```
/claude-hud:setup
```
> **Windows users**: If setup reports no JavaScript runtime, install Node.js LTS first:
> ```powershell
> winget install OpenJS.NodeJS.LTS
> ```
**Step 4: Restart Claude Code** to load the new `statusLine` config.
## What You See
### Default 2-line layout
```
[Opus] │ my-project git:(main*)
Context █████░░░░░ 45% │ Usage ██░░░░░░░░ 25% (1h 30m / 5h)
```
### With optional lines enabled
```
[Opus] │ my-project git:(main*)
Context █████░░░░░ 45% │ Usage ██░░░░░░░░ 25% (1h 30m / 5h)
◐ Edit: auth.ts | ✓ Read ×3 | ✓ Grep ×2
◐ explore [haiku]: Finding auth code (2m 15s)
▸ Fix authentication bug (2/5)
```
## Configuration
### Interactive configuration (recommended)
```
/claude-hud:configure
```
This opens a guided flow with preset options:
| Preset | Shows |
|--------|-------|
| **Full** | Everything — tools, agents, todos, git, usage, duration |
| **Essential** | Activity lines + git, minimal clutter |
| **Minimal** | Model name and context bar only |
### Manual configuration
Edit `~/.claude/plugins/claude-hud/config.json` directly:
```json
{
"lineLayout": "expanded",
"pathLevels": 2,
"elementOrder": ["project", "context", "usage", "tools", "agents", "todos"],
"gitStatus": {
"enabled": true,
"showDirty": true,
"showAheadBehind": true,
"showFileStats": false
},
"display": {
"showModel": true,
"showContextBar": true,
"contextValue": "percent",
"showUsage": true,
"usageBarEnabled": true,
"showTools": true,
"showAgents": true,
"showTodos": true,
"showDuration": false,
"showSpeed": false,
"showConfigCounts": false,
"showMemoryUsage": false,
"showSessionName": false,
"showClaudeCodeVersion": false,
"sevenDayThreshold": 80,
"showTokenBreakdown": true
},
"colors": {
"context": "green",
"usage": "brightBlue",
"warning": "yellow",
"usageWarning": "brightMagenta",
"critical": "red",
"model": "cyan",
"project": "yellow",
"git": "magenta",
"gitBranch": "cyan",
"label": "dim",
"custom": "208"
}
}
```
## Key Configuration Options
### Layout
```json
{
"lineLayout": "expanded", // "expanded" (multi-line) or "compact" (single line)
"pathLevels": 1 // 1-3 directory levels in project path
}
```
Path level examples:
- `1` → `[Opus] │ my-project git:(main)`
- `2` → `[Opus] │ apps/my-project git:(main)`
- `3` → `[Opus] │ dev/apps/my-project git:(main)`
### Context display formats
```json
{
"display": {
"contextValue": "percent" // "45%"
// "contextValue": "tokens" // "45k/200k"
// "contextValue": "remaining" // "55% remaining"
// "contextValue": "both" // "45% (45k/200k)"
}
}
```
### Element ordering (expanded layout)
```json
{
"elementOrder": ["project", "context", "usage", "memory", "environment", "tools", "agents", "todos"]
}
```
Omit any entry from the array to hide it entirely.
### Git status options
```json
{
"gitStatus": {
"enabled": true,
"showDirty": true, // "main*" for uncommitted changes
"showAheadBehind": true, // "main ↑2 ↓1"
"showFileStats": true // "main* !3 +1 ?2" (modified/added/deleted/untracked)
}
}
```
### Colors
Supported values: named colors (`dim`, `red`, `green`, `yellow`, `magenta`, `cyan`, `brightBlue`, `brightMagenta`), 256-color numbers (`0-255`), or hex (`#rrggbb`).
```json
{
"colors": {
"context": "#00FF88",
"model": "208",
"project": "#FF6600"
}
}
```
## How It Works
Claude HUD uses Claude Code's native **statusline API** — no separate window, no tmux needed:
```
Claude Code → stdin JSON → claude-hud → stdout → terminal statusline
↘ transcript JSONL (tools, agents, todos parsed live)
```
- Token data comes directly from Claude Code (not estimated)
- Scales with reported context window size including 1M-context sessions
- Parses transcript for tool/agent activity
- Updates every ~300ms
## Common Patterns
### Minimal setup for focused work
```json
{
"lineLayout": "compact",
"display": {
"showModel": true,
"showContextBar": true,
"contextValue": "percent",
"showUsage": false,
"showTools": false,
"showAgents": false,
"showTodos": false
}
}
```
### Full monitoring setup
```json
{
"lineLayout": "expanded",
"pathLevels": 2,
"gitStatus": {
"enabled": true,
"showDirty": true,
"showAheadBehind": true,
"showFileStats": true
},
"display": {
"showTools": true,
"showAgents": true,
"showTodos": true,
"showDuration": true,
"showMemoryUsage": true,
"showConfigCounts": true,
"contextValue": "both",
"showTokenBreakdown": true
}
}
```
### Always show 7-day usage
```json
{
"display": {
"showUsage": true,
"sevenDayThreshold": 0
}
}
```
Output: `Context █████░░░░░ 45% │ Usage ██░░░░░░░░ 25% (1h 30m / 5h) | ██████████ 85% (2d / 7d)`
## Troubleshooting
**HUD not appearing after setup**
- Fully restart Claude Code (quit and re-run `claude` in terminal)
- On macOS, ensure you've fully quit the app, not just closed the window
**Config not applying**
- Check for JSON syntax errors — invalid JSON silently falls back to defaults
- Validate: `cat ~/.claude/plugins/claude-hud/config.json | node -e "JSON.parse(require('fs').readFileSync('/dev/stdin','utf8'))"`
- Delete config and run `/claude-hud:configure` to regenerate
**Git status missing**
- Verify you're in a git repository (`git status`)
- Ensure `gitStatus.enabled` is not `false` in config
**Tool/agent/todo lines not showing**
- These are hidden by default — enable with `showTools`, `showAgents`, `showTodos`
- Lines only render when there's active activity to display
**Usage limits not showing**
- Requires a Claude subscriber account (not API key only)
- AWS Bedrock users see `Bedrock` label; usage is managed in AWS console instead
- Usage data may be empty until after the first model response in a new session
- Older Claude Code versions that don't emit `rate_limits` won't show subscriber usage
**Linux cross-device error on install**
```bash
mkdir -p ~/.cache/tmp && TMPDIR=~/.cache/tmp claude
# Then run /plugin install claude-hud inside that session
```
**Windows: no JavaScript runtime found**
```powershell
winget install OpenJS.NodeJS.LTS
# Restart shell, then run /claude-hud:setup again
```
## Plugin Commands Reference
| Command | Description |
|---------|-------------|
| `/plugin marketplace add jarrodwatts/claude-hud` | Register the plugin source |
| `/plugin install claude-hud` | Install the plugin |
| `/claude-hud:setup` | Initial setup wizard, writes `statusLine` config |
| `/claude-hud:configure` | InterRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.